mirror of
https://github.com/kennethreitz/langchain.git
synced 2026-06-05 23:00:18 +00:00
mv module integrations docs (#8101)
This commit is contained in:
Bagatur
Binary file not shown.
|
After Width: | Height: | Size: 875 KiB |
@@ -0,0 +1,168 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Apify\n",
|
||||
"\n",
|
||||
"This notebook shows how to use the [Apify integration](/docs/ecosystem/integrations/apify.html) for LangChain.\n",
|
||||
"\n",
|
||||
"[Apify](https://apify.com) is a cloud platform for web scraping and data extraction,\n",
|
||||
"which provides an [ecosystem](https://apify.com/store) of more than a thousand\n",
|
||||
"ready-made apps called *Actors* for various web scraping, crawling, and data extraction use cases.\n",
|
||||
"For example, you can use it to extract Google Search results, Instagram and Facebook profiles, products from Amazon or Shopify, Google Maps reviews, etc. etc.\n",
|
||||
"\n",
|
||||
"In this example, we'll use the [Website Content Crawler](https://apify.com/apify/website-content-crawler) Actor,\n",
|
||||
"which can deeply crawl websites such as documentation, knowledge bases, help centers, or blogs,\n",
|
||||
"and extract text content from the web pages. Then we feed the documents into a vector index and answer questions from it.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install apify-client openai langchain chromadb tiktoken"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First, import `ApifyWrapper` into your source code:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders.base import Document\n",
|
||||
"from langchain.indexes import VectorstoreIndexCreator\n",
|
||||
"from langchain.utilities import ApifyWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Initialize it using your [Apify API token](https://console.apify.com/account/integrations) and for the purpose of this example, also with your OpenAI API key:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"Your OpenAI API key\"\n",
|
||||
"os.environ[\"APIFY_API_TOKEN\"] = \"Your Apify API token\"\n",
|
||||
"\n",
|
||||
"apify = ApifyWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then run the Actor, wait for it to finish, and fetch its results from the Apify dataset into a LangChain document loader.\n",
|
||||
"\n",
|
||||
"Note that if you already have some results in an Apify dataset, you can load them directly using `ApifyDatasetLoader`, as shown in [this notebook](/docs/modules/data_connection/document_loaders/integrations/apify_dataset.html). In that notebook, you'll also find the explanation of the `dataset_mapping_function`, which is used to map fields from the Apify dataset records to LangChain `Document` fields."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = apify.call_actor(\n",
|
||||
" actor_id=\"apify/website-content-crawler\",\n",
|
||||
" run_input={\"startUrls\": [{\"url\": \"https://python.langchain.com/en/latest/\"}]},\n",
|
||||
" dataset_mapping_function=lambda item: Document(\n",
|
||||
" page_content=item[\"text\"] or \"\", metadata={\"source\": item[\"url\"]}\n",
|
||||
" ),\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Initialize the vector index from the crawled documents:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"index = VectorstoreIndexCreator().from_loaders([loader])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And finally, query the vector index:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"What is LangChain?\"\n",
|
||||
"result = index.query_with_sources(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" LangChain is a standard interface through which you can interact with a variety of large language models (LLMs). It provides modules that can be used to build language model applications, and it also provides chains and agents with memory capabilities.\n",
|
||||
"\n",
|
||||
"https://python.langchain.com/en/latest/modules/models/llms.html, https://python.langchain.com/en/latest/getting_started/getting_started.html\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(result[\"answer\"])\n",
|
||||
"print(result[\"sources\"])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,258 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ArXiv API Tool\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the `arxiv` component. \n",
|
||||
"\n",
|
||||
"First, you need to install `arxiv` python package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d5a7209e",
|
||||
"metadata": {
|
||||
"tags": [],
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install arxiv"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "ce1a4827-ce89-4f31-a041-3246743e513a",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent, AgentType\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0.0)\n",
|
||||
"tools = load_tools(\n",
|
||||
" [\"arxiv\"],\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "ad7dd945-5ae3-49e5-b667-6d86b15050b6",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use Arxiv to search for the paper.\n",
|
||||
"Action: Arxiv\n",
|
||||
"Action Input: \"1605.08386\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mPublished: 2016-05-26\n",
|
||||
"Title: Heat-bath random walks with Markov bases\n",
|
||||
"Authors: Caprice Stanley, Tobias Windisch\n",
|
||||
"Summary: Graphs on lattice points are studied whose edges come from a finite set of\n",
|
||||
"allowed moves of arbitrary length. We show that the diameter of these graphs on\n",
|
||||
"fibers of a fixed integer matrix can be bounded from above by a constant. We\n",
|
||||
"then study the mixing behaviour of heat-bath random walks on these graphs. We\n",
|
||||
"also state explicit conditions on the set of moves so that the heat-bath random\n",
|
||||
"walk, a generalization of the Glauber dynamics, is an expander in fixed\n",
|
||||
"dimension.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThe paper is about heat-bath random walks with Markov bases on graphs of lattice points.\n",
|
||||
"Final Answer: The paper 1605.08386 is about heat-bath random walks with Markov bases on graphs of lattice points.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The paper 1605.08386 is about heat-bath random walks with Markov bases on graphs of lattice points.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\n",
|
||||
" \"What's the paper 1605.08386 about?\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b4183343-d69a-4be0-9b2c-cc98464a6825",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## The ArXiv API Wrapper\n",
|
||||
"\n",
|
||||
"The tool wraps the API Wrapper. Below, we can explore some of the features it provides."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "8d32b39a",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import ArxivAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c89c110c-96ac-4fe1-ba3e-6056543d1a59",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Run a query to get information about some `scientific article`/articles. The query text is limited to 300 characters.\n",
|
||||
"\n",
|
||||
"It returns these article fields:\n",
|
||||
"- Publishing date\n",
|
||||
"- Title\n",
|
||||
"- Authors\n",
|
||||
"- Summary\n",
|
||||
"\n",
|
||||
"Next query returns information about one article with arxiv Id equal \"1605.08386\". "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "34bb5968",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Published: 2016-05-26\\nTitle: Heat-bath random walks with Markov bases\\nAuthors: Caprice Stanley, Tobias Windisch\\nSummary: Graphs on lattice points are studied whose edges come from a finite set of\\nallowed moves of arbitrary length. We show that the diameter of these graphs on\\nfibers of a fixed integer matrix can be bounded from above by a constant. We\\nthen study the mixing behaviour of heat-bath random walks on these graphs. We\\nalso state explicit conditions on the set of moves so that the heat-bath random\\nwalk, a generalization of the Glauber dynamics, is an expander in fixed\\ndimension.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"arxiv = ArxivAPIWrapper()\n",
|
||||
"docs = arxiv.run(\"1605.08386\")\n",
|
||||
"docs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "840f70c9-8f80-4680-bb38-46198e931bcf",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, we want to get information about one author, `Caprice Stanley`.\n",
|
||||
"\n",
|
||||
"This query returns information about three articles. By default, the query returns information only about three top articles."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "b0867fda-e119-4b19-9ec6-e354fa821db3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Published: 2017-10-10\\nTitle: On Mixing Behavior of a Family of Random Walks Determined by a Linear Recurrence\\nAuthors: Caprice Stanley, Seth Sullivant\\nSummary: We study random walks on the integers mod $G_n$ that are determined by an\\ninteger sequence $\\\\{ G_n \\\\}_{n \\\\geq 1}$ generated by a linear recurrence\\nrelation. Fourier analysis provides explicit formulas to compute the\\neigenvalues of the transition matrices and we use this to bound the mixing time\\nof the random walks.\\n\\nPublished: 2016-05-26\\nTitle: Heat-bath random walks with Markov bases\\nAuthors: Caprice Stanley, Tobias Windisch\\nSummary: Graphs on lattice points are studied whose edges come from a finite set of\\nallowed moves of arbitrary length. We show that the diameter of these graphs on\\nfibers of a fixed integer matrix can be bounded from above by a constant. We\\nthen study the mixing behaviour of heat-bath random walks on these graphs. We\\nalso state explicit conditions on the set of moves so that the heat-bath random\\nwalk, a generalization of the Glauber dynamics, is an expander in fixed\\ndimension.\\n\\nPublished: 2003-03-18\\nTitle: Calculation of fluxes of charged particles and neutrinos from atmospheric showers\\nAuthors: V. Plyaskin\\nSummary: The results on the fluxes of charged particles and neutrinos from a\\n3-dimensional (3D) simulation of atmospheric showers are presented. An\\nagreement of calculated fluxes with data on charged particles from the AMS and\\nCAPRICE detectors is demonstrated. Predictions on neutrino fluxes at different\\nexperimental sites are compared with results from other calculations.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs = arxiv.run(\"Caprice Stanley\")\n",
|
||||
"docs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2d9b6292-a47d-4f99-9827-8e9f244bf887",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, we are trying to find information about non-existing article. In this case, the response is \"No good Arxiv Result was found\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "3580aeeb-086f-45ba-bcdc-b46f5134b3dd",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'No good Arxiv Result was found'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs = arxiv.run(\"1605.08386WWW\")\n",
|
||||
"docs"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,121 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## AWS Lambda API"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This notebook goes over how to use the AWS Lambda Tool component.\n",
|
||||
"\n",
|
||||
"AWS Lambda is a serverless computing service provided by Amazon Web Services (AWS), designed to allow developers to build and run applications and services without the need for provisioning or managing servers. This serverless architecture enables you to focus on writing and deploying code, while AWS automatically takes care of scaling, patching, and managing the infrastructure required to run your applications.\n",
|
||||
"\n",
|
||||
"By including a `awslambda` in the list of tools provided to an Agent, you can grant your Agent the ability to invoke code running in your AWS Cloud for whatever purposes you need.\n",
|
||||
"\n",
|
||||
"When an Agent uses the awslambda tool, it will provide an argument of type string which will in turn be passed into the Lambda function via the event parameter.\n",
|
||||
"\n",
|
||||
"First, you need to install `boto3` python package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install boto3 > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In order for an agent to use the tool, you must provide it with the name and description that match the functionality of you lambda function's logic. \n",
|
||||
"\n",
|
||||
"You must also provide the name of your function. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that because this tool is effectively just a wrapper around the boto3 library, you will need to run `aws configure` in order to make use of the tool. For more detail, see [here](https://docs.aws.amazon.com/cli/index.html)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI\n",
|
||||
"from langchain.agents import load_tools, AgentType\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"tools = load_tools(\n",
|
||||
" [\"awslambda\"],\n",
|
||||
" awslambda_tool_name=\"email-sender\",\n",
|
||||
" awslambda_tool_description=\"sends an email with the specified content to test@testing123.com\",\n",
|
||||
" function_name=\"testFunction1\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\"Send an email to test@testing123.com saying hello world.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,192 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8f210ec3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Shell Tool\n",
|
||||
"\n",
|
||||
"Giving agents access to the shell is powerful (though risky outside a sandboxed environment).\n",
|
||||
"\n",
|
||||
"The LLM can use it to execute any shell commands. A common use case for this is letting the LLM interact with your local file system."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f7b3767b",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import ShellTool\n",
|
||||
"\n",
|
||||
"shell_tool = ShellTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "c92ac832-556b-4f66-baa4-b78f965dfba0",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Hello World!\n",
|
||||
"\n",
|
||||
"real\t0m0.000s\n",
|
||||
"user\t0m0.000s\n",
|
||||
"sys\t0m0.000s\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning: The shell tool has no safeguards by default. Use at your own risk.\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(shell_tool.run({\"commands\": [\"echo 'Hello World!'\", \"time\"]}))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2fa952fc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Use with Agents\n",
|
||||
"\n",
|
||||
"As with all tools, these can be given to an agent to accomplish more complex tasks. Let's have the agent fetch some links from a web page."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "851fee9f",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mQuestion: What is the task?\n",
|
||||
"Thought: We need to download the langchain.com webpage and extract all the URLs from it. Then we need to sort the URLs and return them.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"shell\",\n",
|
||||
" \"action_input\": {\n",
|
||||
" \"commands\": [\n",
|
||||
" \"curl -s https://langchain.com | grep -o 'http[s]*://[^\\\" ]*' | sort\"\n",
|
||||
" ]\n",
|
||||
" }\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning: The shell tool has no safeguards by default. Use at your own risk.\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mhttps://blog.langchain.dev/\n",
|
||||
"https://discord.gg/6adMQxSpJS\n",
|
||||
"https://docs.langchain.com/docs/\n",
|
||||
"https://github.com/hwchase17/chat-langchain\n",
|
||||
"https://github.com/hwchase17/langchain\n",
|
||||
"https://github.com/hwchase17/langchainjs\n",
|
||||
"https://github.com/sullivan-sean/chat-langchainjs\n",
|
||||
"https://js.langchain.com/docs/\n",
|
||||
"https://python.langchain.com/en/latest/\n",
|
||||
"https://twitter.com/langchainai\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThe URLs have been successfully extracted and sorted. We can return the list of URLs as the final answer.\n",
|
||||
"Final Answer: [\"https://blog.langchain.dev/\", \"https://discord.gg/6adMQxSpJS\", \"https://docs.langchain.com/docs/\", \"https://github.com/hwchase17/chat-langchain\", \"https://github.com/hwchase17/langchain\", \"https://github.com/hwchase17/langchainjs\", \"https://github.com/sullivan-sean/chat-langchainjs\", \"https://js.langchain.com/docs/\", \"https://python.langchain.com/en/latest/\", \"https://twitter.com/langchainai\"]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'[\"https://blog.langchain.dev/\", \"https://discord.gg/6adMQxSpJS\", \"https://docs.langchain.com/docs/\", \"https://github.com/hwchase17/chat-langchain\", \"https://github.com/hwchase17/langchain\", \"https://github.com/hwchase17/langchainjs\", \"https://github.com/sullivan-sean/chat-langchainjs\", \"https://js.langchain.com/docs/\", \"https://python.langchain.com/en/latest/\", \"https://twitter.com/langchainai\"]'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"shell_tool.description = shell_tool.description + f\"args {shell_tool.args}\".replace(\n",
|
||||
" \"{\", \"{{\"\n",
|
||||
").replace(\"}\", \"}}\")\n",
|
||||
"self_ask_with_search = initialize_agent(\n",
|
||||
" [shell_tool], llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"self_ask_with_search.run(\n",
|
||||
" \"Download the langchain.com webpage and grep for all urls. Return only a sorted list of them. Be sure to use double quotes.\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8d0ea3ac-0890-4e39-9cec-74bd80b4b8b8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,193 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Bing Search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This notebook goes over how to use the bing search component.\n",
|
||||
"\n",
|
||||
"First, you need to set up the proper API keys and environment variables. To set it up, follow the instructions found [here](https://levelup.gitconnected.com/api-tutorial-how-to-use-bing-web-search-api-in-python-4165d5592a7e).\n",
|
||||
"\n",
|
||||
"Then we will need to set some environment variables."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"BING_SUBSCRIPTION_KEY\"] = \"<key>\"\n",
|
||||
"os.environ[\"BING_SEARCH_URL\"] = \"https://api.bing.microsoft.com/v7.0/search\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import BingSearchAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = BingSearchAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Thanks to the flexibility of <b>Python</b> and the powerful ecosystem of packages, the Azure CLI supports features such as autocompletion (in shells that support it), persistent credentials, JMESPath result parsing, lazy initialization, network-less unit tests, and more. Building an open-source and cross-platform Azure CLI with <b>Python</b> by Dan Taylor. <b>Python</b> releases by version number: Release version Release date Click for more. <b>Python</b> 3.11.1 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.10.9 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.9.16 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.8.16 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.7.16 Dec. 6, 2022 Download Release Notes. In this lesson, we will look at the += operator in <b>Python</b> and see how it works with several simple examples.. The operator ‘+=’ is a shorthand for the addition assignment operator.It adds two values and assigns the sum to a variable (left operand). W3Schools offers free online tutorials, references and exercises in all the major languages of the web. Covering popular subjects like HTML, CSS, JavaScript, <b>Python</b>, SQL, Java, and many, many more. This tutorial introduces the reader informally to the basic concepts and features of the <b>Python</b> language and system. It helps to have a <b>Python</b> interpreter handy for hands-on experience, but all examples are self-contained, so the tutorial can be read off-line as well. For a description of standard objects and modules, see The <b>Python</b> Standard ... <b>Python</b> is a general-purpose, versatile, and powerful programming language. It's a great first language because <b>Python</b> code is concise and easy to read. Whatever you want to do, <b>python</b> can do it. From web development to machine learning to data science, <b>Python</b> is the language for you. To install <b>Python</b> using the Microsoft Store: Go to your Start menu (lower left Windows icon), type "Microsoft Store", select the link to open the store. Once the store is open, select Search from the upper-right menu and enter "<b>Python</b>". Select which version of <b>Python</b> you would like to use from the results under Apps. Under the “<b>Python</b> Releases for Mac OS X” heading, click the link for the Latest <b>Python</b> 3 Release - <b>Python</b> 3.x.x. As of this writing, the latest version was <b>Python</b> 3.8.4. Scroll to the bottom and click macOS 64-bit installer to start the download. When the installer is finished downloading, move on to the next step. Step 2: Run the Installer'"
|
||||
]
|
||||
},
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"python\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Number of results\n",
|
||||
"You can use the `k` parameter to set the number of results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = BingSearchAPIWrapper(k=1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Thanks to the flexibility of <b>Python</b> and the powerful ecosystem of packages, the Azure CLI supports features such as autocompletion (in shells that support it), persistent credentials, JMESPath result parsing, lazy initialization, network-less unit tests, and more. Building an open-source and cross-platform Azure CLI with <b>Python</b> by Dan Taylor.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"python\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Metadata Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Run query through BingSearch and return snippet, title, and link metadata.\n",
|
||||
"\n",
|
||||
"- Snippet: The description of the result.\n",
|
||||
"- Title: The title of the result.\n",
|
||||
"- Link: The link to the result."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = BingSearchAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[{'snippet': 'Lady Alice. Pink Lady <b>apples</b> aren’t the only lady in the apple family. Lady Alice <b>apples</b> were discovered growing, thanks to bees pollinating, in Washington. They are smaller and slightly more stout in appearance than other varieties. Their skin color appears to have red and yellow stripes running from stem to butt.',\n",
|
||||
" 'title': '25 Types of Apples - Jessica Gavin',\n",
|
||||
" 'link': 'https://www.jessicagavin.com/types-of-apples/'},\n",
|
||||
" {'snippet': '<b>Apples</b> can do a lot for you, thanks to plant chemicals called flavonoids. And they have pectin, a fiber that breaks down in your gut. If you take off the apple’s skin before eating it, you won ...',\n",
|
||||
" 'title': 'Apples: Nutrition & Health Benefits - WebMD',\n",
|
||||
" 'link': 'https://www.webmd.com/food-recipes/benefits-apples'},\n",
|
||||
" {'snippet': '<b>Apples</b> boast many vitamins and minerals, though not in high amounts. However, <b>apples</b> are usually a good source of vitamin C. Vitamin C. Also called ascorbic acid, this vitamin is a common ...',\n",
|
||||
" 'title': 'Apples 101: Nutrition Facts and Health Benefits',\n",
|
||||
" 'link': 'https://www.healthline.com/nutrition/foods/apples'},\n",
|
||||
" {'snippet': 'Weight management. The fibers in <b>apples</b> can slow digestion, helping one to feel greater satisfaction after eating. After following three large prospective cohorts of 133,468 men and women for 24 years, researchers found that higher intakes of fiber-rich fruits with a low glycemic load, particularly <b>apples</b> and pears, were associated with the least amount of weight gain over time.',\n",
|
||||
" 'title': 'Apples | The Nutrition Source | Harvard T.H. Chan School of Public Health',\n",
|
||||
" 'link': 'https://www.hsph.harvard.edu/nutritionsource/food-features/apples/'}]"
|
||||
]
|
||||
},
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.results(\"apples\", 5)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,94 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eda326e4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Brave Search\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the Brave Search tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a4c896e5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import BraveSearch"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6784d37c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"api_key = \"BSAv1neIuQOsxqOyy0sEe_ie2zD_n_V\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5b14008a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={\"count\": 3})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f11937b2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'[{\"title\": \"Obama\\'s Middle Name -- My Last Name -- is \\'Hussein.\\' So?\", \"link\": \"https://www.cair.com/cair_in_the_news/obamas-middle-name-my-last-name-is-hussein-so/\", \"snippet\": \"I wasn\\\\u2019t sure whether to laugh or cry a few days back listening to radio talk show host Bill Cunningham repeatedly scream Barack <strong>Obama</strong>\\\\u2019<strong>s</strong> <strong>middle</strong> <strong>name</strong> \\\\u2014 my last <strong>name</strong> \\\\u2014 as if he had anti-Muslim Tourette\\\\u2019s. \\\\u201cHussein,\\\\u201d Cunningham hissed like he was beckoning Satan when shouting the ...\"}, {\"title\": \"What\\'s up with Obama\\'s middle name? - Quora\", \"link\": \"https://www.quora.com/Whats-up-with-Obamas-middle-name\", \"snippet\": \"Answer (1 of 15): A better question would be, \\\\u201cWhat\\\\u2019s up with <strong>Obama</strong>\\\\u2019s first <strong>name</strong>?\\\\u201d President Barack Hussein <strong>Obama</strong>\\\\u2019s father\\\\u2019s <strong>name</strong> was Barack Hussein <strong>Obama</strong>. He was <strong>named</strong> after his father. Hussein, <strong>Obama</strong>\\\\u2019<strong>s</strong> <strong>middle</strong> <strong>name</strong>, is a very common Arabic <strong>name</strong>, meaning "good," "handsome," or ...\"}, {\"title\": \"Barack Obama | Biography, Parents, Education, Presidency, Books, ...\", \"link\": \"https://www.britannica.com/biography/Barack-Obama\", \"snippet\": \"Barack <strong>Obama</strong>, in full Barack Hussein <strong>Obama</strong> II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009\\\\u201317) and the first African American to hold the office. Before winning the presidency, <strong>Obama</strong> represented Illinois in the U.S.\"}]'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"obama middle name\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "da9c63d5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,123 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3f34700b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ChatGPT Plugins\n",
|
||||
"\n",
|
||||
"This example shows how to use ChatGPT Plugins within LangChain abstractions.\n",
|
||||
"\n",
|
||||
"Note 1: This currently only works for plugins with no auth.\n",
|
||||
"\n",
|
||||
"Note 2: There are almost certainly other ways to do this, this is just a first pass. If you have better ideas, please open a PR!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "d41405b5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.tools import AIPluginTool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d9e61df5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool = AIPluginTool.from_plugin_url(\"https://www.klarna.com/.well-known/ai-plugin.json\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "edc0ea0e",
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to check the Klarna Shopping API to see if it has information on available t shirts.\n",
|
||||
"Action: KlarnaProducts\n",
|
||||
"Action Input: None\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mUsage Guide: Use the Klarna plugin to get relevant product suggestions for any shopping or researching purpose. The query to be sent should not include stopwords like articles, prepositions and determinants. The api works best when searching for words that are related to products, like their name, brand, model or category. Links will always be returned and should be shown to the user.\n",
|
||||
"\n",
|
||||
"OpenAPI Spec: {'openapi': '3.0.1', 'info': {'version': 'v0', 'title': 'Open AI Klarna product Api'}, 'servers': [{'url': 'https://www.klarna.com/us/shopping'}], 'tags': [{'name': 'open-ai-product-endpoint', 'description': 'Open AI Product Endpoint. Query for products.'}], 'paths': {'/public/openai/v0/products': {'get': {'tags': ['open-ai-product-endpoint'], 'summary': 'API for fetching Klarna product information', 'operationId': 'productsUsingGET', 'parameters': [{'name': 'q', 'in': 'query', 'description': 'query, must be between 2 and 100 characters', 'required': True, 'schema': {'type': 'string'}}, {'name': 'size', 'in': 'query', 'description': 'number of products returned', 'required': False, 'schema': {'type': 'integer'}}, {'name': 'budget', 'in': 'query', 'description': 'maximum price of the matching product in local currency, filters results', 'required': False, 'schema': {'type': 'integer'}}], 'responses': {'200': {'description': 'Products found', 'content': {'application/json': {'schema': {'$ref': '#/components/schemas/ProductResponse'}}}}, '503': {'description': 'one or more services are unavailable'}}, 'deprecated': False}}}, 'components': {'schemas': {'Product': {'type': 'object', 'properties': {'attributes': {'type': 'array', 'items': {'type': 'string'}}, 'name': {'type': 'string'}, 'price': {'type': 'string'}, 'url': {'type': 'string'}}, 'title': 'Product'}, 'ProductResponse': {'type': 'object', 'properties': {'products': {'type': 'array', 'items': {'$ref': '#/components/schemas/Product'}}}, 'title': 'ProductResponse'}}}}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI need to use the Klarna Shopping API to search for t shirts.\n",
|
||||
"Action: requests_get\n",
|
||||
"Action Input: https://www.klarna.com/us/shopping/public/openai/v0/products?q=t%20shirts\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Lacoste Men's Pack of Plain T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202043025/Clothing/Lacoste-Men-s-Pack-of-Plain-T-Shirts/?utm_source=openai\",\"price\":\"$26.60\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\"]},{\"name\":\"Hanes Men's Ultimate 6pk. Crewneck T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201808270/Clothing/Hanes-Men-s-Ultimate-6pk.-Crewneck-T-Shirts/?utm_source=openai\",\"price\":\"$13.82\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White\"]},{\"name\":\"Nike Boy's Jordan Stretch T-shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3201863202/Children-s-Clothing/Nike-Boy-s-Jordan-Stretch-T-shirts/?utm_source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Material:Cotton\",\"Color:White,Green\",\"Model:Boy\",\"Size (Small-Large):S,XL,L,M\"]},{\"name\":\"Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203028500/Clothing/Polo-Classic-Fit-Cotton-V-Neck-T-Shirts-3-Pack/?utm_source=openai\",\"price\":\"$29.95\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Blue,Black\"]},{\"name\":\"adidas Comfort T-shirts Men's 3-pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202640533/Clothing/adidas-Comfort-T-shirts-Men-s-3-pack/?utm_source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\",\"Neckline:Round\"]}]}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThe available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\n",
|
||||
"Final Answer: The available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"requests_all\"])\n",
|
||||
"tools += [tool]\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"agent_chain.run(\"what t shirts are available in klarna?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e49318a4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,237 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# DataForSeo API Wrapper\n",
|
||||
"This notebook demonstrates how to use the DataForSeo API wrapper to obtain search engine results. The DataForSeo API allows users to retrieve SERP from most popular search engines like Google, Bing, Yahoo. It also allows to get SERPs from different search engine types like Maps, News, Events, etc.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import DataForSeoAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setting up the API wrapper with your credentials\n",
|
||||
"You can obtain your API credentials by registering on the DataForSeo website."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"DATAFORSEO_LOGIN\"] = \"your_api_access_username\"\n",
|
||||
"os.environ[\"DATAFORSEO_PASSWORD\"] = \"your_api_access_password\"\n",
|
||||
"\n",
|
||||
"wrapper = DataForSeoAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The run method will return the first result snippet from one of the following elements: answer_box, knowledge_graph, featured_snippet, shopping, organic."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"wrapper.run(\"Weather in Los Angeles\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## The Difference Between `run` and `results`\n",
|
||||
"`run` and `results` are two methods provided by the `DataForSeoAPIWrapper` class.\n",
|
||||
"\n",
|
||||
"The `run` method executes the search and returns the first result snippet from the answer box, knowledge graph, featured snippet, shopping, or organic results. These elements are sorted by priority from highest to lowest.\n",
|
||||
"\n",
|
||||
"The `results` method returns a JSON response configured according to the parameters set in the wrapper. This allows for more flexibility in terms of what data you want to return from the API."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Getting Results as JSON\n",
|
||||
"You can customize the result types and fields you want to return in the JSON response. You can also set a maximum count for the number of top results to return."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"json_wrapper = DataForSeoAPIWrapper(\n",
|
||||
" json_result_types=[\"organic\", \"knowledge_graph\", \"answer_box\"],\n",
|
||||
" json_result_fields=[\"type\", \"title\", \"description\", \"text\"],\n",
|
||||
" top_count=3,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"json_wrapper.results(\"Bill Gates\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Customizing Location and Language\n",
|
||||
"You can specify the location and language of your search results by passing additional parameters to the API wrapper."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"customized_wrapper = DataForSeoAPIWrapper(\n",
|
||||
" top_count=10,\n",
|
||||
" json_result_types=[\"organic\", \"local_pack\"],\n",
|
||||
" json_result_fields=[\"title\", \"description\", \"type\"],\n",
|
||||
" params={\"location_name\": \"Germany\", \"language_code\": \"en\"},\n",
|
||||
")\n",
|
||||
"customized_wrapper.results(\"coffee near me\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Customizing the Search Engine\n",
|
||||
"You can also specify the search engine you want to use."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"customized_wrapper = DataForSeoAPIWrapper(\n",
|
||||
" top_count=10,\n",
|
||||
" json_result_types=[\"organic\", \"local_pack\"],\n",
|
||||
" json_result_fields=[\"title\", \"description\", \"type\"],\n",
|
||||
" params={\"location_name\": \"Germany\", \"language_code\": \"en\", \"se_name\": \"bing\"},\n",
|
||||
")\n",
|
||||
"customized_wrapper.results(\"coffee near me\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Customizing the Search Type\n",
|
||||
"The API wrapper also allows you to specify the type of search you want to perform. For example, you can perform a maps search."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"maps_search = DataForSeoAPIWrapper(\n",
|
||||
" top_count=10,\n",
|
||||
" json_result_fields=[\"title\", \"value\", \"address\", \"rating\", \"type\"],\n",
|
||||
" params={\n",
|
||||
" \"location_coordinate\": \"52.512,13.36,12z\",\n",
|
||||
" \"language_code\": \"en\",\n",
|
||||
" \"se_type\": \"maps\",\n",
|
||||
" },\n",
|
||||
")\n",
|
||||
"maps_search.results(\"coffee near me\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Integration with Langchain Agents\n",
|
||||
"You can use the `Tool` class from the `langchain.agents` module to integrate the `DataForSeoAPIWrapper` with a langchain agent. The `Tool` class encapsulates a function that the agent can call."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"\n",
|
||||
"search = DataForSeoAPIWrapper(\n",
|
||||
" top_count=3,\n",
|
||||
" json_result_types=[\"organic\"],\n",
|
||||
" json_result_fields=[\"title\", \"description\", \"type\"],\n",
|
||||
")\n",
|
||||
"tool = Tool(\n",
|
||||
" name=\"google-search-answer\",\n",
|
||||
" description=\"My new answer tool\",\n",
|
||||
" func=search.run,\n",
|
||||
")\n",
|
||||
"json_tool = Tool(\n",
|
||||
" name=\"google-search-json\",\n",
|
||||
" description=\"My new json tool\",\n",
|
||||
" func=search.results,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.11"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,91 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# DuckDuckGo Search\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the duck-duck-go search component."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "21e46d4d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install duckduckgo-search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ac4910f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import DuckDuckGoSearchRun"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "84b8f773",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = DuckDuckGoSearchRun()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "068991a6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Barack Obama, in full Barack Hussein Obama II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009-17) and the first African American to hold the office. Before winning the presidency, Obama represented Illinois in the U.S. Senate (2005-08). Barack Hussein Obama II (/ b ə ˈ r ɑː k h uː ˈ s eɪ n oʊ ˈ b ɑː m ə / bə-RAHK hoo-SAYN oh-BAH-mə; born August 4, 1961) is an American former politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, he was the first African-American president of the United States. Obama previously served as a U.S. senator representing ... Barack Obama was the first African American president of the United States (2009-17). He oversaw the recovery of the U.S. economy (from the Great Recession of 2008-09) and the enactment of landmark health care reform (the Patient Protection and Affordable Care Act ). In 2009 he was awarded the Nobel Peace Prize. His birth certificate lists his first name as Barack: That\\'s how Obama has spelled his name throughout his life. His name derives from a Hebrew name which means \"lightning.\". The Hebrew word has been transliterated into English in various spellings, including Barak, Buraq, Burack, and Barack. Most common names of U.S. presidents 1789-2021. Published by. Aaron O\\'Neill , Jun 21, 2022. The most common first name for a U.S. president is James, followed by John and then William. Six U.S ...'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"Obama's first name?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,195 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# File System Tools\n",
|
||||
"\n",
|
||||
"LangChain provides tools for interacting with a local file system out of the box. This notebook walks through some of them.\n",
|
||||
"\n",
|
||||
"Note: these tools are not recommended for use outside a sandboxed environment! "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First, we'll import the tools."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools.file_management import (\n",
|
||||
" ReadFileTool,\n",
|
||||
" CopyFileTool,\n",
|
||||
" DeleteFileTool,\n",
|
||||
" MoveFileTool,\n",
|
||||
" WriteFileTool,\n",
|
||||
" ListDirectoryTool,\n",
|
||||
")\n",
|
||||
"from langchain.agents.agent_toolkits import FileManagementToolkit\n",
|
||||
"from tempfile import TemporaryDirectory\n",
|
||||
"\n",
|
||||
"# We'll make a temporary directory to avoid clutter\n",
|
||||
"working_directory = TemporaryDirectory()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## The FileManagementToolkit\n",
|
||||
"\n",
|
||||
"If you want to provide all the file tooling to your agent, it's easy to do so with the toolkit. We'll pass the temporary directory in as a root directory as a workspace for the LLM.\n",
|
||||
"\n",
|
||||
"It's recommended to always pass in a root directory, since without one, it's easy for the LLM to pollute the working directory, and without one, there isn't any validation against\n",
|
||||
"straightforward prompt injection."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[CopyFileTool(name='copy_file', description='Create a copy of a file in a specified location', args_schema=<class 'langchain.tools.file_management.copy.FileCopyInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" DeleteFileTool(name='file_delete', description='Delete a file', args_schema=<class 'langchain.tools.file_management.delete.FileDeleteInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" FileSearchTool(name='file_search', description='Recursively search for files in a subdirectory that match the regex pattern', args_schema=<class 'langchain.tools.file_management.file_search.FileSearchInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" MoveFileTool(name='move_file', description='Move or rename a file from one location to another', args_schema=<class 'langchain.tools.file_management.move.FileMoveInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"toolkit = FileManagementToolkit(\n",
|
||||
" root_dir=str(working_directory.name)\n",
|
||||
") # If you don't provide a root_dir, operations will default to the current working directory\n",
|
||||
"toolkit.get_tools()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Selecting File System Tools\n",
|
||||
"\n",
|
||||
"If you only want to select certain tools, you can pass them in as arguments when initializing the toolkit, or you can individually initialize the desired tools."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),\n",
|
||||
" ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tools = FileManagementToolkit(\n",
|
||||
" root_dir=str(working_directory.name),\n",
|
||||
" selected_tools=[\"read_file\", \"write_file\", \"list_directory\"],\n",
|
||||
").get_tools()\n",
|
||||
"tools"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'File written successfully to example.txt.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"read_tool, write_tool, list_tool = tools\n",
|
||||
"write_tool.run({\"file_path\": \"example.txt\", \"text\": \"Hello World!\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'example.txt'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# List files in the working directory\n",
|
||||
"list_tool.run({})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,142 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Golden Query\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the golden-query tool.\n",
|
||||
"\n",
|
||||
"- Go to the [Golden API docs](https://docs.golden.com/) to get an overview about the Golden API.\n",
|
||||
"- Create a Golden account if you don't have one on the [Golden Website](golden.com).\n",
|
||||
"- Get your API key from the [Golden API Settings](https://golden.com/settings/api) page.\n",
|
||||
"- Save your API key into GOLDEN_API_KEY env variable"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "34bb5968",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"GOLDEN_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "ac4910f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities.golden_query import GoldenQueryAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "84b8f773",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"golden_query = GoldenQueryAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "068991a6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'results': [{'id': 4673886,\n",
|
||||
" 'latestVersionId': 60276991,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Samsung', 'citations': []}]}]},\n",
|
||||
" {'id': 7008,\n",
|
||||
" 'latestVersionId': 61087416,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Intel', 'citations': []}]}]},\n",
|
||||
" {'id': 24193,\n",
|
||||
" 'latestVersionId': 60274482,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Texas Instruments', 'citations': []}]}]},\n",
|
||||
" {'id': 1142,\n",
|
||||
" 'latestVersionId': 61406205,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Advanced Micro Devices', 'citations': []}]}]},\n",
|
||||
" {'id': 193948,\n",
|
||||
" 'latestVersionId': 58326582,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Freescale Semiconductor', 'citations': []}]}]},\n",
|
||||
" {'id': 91316,\n",
|
||||
" 'latestVersionId': 60387380,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Agilent Technologies', 'citations': []}]}]},\n",
|
||||
" {'id': 90014,\n",
|
||||
" 'latestVersionId': 60388078,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Novartis', 'citations': []}]}]},\n",
|
||||
" {'id': 237458,\n",
|
||||
" 'latestVersionId': 61406160,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'Analog Devices', 'citations': []}]}]},\n",
|
||||
" {'id': 3941943,\n",
|
||||
" 'latestVersionId': 60382250,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'AbbVie Inc.', 'citations': []}]}]},\n",
|
||||
" {'id': 4178762,\n",
|
||||
" 'latestVersionId': 60542667,\n",
|
||||
" 'properties': [{'predicateId': 'name',\n",
|
||||
" 'instances': [{'value': 'IBM', 'citations': []}]}]}],\n",
|
||||
" 'next': 'https://golden.com/api/v2/public/queries/59044/results/?cursor=eyJwb3NpdGlvbiI6IFsxNzYxNiwgIklCTS04M1lQM1oiXX0%3D&pageSize=10',\n",
|
||||
" 'previous': None}"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"\n",
|
||||
"json.loads(golden_query.run(\"companies in nanotech\"))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.13"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "487607cd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Places\n",
|
||||
"\n",
|
||||
"This notebook goes through how to use Google Places API"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "8690845f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install googlemaps"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "fae31ef4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"GPLACES_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "abb502b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import GooglePlacesTool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "a83a02ac",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"places = GooglePlacesTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "2b65a285",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"1. Delfina Restaurant\\nAddress: 3621 18th St, San Francisco, CA 94110, USA\\nPhone: (415) 552-4055\\nWebsite: https://www.delfinasf.com/\\n\\n\\n2. Piccolo Forno\\nAddress: 725 Columbus Ave, San Francisco, CA 94133, USA\\nPhone: (415) 757-0087\\nWebsite: https://piccolo-forno-sf.com/\\n\\n\\n3. L'Osteria del Forno\\nAddress: 519 Columbus Ave, San Francisco, CA 94133, USA\\nPhone: (415) 982-1124\\nWebsite: Unknown\\n\\n\\n4. Il Fornaio\\nAddress: 1265 Battery St, San Francisco, CA 94111, USA\\nPhone: (415) 986-0100\\nWebsite: https://www.ilfornaio.com/\\n\\n\""
|
||||
]
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"places.run(\"al fornos\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "66d3da8a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,200 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Search\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the google search component.\n",
|
||||
"\n",
|
||||
"First, you need to set up the proper API keys and environment variables. To set it up, create the GOOGLE_API_KEY in the Google Cloud credential console (https://console.cloud.google.com/apis/credentials) and a GOOGLE_CSE_ID using the Programmable Search Enginge (https://programmablesearchengine.google.com/controlpanel/create). Next, it is good to follow the instructions found [here](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search).\n",
|
||||
"\n",
|
||||
"Then we will need to set some environment variables."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "34bb5968",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"GOOGLE_CSE_ID\"] = \"\"\n",
|
||||
"os.environ[\"GOOGLE_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "ac4910f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import Tool\n",
|
||||
"from langchain.utilities import GoogleSearchAPIWrapper\n",
|
||||
"\n",
|
||||
"search = GoogleSearchAPIWrapper()\n",
|
||||
"\n",
|
||||
"tool = Tool(\n",
|
||||
" name=\"Google Search\",\n",
|
||||
" description=\"Search Google for recent results.\",\n",
|
||||
" func=search.run,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "84b8f773",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"STATE OF HAWAII. 1 Child's First Name. (Type or print). 2. Sex. BARACK. 3. This Birth. CERTIFICATE OF LIVE BIRTH. FILE. NUMBER 151 le. lb. Middle Name. Barack Hussein Obama II is an American former politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic\\xa0... When Barack Obama was elected president in 2008, he became the first African American to hold ... The Middle East remained a key foreign policy challenge. Jan 19, 2017 ... Jordan Barack Treasure, New York City, born in 2008 ... Jordan Barack Treasure made national news when he was the focus of a New York newspaper\\xa0... Portrait of George Washington, the 1st President of the United States ... Portrait of Barack Obama, the 44th President of the United States\\xa0... His full name is Barack Hussein Obama II. Since the “II” is simply because he was named for his father, his last name is Obama. Mar 22, 2008 ... Barry Obama decided that he didn't like his nickname. A few of his friends at Occidental College had already begun to call him Barack (his\\xa0... Aug 18, 2017 ... It took him several seconds and multiple clues to remember former President Barack Obama's first name. Miller knew that every answer had to\\xa0... Feb 9, 2015 ... Michael Jordan misspelled Barack Obama's first name on 50th-birthday gift ... Knowing Obama is a Chicagoan and huge basketball fan,\\xa0... 4 days ago ... Barack Obama, in full Barack Hussein Obama II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009–17) and\\xa0...\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"Obama's first name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "074b7f07",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Number of Results\n",
|
||||
"You can use the `k` parameter to set the number of results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "5083fbdd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = GoogleSearchAPIWrapper(k=1)\n",
|
||||
"\n",
|
||||
"tool = Tool(\n",
|
||||
" name=\"I'm Feeling Lucky\",\n",
|
||||
" description=\"Search Google and return the first result.\",\n",
|
||||
" func=search.run,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "77aaa857",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The official home of the Python Programming Language.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"python\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "11c8d94f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"'The official home of the Python Programming Language.'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "73473110",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Metadata Results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "109fe796",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Run query through GoogleSearch and return snippet, title, and link metadata.\n",
|
||||
"\n",
|
||||
"- Snippet: The description of the result.\n",
|
||||
"- Title: The title of the result.\n",
|
||||
"- Link: The link to the result."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "028f4cba",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = GoogleSearchAPIWrapper()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def top5_results(query):\n",
|
||||
" return search.results(query, 5)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"tool = Tool(\n",
|
||||
" name=\"Google Search Snippets\",\n",
|
||||
" description=\"Search Google for recent results.\",\n",
|
||||
" func=top5_results,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4d7f92e1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,893 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dc23c48e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Serper API\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the Google Serper component to search the web. First you need to sign up for a free account at [serper.dev](https://serper.dev) and get your api key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import pprint\n",
|
||||
"\n",
|
||||
"os.environ[\"SERPER_API_KEY\"] = \"\""
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:56:29.336521Z",
|
||||
"start_time": "2023-05-04T00:56:29.334173Z"
|
||||
}
|
||||
},
|
||||
"id": "a8acfb24"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "54bf5afd",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:07.676293Z",
|
||||
"start_time": "2023-05-04T00:54:06.665742Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import GoogleSerperAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "31f8f382",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:08.324245Z",
|
||||
"start_time": "2023-05-04T00:54:08.321577Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "25ce0225",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:11.399847Z",
|
||||
"start_time": "2023-05-04T00:54:09.335597Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "'Barack Hussein Obama II'"
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"Obama's first name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## As part of a Self Ask With Search Chain"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "1f1c6c22"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\""
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:14.311773Z",
|
||||
"start_time": "2023-05-04T00:54:14.304389Z"
|
||||
}
|
||||
},
|
||||
"id": "c1b5edd7"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m Yes.\n",
|
||||
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
|
||||
"Intermediate answer: \u001b[36;1m\u001b[1;3mCurrent champions Carlos Alcaraz, 2022 men's singles champion.\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
|
||||
"Intermediate answer: \u001b[36;1m\u001b[1;3mEl Palmar, Spain\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mSo the final answer is: El Palmar, Spain\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "'El Palmar, Spain'"
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.utilities import GoogleSerperAPIWrapper\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.agents import initialize_agent, Tool\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"search = GoogleSerperAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Intermediate Answer\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to ask with search\",\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"self_ask_with_search = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True\n",
|
||||
")\n",
|
||||
"self_ask_with_search.run(\n",
|
||||
" \"What is the hometown of the reigning men's U.S. Open champion?\"\n",
|
||||
")"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "a8ccea61"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Obtaining results with metadata\n",
|
||||
"If you would also like to obtain the results in a structured way including metadata. For this we will be using the `results` method of the wrapper."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "3aee3682"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'searchParameters': {'q': 'Apple Inc.',\n",
|
||||
" 'gl': 'us',\n",
|
||||
" 'hl': 'en',\n",
|
||||
" 'num': 10,\n",
|
||||
" 'type': 'search'},\n",
|
||||
" 'knowledgeGraph': {'title': 'Apple',\n",
|
||||
" 'type': 'Technology company',\n",
|
||||
" 'website': 'http://www.apple.com/',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQwGQRv5TjjkycpctY66mOg_e2-npacrmjAb6_jAWhzlzkFE3OTjxyzbA&s=0',\n",
|
||||
" 'description': 'Apple Inc. is an American multinational '\n",
|
||||
" 'technology company headquartered in '\n",
|
||||
" 'Cupertino, California. Apple is the '\n",
|
||||
" \"world's largest technology company by \"\n",
|
||||
" 'revenue, with US$394.3 billion in 2022 '\n",
|
||||
" 'revenue. As of March 2023, Apple is the '\n",
|
||||
" \"world's biggest...\",\n",
|
||||
" 'descriptionSource': 'Wikipedia',\n",
|
||||
" 'descriptionLink': 'https://en.wikipedia.org/wiki/Apple_Inc.',\n",
|
||||
" 'attributes': {'Customer service': '1 (800) 275-2273',\n",
|
||||
" 'CEO': 'Tim Cook (Aug 24, 2011–)',\n",
|
||||
" 'Headquarters': 'Cupertino, CA',\n",
|
||||
" 'Founded': 'April 1, 1976, Los Altos, CA',\n",
|
||||
" 'Founders': 'Steve Jobs, Steve Wozniak, '\n",
|
||||
" 'Ronald Wayne, and more',\n",
|
||||
" 'Products': 'iPhone, iPad, Apple TV, and '\n",
|
||||
" 'more'}},\n",
|
||||
" 'organic': [{'title': 'Apple',\n",
|
||||
" 'link': 'https://www.apple.com/',\n",
|
||||
" 'snippet': 'Discover the innovative world of Apple and shop '\n",
|
||||
" 'everything iPhone, iPad, Apple Watch, Mac, and Apple '\n",
|
||||
" 'TV, plus explore accessories, entertainment, ...',\n",
|
||||
" 'sitelinks': [{'title': 'Support',\n",
|
||||
" 'link': 'https://support.apple.com/'},\n",
|
||||
" {'title': 'iPhone',\n",
|
||||
" 'link': 'https://www.apple.com/iphone/'},\n",
|
||||
" {'title': 'Site Map',\n",
|
||||
" 'link': 'https://www.apple.com/sitemap/'},\n",
|
||||
" {'title': 'Business',\n",
|
||||
" 'link': 'https://www.apple.com/business/'},\n",
|
||||
" {'title': 'Mac',\n",
|
||||
" 'link': 'https://www.apple.com/mac/'},\n",
|
||||
" {'title': 'Watch',\n",
|
||||
" 'link': 'https://www.apple.com/watch/'}],\n",
|
||||
" 'position': 1},\n",
|
||||
" {'title': 'Apple Inc. - Wikipedia',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Apple_Inc.',\n",
|
||||
" 'snippet': 'Apple Inc. is an American multinational technology '\n",
|
||||
" 'company headquartered in Cupertino, California. '\n",
|
||||
" \"Apple is the world's largest technology company by \"\n",
|
||||
" 'revenue, ...',\n",
|
||||
" 'attributes': {'Products': 'AirPods; Apple Watch; iPad; iPhone; '\n",
|
||||
" 'Mac; Full list',\n",
|
||||
" 'Founders': 'Steve Jobs; Steve Wozniak; Ronald '\n",
|
||||
" 'Wayne; Mike Markkula'},\n",
|
||||
" 'sitelinks': [{'title': 'History',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/History_of_Apple_Inc.'},\n",
|
||||
" {'title': 'Timeline of Apple Inc. products',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Timeline_of_Apple_Inc._products'},\n",
|
||||
" {'title': 'Litigation involving Apple Inc.',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Litigation_involving_Apple_Inc.'},\n",
|
||||
" {'title': 'Apple Store',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Apple_Store'}],\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRvmB5fT1LjqpZx02UM7IJq0Buoqt0DZs_y0dqwxwSWyP4PIN9FaxuTea0&s',\n",
|
||||
" 'position': 2},\n",
|
||||
" {'title': 'Apple Inc. | History, Products, Headquarters, & Facts '\n",
|
||||
" '| Britannica',\n",
|
||||
" 'link': 'https://www.britannica.com/topic/Apple-Inc',\n",
|
||||
" 'snippet': 'Apple Inc., formerly Apple Computer, Inc., American '\n",
|
||||
" 'manufacturer of personal computers, smartphones, '\n",
|
||||
" 'tablet computers, computer peripherals, and computer '\n",
|
||||
" '...',\n",
|
||||
" 'attributes': {'Related People': 'Steve Jobs Steve Wozniak Jony '\n",
|
||||
" 'Ive Tim Cook Angela Ahrendts',\n",
|
||||
" 'Date': '1976 - present'},\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcS3liELlhrMz3Wpsox29U8jJ3L8qETR0hBWHXbFnwjwQc34zwZvFELst2E&s',\n",
|
||||
" 'position': 3},\n",
|
||||
" {'title': 'AAPL: Apple Inc Stock Price Quote - NASDAQ GS - '\n",
|
||||
" 'Bloomberg.com',\n",
|
||||
" 'link': 'https://www.bloomberg.com/quote/AAPL:US',\n",
|
||||
" 'snippet': 'AAPL:USNASDAQ GS. Apple Inc. COMPANY INFO ; Open. '\n",
|
||||
" '170.09 ; Prev Close. 169.59 ; Volume. 48,425,696 ; '\n",
|
||||
" 'Market Cap. 2.667T ; Day Range. 167.54170.35.',\n",
|
||||
" 'position': 4},\n",
|
||||
" {'title': 'Apple Inc. (AAPL) Company Profile & Facts - Yahoo '\n",
|
||||
" 'Finance',\n",
|
||||
" 'link': 'https://finance.yahoo.com/quote/AAPL/profile/',\n",
|
||||
" 'snippet': 'Apple Inc. designs, manufactures, and markets '\n",
|
||||
" 'smartphones, personal computers, tablets, wearables, '\n",
|
||||
" 'and accessories worldwide. The company offers '\n",
|
||||
" 'iPhone, a line ...',\n",
|
||||
" 'position': 5},\n",
|
||||
" {'title': 'Apple Inc. (AAPL) Stock Price, News, Quote & History - '\n",
|
||||
" 'Yahoo Finance',\n",
|
||||
" 'link': 'https://finance.yahoo.com/quote/AAPL',\n",
|
||||
" 'snippet': 'Find the latest Apple Inc. (AAPL) stock quote, '\n",
|
||||
" 'history, news and other vital information to help '\n",
|
||||
" 'you with your stock trading and investing.',\n",
|
||||
" 'position': 6}],\n",
|
||||
" 'peopleAlsoAsk': [{'question': 'What does Apple Inc do?',\n",
|
||||
" 'snippet': 'Apple Inc. (Apple) designs, manufactures and '\n",
|
||||
" 'markets smartphones, personal\\n'\n",
|
||||
" 'computers, tablets, wearables and accessories '\n",
|
||||
" 'and sells a range of related\\n'\n",
|
||||
" 'services.',\n",
|
||||
" 'title': 'AAPL.O - | Stock Price & Latest News - Reuters',\n",
|
||||
" 'link': 'https://www.reuters.com/markets/companies/AAPL.O/'},\n",
|
||||
" {'question': 'What is the full form of Apple Inc?',\n",
|
||||
" 'snippet': '(formerly Apple Computer Inc.) is an American '\n",
|
||||
" 'computer and consumer electronics\\n'\n",
|
||||
" 'company famous for creating the iPhone, iPad '\n",
|
||||
" 'and Macintosh computers.',\n",
|
||||
" 'title': 'What is Apple? An products and history overview '\n",
|
||||
" '- TechTarget',\n",
|
||||
" 'link': 'https://www.techtarget.com/whatis/definition/Apple'},\n",
|
||||
" {'question': 'What is Apple Inc iPhone?',\n",
|
||||
" 'snippet': 'Apple Inc (Apple) designs, manufactures, and '\n",
|
||||
" 'markets smartphones, tablets,\\n'\n",
|
||||
" 'personal computers, and wearable devices. The '\n",
|
||||
" 'company also offers software\\n'\n",
|
||||
" 'applications and related services, '\n",
|
||||
" 'accessories, and third-party digital content.\\n'\n",
|
||||
" \"Apple's product portfolio includes iPhone, \"\n",
|
||||
" 'iPad, Mac, iPod, Apple Watch, and\\n'\n",
|
||||
" 'Apple TV.',\n",
|
||||
" 'title': 'Apple Inc Company Profile - Apple Inc Overview - '\n",
|
||||
" 'GlobalData',\n",
|
||||
" 'link': 'https://www.globaldata.com/company-profile/apple-inc/'},\n",
|
||||
" {'question': 'Who runs Apple Inc?',\n",
|
||||
" 'snippet': 'Timothy Donald Cook (born November 1, 1960) is '\n",
|
||||
" 'an American business executive\\n'\n",
|
||||
" 'who has been the chief executive officer of '\n",
|
||||
" 'Apple Inc. since 2011. Cook\\n'\n",
|
||||
" \"previously served as the company's chief \"\n",
|
||||
" 'operating officer under its co-founder\\n'\n",
|
||||
" 'Steve Jobs. He is the first CEO of any Fortune '\n",
|
||||
" '500 company who is openly gay.',\n",
|
||||
" 'title': 'Tim Cook - Wikipedia',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Tim_Cook'}],\n",
|
||||
" 'relatedSearches': [{'query': 'Who invented the iPhone'},\n",
|
||||
" {'query': 'Apple iPhone'},\n",
|
||||
" {'query': 'History of Apple company PDF'},\n",
|
||||
" {'query': 'Apple company history'},\n",
|
||||
" {'query': 'Apple company introduction'},\n",
|
||||
" {'query': 'Apple India'},\n",
|
||||
" {'query': 'What does Apple Inc own'},\n",
|
||||
" {'query': 'Apple Inc After Steve'},\n",
|
||||
" {'query': 'Apple Watch'},\n",
|
||||
" {'query': 'Apple App Store'}]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper()\n",
|
||||
"results = search.results(\"Apple Inc.\")\n",
|
||||
"pprint.pp(results)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:22.863413Z",
|
||||
"start_time": "2023-05-04T00:54:20.827395Z"
|
||||
}
|
||||
},
|
||||
"id": "073c3fc5"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Searching for Google Images\n",
|
||||
"We can also query Google Images using this wrapper. For example:"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "b402c308"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'searchParameters': {'q': 'Lion',\n",
|
||||
" 'gl': 'us',\n",
|
||||
" 'hl': 'en',\n",
|
||||
" 'num': 10,\n",
|
||||
" 'type': 'images'},\n",
|
||||
" 'images': [{'title': 'Lion - Wikipedia',\n",
|
||||
" 'imageUrl': 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/73/Lion_waiting_in_Namibia.jpg/1200px-Lion_waiting_in_Namibia.jpg',\n",
|
||||
" 'imageWidth': 1200,\n",
|
||||
" 'imageHeight': 900,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRye79ROKwjfb6017jr0iu8Bz2E1KKuHg-A4qINJaspyxkZrkw&s',\n",
|
||||
" 'thumbnailWidth': 259,\n",
|
||||
" 'thumbnailHeight': 194,\n",
|
||||
" 'source': 'Wikipedia',\n",
|
||||
" 'domain': 'en.wikipedia.org',\n",
|
||||
" 'link': 'https://en.wikipedia.org/wiki/Lion',\n",
|
||||
" 'position': 1},\n",
|
||||
" {'title': 'Lion | Characteristics, Habitat, & Facts | Britannica',\n",
|
||||
" 'imageUrl': 'https://cdn.britannica.com/55/2155-050-604F5A4A/lion.jpg',\n",
|
||||
" 'imageWidth': 754,\n",
|
||||
" 'imageHeight': 752,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcS3fnDub1GSojI0hJ-ZGS8Tv-hkNNloXh98DOwXZoZ_nUs3GWSd&s',\n",
|
||||
" 'thumbnailWidth': 225,\n",
|
||||
" 'thumbnailHeight': 224,\n",
|
||||
" 'source': 'Encyclopedia Britannica',\n",
|
||||
" 'domain': 'www.britannica.com',\n",
|
||||
" 'link': 'https://www.britannica.com/animal/lion',\n",
|
||||
" 'position': 2},\n",
|
||||
" {'title': 'African lion, facts and photos',\n",
|
||||
" 'imageUrl': 'https://i.natgeofe.com/n/487a0d69-8202-406f-a6a0-939ed3704693/african-lion.JPG',\n",
|
||||
" 'imageWidth': 3072,\n",
|
||||
" 'imageHeight': 2043,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTPlTarrtDbyTiEm-VI_PML9VtOTVPuDXJ5ybDf_lN11H2mShk&s',\n",
|
||||
" 'thumbnailWidth': 275,\n",
|
||||
" 'thumbnailHeight': 183,\n",
|
||||
" 'source': 'National Geographic',\n",
|
||||
" 'domain': 'www.nationalgeographic.com',\n",
|
||||
" 'link': 'https://www.nationalgeographic.com/animals/mammals/facts/african-lion',\n",
|
||||
" 'position': 3},\n",
|
||||
" {'title': 'Saint Louis Zoo | African Lion',\n",
|
||||
" 'imageUrl': 'https://optimise2.assets-servd.host/maniacal-finch/production/animals/african-lion-01-01.jpg?w=1200&auto=compress%2Cformat&fit=crop&dm=1658933674&s=4b63f926a0f524f2087a8e0613282bdb',\n",
|
||||
" 'imageWidth': 1200,\n",
|
||||
" 'imageHeight': 1200,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTlewcJ5SwC7yKup6ByaOjTnAFDeoOiMxyJTQaph2W_I3dnks4&s',\n",
|
||||
" 'thumbnailWidth': 225,\n",
|
||||
" 'thumbnailHeight': 225,\n",
|
||||
" 'source': 'St. Louis Zoo',\n",
|
||||
" 'domain': 'stlzoo.org',\n",
|
||||
" 'link': 'https://stlzoo.org/animals/mammals/carnivores/lion',\n",
|
||||
" 'position': 4},\n",
|
||||
" {'title': 'How to Draw a Realistic Lion like an Artist - Studio '\n",
|
||||
" 'Wildlife',\n",
|
||||
" 'imageUrl': 'https://studiowildlife.com/wp-content/uploads/2021/10/245528858_183911853822648_6669060845725210519_n.jpg',\n",
|
||||
" 'imageWidth': 1431,\n",
|
||||
" 'imageHeight': 2048,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTmn5HayVj3wqoBDQacnUtzaDPZzYHSLKUlIEcni6VB8w0mVeA&s',\n",
|
||||
" 'thumbnailWidth': 188,\n",
|
||||
" 'thumbnailHeight': 269,\n",
|
||||
" 'source': 'Studio Wildlife',\n",
|
||||
" 'domain': 'studiowildlife.com',\n",
|
||||
" 'link': 'https://studiowildlife.com/how-to-draw-a-realistic-lion-like-an-artist/',\n",
|
||||
" 'position': 5},\n",
|
||||
" {'title': 'Lion | Characteristics, Habitat, & Facts | Britannica',\n",
|
||||
" 'imageUrl': 'https://cdn.britannica.com/29/150929-050-547070A1/lion-Kenya-Masai-Mara-National-Reserve.jpg',\n",
|
||||
" 'imageWidth': 1600,\n",
|
||||
" 'imageHeight': 1085,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSCqaKY_THr0IBZN8c-2VApnnbuvKmnsWjfrwKoWHFR9w3eN5o&s',\n",
|
||||
" 'thumbnailWidth': 273,\n",
|
||||
" 'thumbnailHeight': 185,\n",
|
||||
" 'source': 'Encyclopedia Britannica',\n",
|
||||
" 'domain': 'www.britannica.com',\n",
|
||||
" 'link': 'https://www.britannica.com/animal/lion',\n",
|
||||
" 'position': 6},\n",
|
||||
" {'title': \"Where do lions live? Facts about lions' habitats and \"\n",
|
||||
" 'other cool facts',\n",
|
||||
" 'imageUrl': 'https://www.gannett-cdn.com/-mm-/b2b05a4ab25f4fca0316459e1c7404c537a89702/c=0-0-1365-768/local/-/media/2022/03/16/USATODAY/usatsports/imageForEntry5-ODq.jpg?width=1365&height=768&fit=crop&format=pjpg&auto=webp',\n",
|
||||
" 'imageWidth': 1365,\n",
|
||||
" 'imageHeight': 768,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTc_4vCHscgvFvYy3PSrtIOE81kNLAfhDK8F3mfOuotL0kUkbs&s',\n",
|
||||
" 'thumbnailWidth': 299,\n",
|
||||
" 'thumbnailHeight': 168,\n",
|
||||
" 'source': 'USA Today',\n",
|
||||
" 'domain': 'www.usatoday.com',\n",
|
||||
" 'link': 'https://www.usatoday.com/story/news/2023/01/08/where-do-lions-live-habitat/10927718002/',\n",
|
||||
" 'position': 7},\n",
|
||||
" {'title': 'Lion',\n",
|
||||
" 'imageUrl': 'https://i.natgeofe.com/k/1d33938b-3d02-4773-91e3-70b113c3b8c7/lion-male-roar_square.jpg',\n",
|
||||
" 'imageWidth': 3072,\n",
|
||||
" 'imageHeight': 3072,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQqLfnBrBLcTiyTZynHH3FGbBtX2bd1ScwpcuOLnksTyS9-4GM&s',\n",
|
||||
" 'thumbnailWidth': 225,\n",
|
||||
" 'thumbnailHeight': 225,\n",
|
||||
" 'source': 'National Geographic Kids',\n",
|
||||
" 'domain': 'kids.nationalgeographic.com',\n",
|
||||
" 'link': 'https://kids.nationalgeographic.com/animals/mammals/facts/lion',\n",
|
||||
" 'position': 8},\n",
|
||||
" {'title': \"Lion | Smithsonian's National Zoo\",\n",
|
||||
" 'imageUrl': 'https://nationalzoo.si.edu/sites/default/files/styles/1400_scale/public/animals/exhibit/africanlion-005.jpg?itok=6wA745g_',\n",
|
||||
" 'imageWidth': 1400,\n",
|
||||
" 'imageHeight': 845,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSgB3z_D4dMEOWJ7lajJk4XaQSL4DdUvIRj4UXZ0YoE5fGuWuo&s',\n",
|
||||
" 'thumbnailWidth': 289,\n",
|
||||
" 'thumbnailHeight': 174,\n",
|
||||
" 'source': \"Smithsonian's National Zoo\",\n",
|
||||
" 'domain': 'nationalzoo.si.edu',\n",
|
||||
" 'link': 'https://nationalzoo.si.edu/animals/lion',\n",
|
||||
" 'position': 9},\n",
|
||||
" {'title': \"Zoo's New Male Lion Explores Habitat for the First Time \"\n",
|
||||
" '- Virginia Zoo',\n",
|
||||
" 'imageUrl': 'https://virginiazoo.org/wp-content/uploads/2022/04/ZOO_0056-scaled.jpg',\n",
|
||||
" 'imageWidth': 2560,\n",
|
||||
" 'imageHeight': 2141,\n",
|
||||
" 'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTDCG7XvXRCwpe_-Vy5mpvrQpVl5q2qwgnDklQhrJpQzObQGz4&s',\n",
|
||||
" 'thumbnailWidth': 246,\n",
|
||||
" 'thumbnailHeight': 205,\n",
|
||||
" 'source': 'Virginia Zoo',\n",
|
||||
" 'domain': 'virginiazoo.org',\n",
|
||||
" 'link': 'https://virginiazoo.org/zoos-new-male-lion-explores-habitat-for-thefirst-time/',\n",
|
||||
" 'position': 10}]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper(type=\"images\")\n",
|
||||
"results = search.results(\"Lion\")\n",
|
||||
"pprint.pp(results)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:27.879867Z",
|
||||
"start_time": "2023-05-04T00:54:26.380022Z"
|
||||
}
|
||||
},
|
||||
"id": "7fb2b7e2"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Searching for Google News\n",
|
||||
"We can also query Google News using this wrapper. For example:"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "85a3bed3"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'searchParameters': {'q': 'Tesla Inc.',\n",
|
||||
" 'gl': 'us',\n",
|
||||
" 'hl': 'en',\n",
|
||||
" 'num': 10,\n",
|
||||
" 'type': 'news'},\n",
|
||||
" 'news': [{'title': 'ISS recommends Tesla investors vote against re-election '\n",
|
||||
" 'of Robyn Denholm',\n",
|
||||
" 'link': 'https://www.reuters.com/business/autos-transportation/iss-recommends-tesla-investors-vote-against-re-election-robyn-denholm-2023-05-04/',\n",
|
||||
" 'snippet': 'Proxy advisory firm ISS on Wednesday recommended Tesla '\n",
|
||||
" 'investors vote against re-election of board chair Robyn '\n",
|
||||
" 'Denholm, citing \"concerns on...',\n",
|
||||
" 'date': '5 mins ago',\n",
|
||||
" 'source': 'Reuters',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcROdETe_GUyp1e8RHNhaRM8Z_vfxCvdfinZwzL1bT1ZGSYaGTeOojIdBoLevA&s',\n",
|
||||
" 'position': 1},\n",
|
||||
" {'title': 'Global companies by market cap: Tesla fell most in April',\n",
|
||||
" 'link': 'https://www.reuters.com/markets/global-companies-by-market-cap-tesla-fell-most-april-2023-05-02/',\n",
|
||||
" 'snippet': 'Tesla Inc was the biggest loser among top companies by '\n",
|
||||
" 'market capitalisation in April, hit by disappointing '\n",
|
||||
" 'quarterly earnings after it...',\n",
|
||||
" 'date': '1 day ago',\n",
|
||||
" 'source': 'Reuters',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ4u4CP8aOdGyRFH6o4PkXi-_eZDeY96vLSag5gDjhKMYf98YBER2cZPbkStQ&s',\n",
|
||||
" 'position': 2},\n",
|
||||
" {'title': 'Tesla Wanted an EV Price War. Ford Showed Up.',\n",
|
||||
" 'link': 'https://www.bloomberg.com/opinion/articles/2023-05-03/tesla-wanted-an-ev-price-war-ford-showed-up',\n",
|
||||
" 'snippet': 'The legacy automaker is paring back the cost of its '\n",
|
||||
" 'Mustang Mach-E model after Tesla discounted its '\n",
|
||||
" 'competing EVs, portending tighter...',\n",
|
||||
" 'date': '6 hours ago',\n",
|
||||
" 'source': 'Bloomberg.com',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcS_3Eo4VI0H-nTeIbYc5DaQn5ep7YrWnmhx6pv8XddFgNF5zRC9gEpHfDq8yQ&s',\n",
|
||||
" 'position': 3},\n",
|
||||
" {'title': 'Joby Aviation to get investment from Tesla shareholder '\n",
|
||||
" 'Baillie Gifford',\n",
|
||||
" 'link': 'https://finance.yahoo.com/news/joby-aviation-investment-tesla-shareholder-204450712.html',\n",
|
||||
" 'snippet': 'This comes days after Joby clinched a $55 million '\n",
|
||||
" 'contract extension to deliver up to nine air taxis to '\n",
|
||||
" 'the U.S. Air Force,...',\n",
|
||||
" 'date': '4 hours ago',\n",
|
||||
" 'source': 'Yahoo Finance',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQO0uVn297LI-xryrPNqJ-apUOulj4ohM-xkN4OfmvMOYh1CPdUEBbYx6hviw&s',\n",
|
||||
" 'position': 4},\n",
|
||||
" {'title': 'Tesla resumes U.S. orders for a Model 3 version at lower '\n",
|
||||
" 'price, range',\n",
|
||||
" 'link': 'https://finance.yahoo.com/news/tesla-resumes-us-orders-model-045736115.html',\n",
|
||||
" 'snippet': '(Reuters) -Tesla Inc has resumed taking orders for its '\n",
|
||||
" 'Model 3 long-range vehicle in the United States, the '\n",
|
||||
" \"company's website showed late on...\",\n",
|
||||
" 'date': '19 hours ago',\n",
|
||||
" 'source': 'Yahoo Finance',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTIZetJ62sQefPfbQ9KKDt6iH7Mc0ylT5t_hpgeeuUkHhJuAx2FOJ4ZTRVDFg&s',\n",
|
||||
" 'position': 5},\n",
|
||||
" {'title': 'The Tesla Model 3 Long Range AWD Is Now Available in the '\n",
|
||||
" 'U.S. With 325 Miles of Range',\n",
|
||||
" 'link': 'https://www.notateslaapp.com/news/1393/tesla-reopens-orders-for-model-3-long-range-after-months-of-unavailability',\n",
|
||||
" 'snippet': 'Tesla has reopened orders for the Model 3 Long Range '\n",
|
||||
" 'RWD, which has been unavailable for months due to high '\n",
|
||||
" 'demand.',\n",
|
||||
" 'date': '7 hours ago',\n",
|
||||
" 'source': 'Not a Tesla App',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSecrgxZpRj18xIJY-nDHljyP-A4ejEkswa9eq77qhMNrScnVIqe34uql5U4w&s',\n",
|
||||
" 'position': 6},\n",
|
||||
" {'title': 'Tesla Cybertruck alpha prototype spotted at the Fremont '\n",
|
||||
" 'factory in new pics and videos',\n",
|
||||
" 'link': 'https://www.teslaoracle.com/2023/05/03/tesla-cybertruck-alpha-prototype-interior-and-exterior-spotted-at-the-fremont-factory-in-new-pics-and-videos/',\n",
|
||||
" 'snippet': 'A Tesla Cybertruck alpha prototype goes to Fremont, '\n",
|
||||
" 'California for another round of testing before going to '\n",
|
||||
" 'production later this year (pics...',\n",
|
||||
" 'date': '14 hours ago',\n",
|
||||
" 'source': 'Tesla Oracle',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRO7M5ZLQE-Zo4-_5dv9hNAQZ3wSqfvYCuKqzxHG-M6CgLpwPMMG_ssebdcMg&s',\n",
|
||||
" 'position': 7},\n",
|
||||
" {'title': 'Tesla putting facility in new part of country - Austin '\n",
|
||||
" 'Business Journal',\n",
|
||||
" 'link': 'https://www.bizjournals.com/austin/news/2023/05/02/tesla-leases-building-seattle-area.html',\n",
|
||||
" 'snippet': 'Check out what Puget Sound Business Journal has to '\n",
|
||||
" \"report about the Austin-based company's real estate \"\n",
|
||||
" 'footprint in the Pacific Northwest.',\n",
|
||||
" 'date': '22 hours ago',\n",
|
||||
" 'source': 'The Business Journals',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcR9kIEHWz1FcHKDUtGQBS0AjmkqtyuBkQvD8kyIY3kpaPrgYaN7I_H2zoOJsA&s',\n",
|
||||
" 'position': 8},\n",
|
||||
" {'title': 'Tesla (TSLA) Resumes Orders for Model 3 Long Range After '\n",
|
||||
" 'Backlog',\n",
|
||||
" 'link': 'https://www.bloomberg.com/news/articles/2023-05-03/tesla-resumes-orders-for-popular-model-3-long-range-at-47-240',\n",
|
||||
" 'snippet': 'Tesla Inc. has resumed taking orders for its Model 3 '\n",
|
||||
" 'Long Range edition with a starting price of $47240, '\n",
|
||||
" 'according to its website.',\n",
|
||||
" 'date': '5 hours ago',\n",
|
||||
" 'source': 'Bloomberg.com',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTWWIC4VpMTfRvSyqiomODOoLg0xhoBf-Tc1qweKnSuaiTk-Y1wMJZM3jct0w&s',\n",
|
||||
" 'position': 9}]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper(type=\"news\")\n",
|
||||
"results = search.results(\"Tesla Inc.\")\n",
|
||||
"pprint.pp(results)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:34.984087Z",
|
||||
"start_time": "2023-05-04T00:54:33.369231Z"
|
||||
}
|
||||
},
|
||||
"id": "afc48b39"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"If you want to only receive news articles published in the last hour, you can do the following:"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "d42ee7b5"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'searchParameters': {'q': 'Tesla Inc.',\n",
|
||||
" 'gl': 'us',\n",
|
||||
" 'hl': 'en',\n",
|
||||
" 'num': 10,\n",
|
||||
" 'type': 'news',\n",
|
||||
" 'tbs': 'qdr:h'},\n",
|
||||
" 'news': [{'title': 'Oklahoma Gov. Stitt sees growing foreign interest in '\n",
|
||||
" 'investments in ...',\n",
|
||||
" 'link': 'https://www.reuters.com/world/us/oklahoma-gov-stitt-sees-growing-foreign-interest-investments-state-2023-05-04/',\n",
|
||||
" 'snippet': 'T)), a battery supplier to electric vehicle maker Tesla '\n",
|
||||
" 'Inc (TSLA.O), said on Sunday it is considering building '\n",
|
||||
" 'a battery plant in Oklahoma, its third in...',\n",
|
||||
" 'date': '53 mins ago',\n",
|
||||
" 'source': 'Reuters',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSSTcsXeenqmEKdiekvUgAmqIPR4nlAmgjTkBqLpza-lLfjX1CwB84MoNVj0Q&s',\n",
|
||||
" 'position': 1},\n",
|
||||
" {'title': 'Ryder lanza solución llave en mano para vehículos '\n",
|
||||
" 'eléctricos en EU',\n",
|
||||
" 'link': 'https://www.tyt.com.mx/nota/ryder-lanza-solucion-llave-en-mano-para-vehiculos-electricos-en-eu',\n",
|
||||
" 'snippet': 'Ryder System Inc. presentó RyderElectric+ TM como su '\n",
|
||||
" 'nueva solución llave en mano ... Ryder también tiene '\n",
|
||||
" 'reservados los semirremolques Tesla y continúa...',\n",
|
||||
" 'date': '56 mins ago',\n",
|
||||
" 'source': 'Revista Transportes y Turismo',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQJhXTQQtjSUZf9YPM235WQhFU5_d7lEA76zB8DGwZfixcgf1_dhPJyKA1Nbw&s',\n",
|
||||
" 'position': 2},\n",
|
||||
" {'title': '\"I think people can get by with $999 million,\" Bernie '\n",
|
||||
" 'Sanders tells American Billionaires.',\n",
|
||||
" 'link': 'https://thebharatexpressnews.com/i-think-people-can-get-by-with-999-million-bernie-sanders-tells-american-billionaires-heres-how-the-ultra-rich-can-pay-less-income-tax-than-you-legally/',\n",
|
||||
" 'snippet': 'The report noted that in 2007 and 2011, Amazon.com Inc. '\n",
|
||||
" 'founder Jeff Bezos “did not pay a dime in federal ... '\n",
|
||||
" 'If you want to bet on Musk, check out Tesla.',\n",
|
||||
" 'date': '11 mins ago',\n",
|
||||
" 'source': 'THE BHARAT EXPRESS NEWS',\n",
|
||||
" 'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcR_X9qqSwVFBBdos2CK5ky5IWIE3aJPCQeRYR9O1Jz4t-MjaEYBuwK7AU3AJQ&s',\n",
|
||||
" 'position': 3}]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper(type=\"news\", tbs=\"qdr:h\")\n",
|
||||
"results = search.results(\"Tesla Inc.\")\n",
|
||||
"pprint.pp(results)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:54:41.786864Z",
|
||||
"start_time": "2023-05-04T00:54:40.691905Z"
|
||||
}
|
||||
},
|
||||
"id": "8e3824cb"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"Some examples of the `tbs` parameter:\n",
|
||||
"\n",
|
||||
"`qdr:h` (past hour)\n",
|
||||
"`qdr:d` (past day)\n",
|
||||
"`qdr:w` (past week)\n",
|
||||
"`qdr:m` (past month)\n",
|
||||
"`qdr:y` (past year)\n",
|
||||
"\n",
|
||||
"You can specify intermediate time periods by adding a number:\n",
|
||||
"`qdr:h12` (past 12 hours)\n",
|
||||
"`qdr:d3` (past 3 days)\n",
|
||||
"`qdr:w2` (past 2 weeks)\n",
|
||||
"`qdr:m6` (past 6 months)\n",
|
||||
"`qdr:m2` (past 2 years)\n",
|
||||
"\n",
|
||||
"For all supported filters simply go to [Google Search](https://google.com), search for something, click on \"Tools\", add your date filter and check the URL for \"tbs=\".\n"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "3f13e9f9"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Searching for Google Places\n",
|
||||
"We can also query Google Places using this wrapper. For example:"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "38d4402c"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'searchParameters': {'q': 'Italian restaurants in Upper East Side',\n",
|
||||
" 'gl': 'us',\n",
|
||||
" 'hl': 'en',\n",
|
||||
" 'num': 10,\n",
|
||||
" 'type': 'places'},\n",
|
||||
" 'places': [{'position': 1,\n",
|
||||
" 'title': \"L'Osteria\",\n",
|
||||
" 'address': '1219 Lexington Ave',\n",
|
||||
" 'latitude': 40.777154599999996,\n",
|
||||
" 'longitude': -73.9571363,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNjU7BWEq_aYQANBCbX52Kb0lDpd_lFIx5onw40=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.7,\n",
|
||||
" 'ratingCount': 91,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 2,\n",
|
||||
" 'title': \"Tony's Di Napoli\",\n",
|
||||
" 'address': '1081 3rd Ave',\n",
|
||||
" 'latitude': 40.7643567,\n",
|
||||
" 'longitude': -73.9642373,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNbNv6jZkJ9nyVi60__8c1DQbe_eEbugRAhIYye=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 2265,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 3,\n",
|
||||
" 'title': 'Caravaggio',\n",
|
||||
" 'address': '23 E 74th St',\n",
|
||||
" 'latitude': 40.773412799999996,\n",
|
||||
" 'longitude': -73.96473379999999,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPDGchokDvppoLfmVEo6X_bWd3Fz0HyxIHTEe9V=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 276,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 4,\n",
|
||||
" 'title': 'Luna Rossa',\n",
|
||||
" 'address': '347 E 85th St',\n",
|
||||
" 'latitude': 40.776593999999996,\n",
|
||||
" 'longitude': -73.950351,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNPCpCPuqPAb1Mv6_fOP7cjb8Wu1rbqbk2sMBlh=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 140,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 5,\n",
|
||||
" 'title': \"Paola's\",\n",
|
||||
" 'address': '1361 Lexington Ave',\n",
|
||||
" 'latitude': 40.7822019,\n",
|
||||
" 'longitude': -73.9534096,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPJr2Vcx-B6K-GNQa4koOTffggTePz8TKRTnWi3=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 344,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 6,\n",
|
||||
" 'title': 'Come Prima',\n",
|
||||
" 'address': '903 Madison Ave',\n",
|
||||
" 'latitude': 40.772124999999996,\n",
|
||||
" 'longitude': -73.965012,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNrX19G0NVdtDyMovCQ-M-m0c_gLmIxrWDQAAbz=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 176,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 7,\n",
|
||||
" 'title': 'Botte UES',\n",
|
||||
" 'address': '1606 1st Ave.',\n",
|
||||
" 'latitude': 40.7750785,\n",
|
||||
" 'longitude': -73.9504801,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPPN5GXxfH3NDacBc0Pt3uGAInd9OChS5isz9RF=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.4,\n",
|
||||
" 'ratingCount': 152,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 8,\n",
|
||||
" 'title': 'Piccola Cucina Uptown',\n",
|
||||
" 'address': '106 E 60th St',\n",
|
||||
" 'latitude': 40.7632468,\n",
|
||||
" 'longitude': -73.9689825,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPifIgzOCD5SjgzzqBzGkdZCBp0MQsK5k7M7znn=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.6,\n",
|
||||
" 'ratingCount': 941,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 9,\n",
|
||||
" 'title': 'Pinocchio Restaurant',\n",
|
||||
" 'address': '300 E 92nd St',\n",
|
||||
" 'latitude': 40.781453299999995,\n",
|
||||
" 'longitude': -73.9486788,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNtxlIyEEJHtDtFtTR9nB38S8A2VyMu-mVVz72A=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.5,\n",
|
||||
" 'ratingCount': 113,\n",
|
||||
" 'category': 'Italian'},\n",
|
||||
" {'position': 10,\n",
|
||||
" 'title': 'Barbaresco',\n",
|
||||
" 'address': '843 Lexington Ave #1',\n",
|
||||
" 'latitude': 40.7654332,\n",
|
||||
" 'longitude': -73.9656873,\n",
|
||||
" 'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipMb9FbPuXF_r9g5QseOHmReejxSHgSahPMPJ9-8=w92-h92-n-k-no',\n",
|
||||
" 'rating': 4.3,\n",
|
||||
" 'ratingCount': 122,\n",
|
||||
" 'locationHint': 'In The Touraine',\n",
|
||||
" 'category': 'Italian'}]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = GoogleSerperAPIWrapper(type=\"places\")\n",
|
||||
"results = search.results(\"Italian restaurants in Upper East Side\")\n",
|
||||
"pprint.pp(results)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-04T00:56:07.271164Z",
|
||||
"start_time": "2023-05-04T00:56:05.645847Z"
|
||||
}
|
||||
},
|
||||
"id": "e7881203"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,154 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"# GraphQL tool\n",
|
||||
"This Jupyter Notebook demonstrates how to use the BaseGraphQLTool component with an Agent.\n",
|
||||
"\n",
|
||||
"GraphQL is a query language for APIs and a runtime for executing those queries against your data. GraphQL provides a complete and understandable description of the data in your API, gives clients the power to ask for exactly what they need and nothing more, makes it easier to evolve APIs over time, and enables powerful developer tools.\n",
|
||||
"\n",
|
||||
"By including a BaseGraphQLTool in the list of tools provided to an Agent, you can grant your Agent the ability to query data from GraphQL APIs for any purposes you need.\n",
|
||||
"\n",
|
||||
"In this example, we'll be using the public Star Wars GraphQL API available at the following endpoint: https://swapi-graphql.netlify.app/.netlify/functions/index.\n",
|
||||
"\n",
|
||||
"First, you need to install httpx and gql Python packages."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install httpx gql > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, let's create a BaseGraphQLTool instance with the specified Star Wars API endpoint and initialize an Agent with the tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent, AgentType\n",
|
||||
"from langchain.utilities import GraphQLAPIWrapper\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"tools = load_tools(\n",
|
||||
" [\"graphql\"],\n",
|
||||
" graphql_endpoint=\"https://swapi-graphql.netlify.app/.netlify/functions/index\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, we can use the Agent to run queries against the Star Wars GraphQL API. Let's ask the Agent to list all the Star Wars films and their release dates."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to query the graphql database to get the titles of all the star wars films\n",
|
||||
"Action: query_graphql\n",
|
||||
"Action Input: query { allFilms { films { title } } }\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\"{\\n \\\"allFilms\\\": {\\n \\\"films\\\": [\\n {\\n \\\"title\\\": \\\"A New Hope\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Empire Strikes Back\\\"\\n },\\n {\\n \\\"title\\\": \\\"Return of the Jedi\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Phantom Menace\\\"\\n },\\n {\\n \\\"title\\\": \\\"Attack of the Clones\\\"\\n },\\n {\\n \\\"title\\\": \\\"Revenge of the Sith\\\"\\n }\\n ]\\n }\\n}\"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the titles of all the star wars films\n",
|
||||
"Final Answer: The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"graphql_fields = \"\"\"allFilms {\n",
|
||||
" films {\n",
|
||||
" title\n",
|
||||
" director\n",
|
||||
" releaseDate\n",
|
||||
" speciesConnection {\n",
|
||||
" species {\n",
|
||||
" name\n",
|
||||
" classification\n",
|
||||
" homeworld {\n",
|
||||
" name\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"suffix = \"Search for the titles of all the stawars films stored in the graphql database that has this schema \"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"agent.run(suffix + graphql_fields)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"interpreter": {
|
||||
"hash": "f85209c3c4c190dca7367d6a1e623da50a9a4392fd53313a7cf9d4bda9c4b85b"
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.9.16 ('langchain')",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.16"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,102 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "40a27d3c-4e5c-4b96-b290-4c49d4fd7219",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## HuggingFace Tools\n",
|
||||
"\n",
|
||||
"[Huggingface Tools](https://huggingface.co/docs/transformers/v4.29.0/en/custom_tools) supporting text I/O can be\n",
|
||||
"loaded directly using the `load_huggingface_tool` function."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d1055b75-362c-452a-b40d-c9a359706a3a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Requires transformers>=4.29.0 and huggingface_hub>=0.14.1\n",
|
||||
"!pip install --upgrade transformers huggingface_hub > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f964bb45-fba3-4919-b022-70a602ed4354",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"model_download_counter: This is a tool that returns the most downloaded model of a given task on the Hugging Face Hub. It takes the name of the category (such as text-classification, depth-estimation, etc), and returns the name of the checkpoint\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.agents import load_huggingface_tool\n",
|
||||
"\n",
|
||||
"tool = load_huggingface_tool(\"lysandre/hf-model-downloads\")\n",
|
||||
"\n",
|
||||
"print(f\"{tool.name}: {tool.description}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "641d9d79-95bb-469d-b40a-50f37375de7f",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'facebook/bart-large-mnli'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"text-classification\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "88724222-7c10-4aff-8713-751911dc8b63",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,288 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Human as a tool\n",
|
||||
"\n",
|
||||
"Human are AGI so they can certainly be used as a tool to help out AI agent \n",
|
||||
"when it is confused."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0.0)\n",
|
||||
"math_llm = OpenAI(temperature=0.0)\n",
|
||||
"tools = load_tools(\n",
|
||||
" [\"human\", \"llm-math\"],\n",
|
||||
" llm=math_llm,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the above code you can see the tool takes input directly from command line.\n",
|
||||
"You can customize `prompt_func` and `input_func` according to your need (as shown below)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI don't know Eric's surname, so I should ask a human for guidance.\n",
|
||||
"Action: Human\n",
|
||||
"Action Input: \"What is Eric's surname?\"\u001b[0m\n",
|
||||
"\n",
|
||||
"What is Eric's surname?\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" Zhu\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mZhu\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know Eric's surname is Zhu.\n",
|
||||
"Final Answer: Eric's surname is Zhu.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Eric's surname is Zhu.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\"What's my friend Eric's surname?\")\n",
|
||||
"# Answer with 'Zhu'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Configuring the Input Function\n",
|
||||
"\n",
|
||||
"By default, the `HumanInputRun` tool uses the python `input` function to get input from the user.\n",
|
||||
"You can customize the input_func to be anything you'd like.\n",
|
||||
"For instance, if you want to accept multi-line input, you could do the following:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_input() -> str:\n",
|
||||
" print(\"Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\")\n",
|
||||
" contents = []\n",
|
||||
" while True:\n",
|
||||
" try:\n",
|
||||
" line = input()\n",
|
||||
" except EOFError:\n",
|
||||
" break\n",
|
||||
" if line == \"q\":\n",
|
||||
" break\n",
|
||||
" contents.append(line)\n",
|
||||
" return \"\\n\".join(contents)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# You can modify the tool when loading\n",
|
||||
"tools = load_tools([\"human\", \"ddg-search\"], llm=math_llm, input_func=get_input)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Or you can directly instantiate the tool\n",
|
||||
"from langchain.tools import HumanInputRun\n",
|
||||
"\n",
|
||||
"tool = HumanInputRun(input_func=get_input)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI should ask a human for guidance\n",
|
||||
"Action: Human\n",
|
||||
"Action Input: \"Can you help me attribute a quote?\"\u001b[0m\n",
|
||||
"\n",
|
||||
"Can you help me attribute a quote?\n",
|
||||
"Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" vini\n",
|
||||
" vidi\n",
|
||||
" vici\n",
|
||||
" q\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mvini\n",
|
||||
"vidi\n",
|
||||
"vici\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI need to provide more context about the quote\n",
|
||||
"Action: Human\n",
|
||||
"Action Input: \"The quote is 'Veni, vidi, vici'\"\u001b[0m\n",
|
||||
"\n",
|
||||
"The quote is 'Veni, vidi, vici'\n",
|
||||
"Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" oh who said it \n",
|
||||
" q\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3moh who said it \u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI can use DuckDuckGo Search to find out who said the quote\n",
|
||||
"Action: DuckDuckGo Search\n",
|
||||
"Action Input: \"Who said 'Veni, vidi, vici'?\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mUpdated on September 06, 2019. \"Veni, vidi, vici\" is a famous phrase said to have been spoken by the Roman Emperor Julius Caesar (100-44 BCE) in a bit of stylish bragging that impressed many of the writers of his day and beyond. The phrase means roughly \"I came, I saw, I conquered\" and it could be pronounced approximately Vehnee, Veedee ... Veni, vidi, vici (Classical Latin: [weːniː wiːdiː wiːkiː], Ecclesiastical Latin: [ˈveni ˈvidi ˈvitʃi]; \"I came; I saw; I conquered\") is a Latin phrase used to refer to a swift, conclusive victory.The phrase is popularly attributed to Julius Caesar who, according to Appian, used the phrase in a letter to the Roman Senate around 47 BC after he had achieved a quick victory in his short ... veni, vidi, vici Latin quotation from Julius Caesar ve· ni, vi· di, vi· ci ˌwā-nē ˌwē-dē ˈwē-kē ˌvā-nē ˌvē-dē ˈvē-chē : I came, I saw, I conquered Articles Related to veni, vidi, vici 'In Vino Veritas' and Other Latin... Dictionary Entries Near veni, vidi, vici Venite veni, vidi, vici Venizélos See More Nearby Entries Cite this Entry Style The simplest explanation for why veni, vidi, vici is a popular saying is that it comes from Julius Caesar, one of history's most famous figures, and has a simple, strong meaning: I'm powerful and fast. But it's not just the meaning that makes the phrase so powerful. Caesar was a gifted writer, and the phrase makes use of Latin grammar to ... One of the best known and most frequently quoted Latin expression, veni, vidi, vici may be found hundreds of times throughout the centuries used as an expression of triumph. The words are said to have been used by Caesar as he was enjoying a triumph.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
|
||||
"Final Answer: Julius Caesar said the quote \"Veni, vidi, vici\" which means \"I came, I saw, I conquered\".\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Julius Caesar said the quote \"Veni, vidi, vici\" which means \"I came, I saw, I conquered\".'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\"I need help attributing a quote\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,124 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "16763ed3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# IFTTT WebHooks\n",
|
||||
"\n",
|
||||
"This notebook shows how to use IFTTT Webhooks.\n",
|
||||
"\n",
|
||||
"From https://github.com/SidU/teams-langchain-js/wiki/Connecting-IFTTT-Services.\n",
|
||||
"\n",
|
||||
"## Creating a webhook\n",
|
||||
"- Go to https://ifttt.com/create\n",
|
||||
"\n",
|
||||
"## Configuring the \"If This\"\n",
|
||||
"- Click on the \"If This\" button in the IFTTT interface.\n",
|
||||
"- Search for \"Webhooks\" in the search bar.\n",
|
||||
"- Choose the first option for \"Receive a web request with a JSON payload.\"\n",
|
||||
"- Choose an Event Name that is specific to the service you plan to connect to.\n",
|
||||
"This will make it easier for you to manage the webhook URL.\n",
|
||||
"For example, if you're connecting to Spotify, you could use \"Spotify\" as your\n",
|
||||
"Event Name.\n",
|
||||
"- Click the \"Create Trigger\" button to save your settings and create your webhook.\n",
|
||||
"\n",
|
||||
"## Configuring the \"Then That\"\n",
|
||||
"- Tap on the \"Then That\" button in the IFTTT interface.\n",
|
||||
"- Search for the service you want to connect, such as Spotify.\n",
|
||||
"- Choose an action from the service, such as \"Add track to a playlist\".\n",
|
||||
"- Configure the action by specifying the necessary details, such as the playlist name,\n",
|
||||
"e.g., \"Songs from AI\".\n",
|
||||
"- Reference the JSON Payload received by the Webhook in your action. For the Spotify\n",
|
||||
"scenario, choose \"{{JsonPayload}}\" as your search query.\n",
|
||||
"- Tap the \"Create Action\" button to save your action settings.\n",
|
||||
"- Once you have finished configuring your action, click the \"Finish\" button to\n",
|
||||
"complete the setup.\n",
|
||||
"- Congratulations! You have successfully connected the Webhook to the desired\n",
|
||||
"service, and you're ready to start receiving data and triggering actions 🎉\n",
|
||||
"\n",
|
||||
"## Finishing up\n",
|
||||
"- To get your webhook URL go to https://ifttt.com/maker_webhooks/settings\n",
|
||||
"- Copy the IFTTT key value from there. The URL is of the form\n",
|
||||
"https://maker.ifttt.com/use/YOUR_IFTTT_KEY. Grab the YOUR_IFTTT_KEY value.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "10a46e7e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools.ifttt import IFTTTWebhook"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "12003d72",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"key = os.environ[\"IFTTTKey\"]\n",
|
||||
"url = f\"https://maker.ifttt.com/trigger/spotify/json/with/key/{key}\"\n",
|
||||
"tool = IFTTTWebhook(\n",
|
||||
" name=\"Spotify\", description=\"Add a song to spotify playlist\", url=url\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "6e68f846",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Congratulations! You've fired the spotify JSON event\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"taylor swift\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a7e599c9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
---
|
||||
sidebar_position: 0
|
||||
---
|
||||
|
||||
# Tools
|
||||
|
||||
import DocCardList from "@theme/DocCardList";
|
||||
|
||||
<DocCardList />
|
||||
@@ -0,0 +1,233 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "16763ed3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Lemon AI NLP Workflow Automation\n",
|
||||
"\\\n",
|
||||
"Full docs are available at: https://github.com/felixbrock/lemonai-py-client\n",
|
||||
"\n",
|
||||
"**Lemon AI helps you build powerful AI assistants in minutes and automate workflows by allowing for accurate and reliable read and write operations in tools like Airtable, Hubspot, Discord, Notion, Slack and Github.**\n",
|
||||
"\n",
|
||||
"Most connectors available today are focused on read-only operations, limiting the potential of LLMs. Agents, on the other hand, have a tendency to hallucinate from time to time due to missing context or instructions.\n",
|
||||
"\n",
|
||||
"With Lemon AI, it is possible to give your agents access to well-defined APIs for reliable read and write operations. In addition, Lemon AI functions allow you to further reduce the risk of hallucinations by providing a way to statically define workflows that the model can rely on in case of uncertainty."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "4881b484-1b97-478f-b206-aec407ceff66",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Quick Start\n",
|
||||
"\n",
|
||||
"The following quick start demonstrates how to use Lemon AI in combination with Agents to automate workflows that involve interaction with internal tooling."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ff91b41a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1. Install Lemon AI\n",
|
||||
"\n",
|
||||
"Requires Python 3.8.1 and above.\n",
|
||||
"\n",
|
||||
"To use Lemon AI in your Python project run `pip install lemonai`\n",
|
||||
"\n",
|
||||
"This will install the corresponding Lemon AI client which you can then import into your script.\n",
|
||||
"\n",
|
||||
"The tool uses Python packages langchain and loguru. In case of any installation errors with Lemon AI, install both packages first and then install the Lemon AI package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "340ff63d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2. Launch the Server\n",
|
||||
"\n",
|
||||
"The interaction of your agents and all tools provided by Lemon AI is handled by the [Lemon AI Server](https://github.com/felixbrock/lemonai-server). To use Lemon AI you need to run the server on your local machine so the Lemon AI Python client can connect to it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e845f402",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 3. Use Lemon AI with Langchain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d3ae6a82",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Lemon AI automatically solves given tasks by finding the right combination of relevant tools or uses Lemon AI Functions as an alternative. The following example demonstrates how to retrieve a user from Hackernews and write it to a table in Airtable:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "43476a22",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### (Optional) Define your Lemon AI Functions"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "cb038670",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Similar to [OpenAI functions](https://openai.com/blog/function-calling-and-other-api-updates), Lemon AI provides the option to define workflows as reusable functions. These functions can be defined for use cases where it is especially important to move as close as possible to near-deterministic behavior. Specific workflows can be defined in a separate lemonai.json:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e423ebbb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```json\n",
|
||||
"[\n",
|
||||
" {\n",
|
||||
" \"name\": \"Hackernews Airtable User Workflow\",\n",
|
||||
" \"description\": \"retrieves user data from Hackernews and appends it to a table in Airtable\",\n",
|
||||
" \"tools\": [\"hackernews-get-user\", \"airtable-append-data\"]\n",
|
||||
" }\n",
|
||||
"]\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "3fdb36ce",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Your model will have access to these functions and will prefer them over self-selecting tools to solve a given task. All you have to do is to let the agent know that it should use a given function by including the function name in the prompt."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ebfb8b5d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Include Lemon AI in your Langchain project "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "5318715d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from lemonai import execute_workflow\n",
|
||||
"from langchain import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "c9d082cb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Load API Keys and Access Tokens\n",
|
||||
"\n",
|
||||
"To use tools that require authentication, you have to store the corresponding access credentials in your environment in the format \"{tool name}_{authentication string}\" where the authentication string is one of [\"API_KEY\", \"SECRET_KEY\", \"SUBSCRIPTION_KEY\", \"ACCESS_KEY\"] for API keys or [\"ACCESS_TOKEN\", \"SECRET_TOKEN\"] for authentication tokens. Examples are \"OPENAI_API_KEY\", \"BING_SUBSCRIPTION_KEY\", \"AIRTABLE_ACCESS_TOKEN\"."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "a370d999",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\"\"\" Load all relevant API Keys and Access Tokens into your environment variables \"\"\"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"*INSERT OPENAI API KEY HERE*\"\n",
|
||||
"os.environ[\"AIRTABLE_ACCESS_TOKEN\"] = \"*INSERT AIRTABLE TOKEN HERE*\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "38d158e7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"hackernews_username = \"*INSERT HACKERNEWS USERNAME HERE*\"\n",
|
||||
"airtable_base_id = \"*INSERT BASE ID HERE*\"\n",
|
||||
"airtable_table_id = \"*INSERT TABLE ID HERE*\"\n",
|
||||
"\n",
|
||||
"\"\"\" Define your instruction to be given to your LLM \"\"\"\n",
|
||||
"prompt = f\"\"\"Read information from Hackernews for user {hackernews_username} and then write the results to\n",
|
||||
"Airtable (baseId: {airtable_base_id}, tableId: {airtable_table_id}). Only write the fields \"username\", \"karma\"\n",
|
||||
"and \"created_at_i\". Please make sure that Airtable does NOT automatically convert the field types.\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"\"\"\"\n",
|
||||
"Use the Lemon AI execute_workflow wrapper \n",
|
||||
"to run your Langchain agent in combination with Lemon AI \n",
|
||||
"\"\"\"\n",
|
||||
"model = OpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"execute_workflow(llm=model, prompt_string=prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "aef3e801",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 4. Gain transparency on your Agent's decision making\n",
|
||||
"\n",
|
||||
"To gain transparency on how your Agent interacts with Lemon AI tools to solve a given task, all decisions made, tools used and operations performed are written to a local `lemonai.log` file. Every time your LLM agent is interacting with the Lemon AI tool stack a corresponding log entry is created.\n",
|
||||
"\n",
|
||||
"```log\n",
|
||||
"2023-06-26T11:50:27.708785+0100 - b5f91c59-8487-45c2-800a-156eac0c7dae - hackernews-get-user\n",
|
||||
"2023-06-26T11:50:39.624035+0100 - b5f91c59-8487-45c2-800a-156eac0c7dae - airtable-append-data\n",
|
||||
"2023-06-26T11:58:32.925228+0100 - 5efe603c-9898-4143-b99a-55b50007ed9d - hackernews-get-user\n",
|
||||
"2023-06-26T11:58:43.988788+0100 - 5efe603c-9898-4143-b99a-55b50007ed9d - airtable-append-data\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"By using the [Lemon AI Analytics Tool](https://github.com/felixbrock/lemonai-analytics) you can easily gain a better understanding of how frequently and in which order tools are used. As a result, you can identify weak spots in your agent’s decision-making capabilities and move to a more deterministic behavior by defining Lemon AI functions."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,193 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Metaphor Search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Metaphor is a search engine fully designed to be used by LLMs. You can search and then get the contents for any page.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Metaphor search.\n",
|
||||
"\n",
|
||||
"First, you need to set up the proper API keys and environment variables. Get 1000 free searches/month [here](https://platform.metaphor.systems/).\n",
|
||||
"\n",
|
||||
"Then enter your API key as an environment variable."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"METAPHOR_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import MetaphorSearchAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = MetaphorSearchAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Call the API\n",
|
||||
"`results` takes in a Metaphor-optimized search query and a number of results (up to 500). It returns a list of results with title, url, author, and creation date."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search.results(\"The best blog post about AI safety is definitely this: \", 10)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding filters\n",
|
||||
"We can also add filters to our search. \n",
|
||||
"\n",
|
||||
"include_domains: Optional[List[str]] - List of domains to include in the search. If specified, results will only come from these domains. Only one of include_domains and exclude_domains should be specified.\n",
|
||||
"\n",
|
||||
"exclude_domains: Optional[List[str]] - List of domains to exclude in the search. If specified, results will only come from these domains. Only one of include_domains and exclude_domains should be specified.\n",
|
||||
"\n",
|
||||
"start_crawl_date: Optional[str] - \"Crawl date\" refers to the date that Metaphor discovered a link, which is more granular and can be more useful than published date. If start_crawl_date is specified, results will only include links that were crawled after start_crawl_date. Must be specified in ISO 8601 format (YYYY-MM-DDTHH:MM:SSZ)\n",
|
||||
"\n",
|
||||
"end_crawl_date: Optional[str] - \"Crawl date\" refers to the date that Metaphor discovered a link, which is more granular and can be more useful than published date. If endCrawlDate is specified, results will only include links that were crawled before end_crawl_date. Must be specified in ISO 8601 format (YYYY-MM-DDTHH:MM:SSZ)\n",
|
||||
"\n",
|
||||
"start_published_date: Optional[str] - If specified, only links with a published date after start_published_date will be returned. Must be specified in ISO 8601 format (YYYY-MM-DDTHH:MM:SSZ). Note that for some links, we have no published date, and these links will be excluded from the results if start_published_date is specified.\n",
|
||||
"\n",
|
||||
"end_published_date: Optional[str] - If specified, only links with a published date before end_published_date will be returned. Must be specified in ISO 8601 format (YYYY-MM-DDTHH:MM:SSZ). Note that for some links, we have no published date, and these links will be excluded from the results if end_published_date is specified.\n",
|
||||
"\n",
|
||||
"See full docs [here](https://metaphorapi.readme.io/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search.results(\n",
|
||||
" \"The best blog post about AI safety is definitely this: \",\n",
|
||||
" 10,\n",
|
||||
" include_domains=[\"lesswrong.com\"],\n",
|
||||
" start_published_date=\"2019-01-01\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Use Metaphor as a tool\n",
|
||||
"Metaphor can be used as a tool that gets URLs that other tools such as browsing tools."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install playwright\n",
|
||||
"from langchain.agents.agent_toolkits import PlayWrightBrowserToolkit\n",
|
||||
"from langchain.tools.playwright.utils import (\n",
|
||||
" create_async_playwright_browser, # A synchronous browser is available, though it isn't compatible with jupyter.\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"async_browser = create_async_playwright_browser()\n",
|
||||
"toolkit = PlayWrightBrowserToolkit.from_browser(async_browser=async_browser)\n",
|
||||
"tools = toolkit.get_tools()\n",
|
||||
"\n",
|
||||
"tools_by_name = {tool.name: tool for tool in tools}\n",
|
||||
"print(tools_by_name.keys())\n",
|
||||
"navigate_tool = tools_by_name[\"navigate_browser\"]\n",
|
||||
"extract_text = tools_by_name[\"extract_text\"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import initialize_agent, AgentType\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.tools import MetaphorSearchResults\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.7)\n",
|
||||
"\n",
|
||||
"metaphor_tool = MetaphorSearchResults(api_wrapper=search)\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" [metaphor_tool, extract_text, navigate_tool],\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent_chain.run(\n",
|
||||
" \"find me an interesting tweet about AI safety using Metaphor, then tell me the first sentence in the post. Do not finish until able to retrieve the first sentence.\"\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.11"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,170 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenWeatherMap API\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the OpenWeatherMap component to fetch weather information.\n",
|
||||
"\n",
|
||||
"First, you need to sign up for an OpenWeatherMap API key:\n",
|
||||
"\n",
|
||||
"1. Go to OpenWeatherMap and sign up for an API key [here](https://openweathermap.org/api/)\n",
|
||||
"2. pip install pyowm\n",
|
||||
"\n",
|
||||
"Then we will need to set some environment variables:\n",
|
||||
"1. Save your API KEY into OPENWEATHERMAP_API_KEY env variable\n",
|
||||
"\n",
|
||||
"## Use the wrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "34bb5968",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import OpenWeatherMapAPIWrapper\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENWEATHERMAP_API_KEY\"] = \"\"\n",
|
||||
"\n",
|
||||
"weather = OpenWeatherMapAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "ac4910f8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"In London,GB, the current weather is as follows:\n",
|
||||
"Detailed status: broken clouds\n",
|
||||
"Wind speed: 2.57 m/s, direction: 240°\n",
|
||||
"Humidity: 55%\n",
|
||||
"Temperature: \n",
|
||||
" - Current: 20.12°C\n",
|
||||
" - High: 21.75°C\n",
|
||||
" - Low: 18.68°C\n",
|
||||
" - Feels like: 19.62°C\n",
|
||||
"Rain: {}\n",
|
||||
"Heat index: None\n",
|
||||
"Cloud cover: 75%\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"weather_data = weather.run(\"London,GB\")\n",
|
||||
"print(weather_data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e73cfa56",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use the tool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "b3367417",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent, AgentType\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
|
||||
"os.environ[\"OPENWEATHERMAP_API_KEY\"] = \"\"\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"tools = load_tools([\"openweathermap-api\"], llm)\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools=tools, llm=llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "bf4f6854",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out the current weather in London.\n",
|
||||
"Action: OpenWeatherMap\n",
|
||||
"Action Input: London,GB\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mIn London,GB, the current weather is as follows:\n",
|
||||
"Detailed status: broken clouds\n",
|
||||
"Wind speed: 2.57 m/s, direction: 240°\n",
|
||||
"Humidity: 56%\n",
|
||||
"Temperature: \n",
|
||||
" - Current: 20.11°C\n",
|
||||
" - High: 21.75°C\n",
|
||||
" - Low: 18.68°C\n",
|
||||
" - Feels like: 19.64°C\n",
|
||||
"Rain: {}\n",
|
||||
"Heat index: None\n",
|
||||
"Cloud cover: 75%\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather in London.\n",
|
||||
"Final Answer: The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\"What's the weather like in London?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,86 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "64f20f38",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# PubMed Tool\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use PubMed as a tool\n",
|
||||
"\n",
|
||||
"PubMed® comprises more than 35 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web sites."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "c80b9273",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import PubmedQueryRun"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f203c965",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool = PubmedQueryRun()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "baee7a2a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Published: <Year>2023</Year><Month>May</Month><Day>31</Day>\\nTitle: Dermatology in the wake of an AI revolution: who gets a say?\\nSummary: \\n\\nPublished: <Year>2023</Year><Month>May</Month><Day>30</Day>\\nTitle: What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.\\nSummary: \\n\\nPublished: <Year>2023</Year><Month>Jun</Month><Day>02</Day>\\nTitle: The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.\\nSummary: The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"chatgpt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "965903ba",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,95 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "984a8fca",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Python REPL\n",
|
||||
"\n",
|
||||
"Sometimes, for complex calculations, rather than have an LLM generate the answer directly, it can be better to have the LLM generate code to calculate the answer, and then run that code to get the answer. In order to easily do that, we provide a simple Python REPL to execute commands in.\n",
|
||||
"\n",
|
||||
"This interface will only return things that are printed - therefore, if you want to use it to calculate an answer, make sure to have it print out the answer."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f6593089",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"from langchain.utilities import PythonREPL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6f21f0a4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"python_repl = PythonREPL()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "7ebbbaea",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'2\\n'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"python_repl.run(\"print(1+1)\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "54fc1f03",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# You can create the tool to pass to an agent\n",
|
||||
"repl_tool = Tool(\n",
|
||||
" name=\"python_repl\",\n",
|
||||
" description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
|
||||
" func=python_repl.run,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,140 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SceneXplain\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"[SceneXplain](https://scenex.jina.ai/) is an ImageCaptioning service accessible through the SceneXplain Tool.\n",
|
||||
"\n",
|
||||
"To use this tool, you'll need to make an account and fetch your API Token [from the website](https://scenex.jina.ai/api). Then you can instantiate the tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"SCENEX_API_KEY\"] = \"<YOUR_API_KEY>\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import load_tools\n",
|
||||
"\n",
|
||||
"tools = load_tools([\"sceneXplain\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Or directly instantiate the tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import SceneXplainTool\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"tool = SceneXplainTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage in an Agent\n",
|
||||
"\n",
|
||||
"The tool can be used in any LangChain agent as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\n",
|
||||
"Thought: Do I need to use a tool? Yes\n",
|
||||
"Action: Image Explainer\n",
|
||||
"Action Input: https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mIn a charmingly whimsical scene, a young girl is seen braving the rain alongside her furry companion, the lovable Totoro. The two are depicted standing on a bustling street corner, where they are sheltered from the rain by a bright yellow umbrella. The girl, dressed in a cheerful yellow frock, holds onto the umbrella with both hands while gazing up at Totoro with an expression of wonder and delight.\n",
|
||||
"\n",
|
||||
"Totoro, meanwhile, stands tall and proud beside his young friend, holding his own umbrella aloft to protect them both from the downpour. His furry body is rendered in rich shades of grey and white, while his large ears and wide eyes lend him an endearing charm.\n",
|
||||
"\n",
|
||||
"In the background of the scene, a street sign can be seen jutting out from the pavement amidst a flurry of raindrops. A sign with Chinese characters adorns its surface, adding to the sense of cultural diversity and intrigue. Despite the dreary weather, there is an undeniable sense of joy and camaraderie in this heartwarming image.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
|
||||
"AI: This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, memory=memory, agent=\"conversational-react-description\", verbose=True\n",
|
||||
")\n",
|
||||
"output = agent.run(\n",
|
||||
" input=(\n",
|
||||
" \"What is in this image https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png. \"\n",
|
||||
" \"Is it movie or a game? If it is a movie, what is the name of the movie?\"\n",
|
||||
" )\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(output)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,364 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6510f51c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Search Tools\n",
|
||||
"\n",
|
||||
"This notebook shows off usage of various search tools."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e6860c2d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import load_tools\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "dadbcfcd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ee251155",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Google Serper API Wrapper\n",
|
||||
"\n",
|
||||
"First, let's try to use the Google Serper API tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "0cdaa487",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"google-serper\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "01b1ab4a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "5cf44ec0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I should look up the current weather conditions.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m37°F\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the current temperature in Pomfret.\n",
|
||||
"Final Answer: The current temperature in Pomfret is 37°F.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current temperature in Pomfret is 37°F.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0e39fc46",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## SerpAPI\n",
|
||||
"\n",
|
||||
"Now, let's use the SerpAPI tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "e1c39a0f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"serpapi\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "900dd6cb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "342ee8ec",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what the current weather is in Pomfret.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mPartly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather in Pomfret.\n",
|
||||
"Final Answer: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "adc8bb68",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## GoogleSearchAPIWrapper\n",
|
||||
"\n",
|
||||
"Now, let's use the official Google Search API Wrapper."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "ef24f92d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"google-search\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "909cd28b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "46515d2a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I should look up the current weather conditions.\n",
|
||||
"Action: Google Search\n",
|
||||
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mShowers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Hourly Weather-Pomfret, CT. As of 12:52 am EST. Special Weather Statement +2 ... Hazardous Weather Conditions. Special Weather Statement ... Pomfret CT. Tonight ... National Digital Forecast Database Maximum Temperature Forecast. Pomfret Center Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Pomfret, CT 12 hour by hour weather forecast includes precipitation, temperatures, sky conditions, rain chance, dew-point, relative humidity, wind direction ... North Pomfret Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Today's Weather - Pomfret, CT. Dec 31, 2022 4:00 PM. Putnam MS. --. Weather forecast icon. Feels like --. Hi --. Lo --. Pomfret, CT temperature trend for the next 14 Days. Find daytime highs and nighttime lows from TheWeatherNetwork.com. Pomfret, MD Weather Forecast Date: 332 PM EST Wed Dec 28 2022. The area/counties/county of: Charles, including the cites of: St. Charles and Waldorf.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather conditions in Pomfret.\n",
|
||||
"Final Answer: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.\u001b[0m\n",
|
||||
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eabad3af",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## SearxNG Meta Search Engine\n",
|
||||
"\n",
|
||||
"Here we will be using a self hosted SearxNG meta search engine."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "b196c704",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"searx-search\"], searx_host=\"http://localhost:8888\", llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "9023eeaa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "3aad92c1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I should look up the current weather\n",
|
||||
"Action: SearX Search\n",
|
||||
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mMainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.\n",
|
||||
"\n",
|
||||
"10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....\n",
|
||||
"\n",
|
||||
"10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....\n",
|
||||
"\n",
|
||||
"Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.\n",
|
||||
"\n",
|
||||
"Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’s Why We Get More Colds and Flu When It’s Cold Coast-To-Coast...\n",
|
||||
"\n",
|
||||
"Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...\n",
|
||||
"\n",
|
||||
"Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...\n",
|
||||
"\n",
|
||||
"Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...\n",
|
||||
"\n",
|
||||
"12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...\n",
|
||||
"\n",
|
||||
"Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.11"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,619 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "DUXgyWySl5"
|
||||
},
|
||||
"source": [
|
||||
"# SearxNG Search API\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use a self hosted SearxNG search API to search the web.\n",
|
||||
"\n",
|
||||
"You can [check this link](https://docs.searxng.org/dev/search_api.html) for more informations about Searx API parameters."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "OIHXztO2UT"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pprint\n",
|
||||
"from langchain.utilities import SearxSearchWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "4SzT9eDMjt"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SearxSearchWrapper(searx_host=\"http://127.0.0.1:8888\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "jCSkIlQDUK"
|
||||
},
|
||||
"source": [
|
||||
"For some engines, if a direct `answer` is available the warpper will print the answer instead of the full list of search results. You can use the `results` method of the wrapper if you want to obtain all the results."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "gGM9PVQX6m"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Paris is the capital of France, the largest country of Europe with 550 000 km2 (65 millions inhabitants). Paris has 2.234 million inhabitants end 2011. She is the core of Ile de France region (12 million people).'"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"What is the capital of France\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "OHyurqUPbS"
|
||||
},
|
||||
"source": [
|
||||
"## Custom Parameters\n",
|
||||
"\n",
|
||||
"SearxNG supports [135 search engines](https://docs.searxng.org/user/configured_engines.html). You can also customize the Searx wrapper with arbitrary named parameters that will be passed to the Searx search API . In the below example we will making a more interesting use of custom search parameters from searx search api."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "n1B2AyLKi4"
|
||||
},
|
||||
"source": [
|
||||
"In this example we will be using the `engines` parameters to query wikipedia"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "UTEdJ03LqA"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SearxSearchWrapper(\n",
|
||||
" searx_host=\"http://127.0.0.1:8888\", k=5\n",
|
||||
") # k is for max number of items"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "3FyQ6yHI8K",
|
||||
"tags": [
|
||||
"scroll-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Large language models (LLMs) represent a major advancement in AI, with the promise of transforming domains through learned knowledge. LLM sizes have been increasing 10X every year for the last few years, and as these models grow in complexity and size, so do their capabilities.\\n\\nGPT-3 can translate language, write essays, generate computer code, and more — all with limited to no supervision. In July 2020, OpenAI unveiled GPT-3, a language model that was easily the largest known at the time. Put simply, GPT-3 is trained to predict the next word in a sentence, much like how a text message autocomplete feature works.\\n\\nA large language model, or LLM, is a deep learning algorithm that can recognize, summarize, translate, predict and generate text and other content based on knowledge gained from massive datasets. Large language models are among the most successful applications of transformer models.\\n\\nAll of today’s well-known language models—e.g., GPT-3 from OpenAI, PaLM or LaMDA from Google, Galactica or OPT from Meta, Megatron-Turing from Nvidia/Microsoft, Jurassic-1 from AI21 Labs—are...\\n\\nLarge language models (LLMs) such as GPT-3are increasingly being used to generate text. These tools should be used with care, since they can generate content that is biased, non-verifiable, constitutes original research, or violates copyrights.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"large language model \", engines=[\"wiki\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "SYz8nFkt81"
|
||||
},
|
||||
"source": [
|
||||
"Passing other Searx parameters for searx like `language`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "32rDh0Mvbx"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Aprendizaje profundo (en inglés, deep learning) es un conjunto de algoritmos de aprendizaje automático (en inglés, machine learning) que intenta modelar abstracciones de alto nivel en datos usando arquitecturas computacionales que admiten transformaciones no lineales múltiples e iterativas de datos expresados en forma matricial o tensorial. 1'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search = SearxSearchWrapper(searx_host=\"http://127.0.0.1:8888\", k=1)\n",
|
||||
"search.run(\"deep learning\", language=\"es\", engines=[\"wiki\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "d0x164ssV1"
|
||||
},
|
||||
"source": [
|
||||
"## Obtaining results with metadata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "pF6rs8XcDH"
|
||||
},
|
||||
"source": [
|
||||
"In this example we will be looking for scientific paper using the `categories` parameter and limiting the results to a `time_range` (not all engines support the time range option).\n",
|
||||
"\n",
|
||||
"We also would like to obtain the results in a structured way including metadata. For this we will be using the `results` method of the wrapper."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "BFgpPH0sxF"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SearxSearchWrapper(searx_host=\"http://127.0.0.1:8888\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "r7qUtvKNOh",
|
||||
"tags": [
|
||||
"scroll-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[{'snippet': '… on natural language instructions, large language models (… the '\n",
|
||||
" 'prompt used to steer the model, and most effective prompts … to '\n",
|
||||
" 'prompt engineering, we propose Automatic Prompt …',\n",
|
||||
" 'title': 'Large language models are human-level prompt engineers',\n",
|
||||
" 'link': 'https://arxiv.org/abs/2211.01910',\n",
|
||||
" 'engines': ['google scholar'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': '… Large language models (LLMs) have introduced new possibilities '\n",
|
||||
" 'for prototyping with AI [18]. Pre-trained on a large amount of '\n",
|
||||
" 'text data, models … language instructions called prompts. …',\n",
|
||||
" 'title': 'Promptchainer: Chaining large language model prompts through '\n",
|
||||
" 'visual programming',\n",
|
||||
" 'link': 'https://dl.acm.org/doi/abs/10.1145/3491101.3519729',\n",
|
||||
" 'engines': ['google scholar'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': '… can introspect the large prompt model. We derive the view '\n",
|
||||
" 'ϕ0(X) and the model h0 from T01. However, instead of fully '\n",
|
||||
" 'fine-tuning T0 during co-training, we focus on soft prompt '\n",
|
||||
" 'tuning, …',\n",
|
||||
" 'title': 'Co-training improves prompt-based learning for large language '\n",
|
||||
" 'models',\n",
|
||||
" 'link': 'https://proceedings.mlr.press/v162/lang22a.html',\n",
|
||||
" 'engines': ['google scholar'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': '… With the success of large language models (LLMs) of code and '\n",
|
||||
" 'their use as … prompt design process become important. In this '\n",
|
||||
" 'work, we propose a framework called Repo-Level Prompt …',\n",
|
||||
" 'title': 'Repository-level prompt generation for large language models of '\n",
|
||||
" 'code',\n",
|
||||
" 'link': 'https://arxiv.org/abs/2206.12839',\n",
|
||||
" 'engines': ['google scholar'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': '… Figure 2 | The benefits of different components of a prompt '\n",
|
||||
" 'for the largest language model (Gopher), as estimated from '\n",
|
||||
" 'hierarchical logistic regression. Each point estimates the '\n",
|
||||
" 'unique …',\n",
|
||||
" 'title': 'Can language models learn from explanations in context?',\n",
|
||||
" 'link': 'https://arxiv.org/abs/2204.02329',\n",
|
||||
" 'engines': ['google scholar'],\n",
|
||||
" 'category': 'science'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = search.results(\n",
|
||||
" \"Large Language Model prompt\",\n",
|
||||
" num_results=5,\n",
|
||||
" categories=\"science\",\n",
|
||||
" time_range=\"year\",\n",
|
||||
")\n",
|
||||
"pprint.pp(results)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "2seI78pR8T"
|
||||
},
|
||||
"source": [
|
||||
"Get papers from arxiv"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "JyNgoFm0vo",
|
||||
"tags": [
|
||||
"scroll-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[{'snippet': 'Thanks to the advanced improvement of large pre-trained language '\n",
|
||||
" 'models, prompt-based fine-tuning is shown to be effective on a '\n",
|
||||
" 'variety of downstream tasks. Though many prompting methods have '\n",
|
||||
" 'been investigated, it remains unknown which type of prompts are '\n",
|
||||
" 'the most effective among three types of prompts (i.e., '\n",
|
||||
" 'human-designed prompts, schema prompts and null prompts). In '\n",
|
||||
" 'this work, we empirically compare the three types of prompts '\n",
|
||||
" 'under both few-shot and fully-supervised settings. Our '\n",
|
||||
" 'experimental results show that schema prompts are the most '\n",
|
||||
" 'effective in general. Besides, the performance gaps tend to '\n",
|
||||
" 'diminish when the scale of training data grows large.',\n",
|
||||
" 'title': 'Do Prompts Solve NLP Tasks Using Natural Language?',\n",
|
||||
" 'link': 'http://arxiv.org/abs/2203.00902v1',\n",
|
||||
" 'engines': ['arxiv'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': 'Cross-prompt automated essay scoring (AES) requires the system '\n",
|
||||
" 'to use non target-prompt essays to award scores to a '\n",
|
||||
" 'target-prompt essay. Since obtaining a large quantity of '\n",
|
||||
" 'pre-graded essays to a particular prompt is often difficult and '\n",
|
||||
" 'unrealistic, the task of cross-prompt AES is vital for the '\n",
|
||||
" 'development of real-world AES systems, yet it remains an '\n",
|
||||
" 'under-explored area of research. Models designed for '\n",
|
||||
" 'prompt-specific AES rely heavily on prompt-specific knowledge '\n",
|
||||
" 'and perform poorly in the cross-prompt setting, whereas current '\n",
|
||||
" 'approaches to cross-prompt AES either require a certain quantity '\n",
|
||||
" 'of labelled target-prompt essays or require a large quantity of '\n",
|
||||
" 'unlabelled target-prompt essays to perform transfer learning in '\n",
|
||||
" 'a multi-step manner. To address these issues, we introduce '\n",
|
||||
" 'Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES. Our '\n",
|
||||
" 'method requires no access to labelled or unlabelled '\n",
|
||||
" 'target-prompt data during training and is a single-stage '\n",
|
||||
" 'approach. PAES is easy to apply in practice and achieves '\n",
|
||||
" 'state-of-the-art performance on the Automated Student Assessment '\n",
|
||||
" 'Prize (ASAP) dataset.',\n",
|
||||
" 'title': 'Prompt Agnostic Essay Scorer: A Domain Generalization Approach to '\n",
|
||||
" 'Cross-prompt Automated Essay Scoring',\n",
|
||||
" 'link': 'http://arxiv.org/abs/2008.01441v1',\n",
|
||||
" 'engines': ['arxiv'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': 'Research on prompting has shown excellent performance with '\n",
|
||||
" 'little or even no supervised training across many tasks. '\n",
|
||||
" 'However, prompting for machine translation is still '\n",
|
||||
" 'under-explored in the literature. We fill this gap by offering a '\n",
|
||||
" 'systematic study on prompting strategies for translation, '\n",
|
||||
" 'examining various factors for prompt template and demonstration '\n",
|
||||
" 'example selection. We further explore the use of monolingual '\n",
|
||||
" 'data and the feasibility of cross-lingual, cross-domain, and '\n",
|
||||
" 'sentence-to-document transfer learning in prompting. Extensive '\n",
|
||||
" 'experiments with GLM-130B (Zeng et al., 2022) as the testbed '\n",
|
||||
" 'show that 1) the number and the quality of prompt examples '\n",
|
||||
" 'matter, where using suboptimal examples degenerates translation; '\n",
|
||||
" '2) several features of prompt examples, such as semantic '\n",
|
||||
" 'similarity, show significant Spearman correlation with their '\n",
|
||||
" 'prompting performance; yet, none of the correlations are strong '\n",
|
||||
" 'enough; 3) using pseudo parallel prompt examples constructed '\n",
|
||||
" 'from monolingual data via zero-shot prompting could improve '\n",
|
||||
" 'translation; and 4) improved performance is achievable by '\n",
|
||||
" 'transferring knowledge from prompt examples selected in other '\n",
|
||||
" 'settings. We finally provide an analysis on the model outputs '\n",
|
||||
" 'and discuss several problems that prompting still suffers from.',\n",
|
||||
" 'title': 'Prompting Large Language Model for Machine Translation: A Case '\n",
|
||||
" 'Study',\n",
|
||||
" 'link': 'http://arxiv.org/abs/2301.07069v2',\n",
|
||||
" 'engines': ['arxiv'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': 'Large language models can perform new tasks in a zero-shot '\n",
|
||||
" 'fashion, given natural language prompts that specify the desired '\n",
|
||||
" 'behavior. Such prompts are typically hand engineered, but can '\n",
|
||||
" 'also be learned with gradient-based methods from labeled data. '\n",
|
||||
" 'However, it is underexplored what factors make the prompts '\n",
|
||||
" 'effective, especially when the prompts are natural language. In '\n",
|
||||
" 'this paper, we investigate common attributes shared by effective '\n",
|
||||
" 'prompts. We first propose a human readable prompt tuning method '\n",
|
||||
" '(F LUENT P ROMPT) based on Langevin dynamics that incorporates a '\n",
|
||||
" 'fluency constraint to find a diverse distribution of effective '\n",
|
||||
" 'and fluent prompts. Our analysis reveals that effective prompts '\n",
|
||||
" 'are topically related to the task domain and calibrate the prior '\n",
|
||||
" 'probability of label words. Based on these findings, we also '\n",
|
||||
" 'propose a method for generating prompts using only unlabeled '\n",
|
||||
" 'data, outperforming strong baselines by an average of 7.0% '\n",
|
||||
" 'accuracy across three tasks.',\n",
|
||||
" 'title': \"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a \"\n",
|
||||
" 'good movie, and a good prompt too?',\n",
|
||||
" 'link': 'http://arxiv.org/abs/2212.10539v1',\n",
|
||||
" 'engines': ['arxiv'],\n",
|
||||
" 'category': 'science'},\n",
|
||||
" {'snippet': 'Prevailing methods for mapping large generative language models '\n",
|
||||
" \"to supervised tasks may fail to sufficiently probe models' novel \"\n",
|
||||
" 'capabilities. Using GPT-3 as a case study, we show that 0-shot '\n",
|
||||
" 'prompts can significantly outperform few-shot prompts. We '\n",
|
||||
" 'suggest that the function of few-shot examples in these cases is '\n",
|
||||
" 'better described as locating an already learned task rather than '\n",
|
||||
" 'meta-learning. This analysis motivates rethinking the role of '\n",
|
||||
" 'prompts in controlling and evaluating powerful language models. '\n",
|
||||
" 'In this work, we discuss methods of prompt programming, '\n",
|
||||
" 'emphasizing the usefulness of considering prompts through the '\n",
|
||||
" 'lens of natural language. We explore techniques for exploiting '\n",
|
||||
" 'the capacity of narratives and cultural anchors to encode '\n",
|
||||
" 'nuanced intentions and techniques for encouraging deconstruction '\n",
|
||||
" 'of a problem into components before producing a verdict. '\n",
|
||||
" 'Informed by this more encompassing theory of prompt programming, '\n",
|
||||
" 'we also introduce the idea of a metaprompt that seeds the model '\n",
|
||||
" 'to generate its own natural language prompts for a range of '\n",
|
||||
" 'tasks. Finally, we discuss how these more general methods of '\n",
|
||||
" 'interacting with language models can be incorporated into '\n",
|
||||
" 'existing and future benchmarks and practical applications.',\n",
|
||||
" 'title': 'Prompt Programming for Large Language Models: Beyond the Few-Shot '\n",
|
||||
" 'Paradigm',\n",
|
||||
" 'link': 'http://arxiv.org/abs/2102.07350v1',\n",
|
||||
" 'engines': ['arxiv'],\n",
|
||||
" 'category': 'science'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = search.results(\n",
|
||||
" \"Large Language Model prompt\", num_results=5, engines=[\"arxiv\"]\n",
|
||||
")\n",
|
||||
"pprint.pp(results)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "LhEisLFcZM"
|
||||
},
|
||||
"source": [
|
||||
"In this example we query for `large language models` under the `it` category. We then filter the results that come from github."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "aATPfXzGzx"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[{'snippet': 'Guide to using pre-trained large language models of source code',\n",
|
||||
" 'title': 'Code-LMs',\n",
|
||||
" 'link': 'https://github.com/VHellendoorn/Code-LMs',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Dramatron uses large language models to generate coherent '\n",
|
||||
" 'scripts and screenplays.',\n",
|
||||
" 'title': 'dramatron',\n",
|
||||
" 'link': 'https://github.com/deepmind/dramatron',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = search.results(\"large language model\", num_results=20, categories=\"it\")\n",
|
||||
"pprint.pp(list(filter(lambda r: r[\"engines\"][0] == \"github\", results)))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"jukit_cell_id": "zDo2YjafuU"
|
||||
},
|
||||
"source": [
|
||||
"We could also directly query for results from `github` and other source forges."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"jukit_cell_id": "5NrlredKxM",
|
||||
"tags": [
|
||||
"scroll-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[{'snippet': \"Implementation of 'A Watermark for Large Language Models' paper \"\n",
|
||||
" 'by Kirchenbauer & Geiping et. al.',\n",
|
||||
" 'title': 'Peutlefaire / LMWatermark',\n",
|
||||
" 'link': 'https://gitlab.com/BrianPulfer/LMWatermark',\n",
|
||||
" 'engines': ['gitlab'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Guide to using pre-trained large language models of source code',\n",
|
||||
" 'title': 'Code-LMs',\n",
|
||||
" 'link': 'https://github.com/VHellendoorn/Code-LMs',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': '',\n",
|
||||
" 'title': 'Simen Burud / Large-scale Language Models for Conversational '\n",
|
||||
" 'Speech Recognition',\n",
|
||||
" 'link': 'https://gitlab.com/BrianPulfer',\n",
|
||||
" 'engines': ['gitlab'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Dramatron uses large language models to generate coherent '\n",
|
||||
" 'scripts and screenplays.',\n",
|
||||
" 'title': 'dramatron',\n",
|
||||
" 'link': 'https://github.com/deepmind/dramatron',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Code for loralib, an implementation of \"LoRA: Low-Rank '\n",
|
||||
" 'Adaptation of Large Language Models\"',\n",
|
||||
" 'title': 'LoRA',\n",
|
||||
" 'link': 'https://github.com/microsoft/LoRA',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Code for the paper \"Evaluating Large Language Models Trained on '\n",
|
||||
" 'Code\"',\n",
|
||||
" 'title': 'human-eval',\n",
|
||||
" 'link': 'https://github.com/openai/human-eval',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'A trend starts from \"Chain of Thought Prompting Elicits '\n",
|
||||
" 'Reasoning in Large Language Models\".',\n",
|
||||
" 'title': 'Chain-of-ThoughtsPapers',\n",
|
||||
" 'link': 'https://github.com/Timothyxxx/Chain-of-ThoughtsPapers',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Mistral: A strong, northwesterly wind: Framework for transparent '\n",
|
||||
" 'and accessible large-scale language model training, built with '\n",
|
||||
" 'Hugging Face 🤗 Transformers.',\n",
|
||||
" 'title': 'mistral',\n",
|
||||
" 'link': 'https://github.com/stanford-crfm/mistral',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'A prize for finding tasks that cause large language models to '\n",
|
||||
" 'show inverse scaling',\n",
|
||||
" 'title': 'prize',\n",
|
||||
" 'link': 'https://github.com/inverse-scaling/prize',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Optimus: the first large-scale pre-trained VAE language model',\n",
|
||||
" 'title': 'Optimus',\n",
|
||||
" 'link': 'https://github.com/ChunyuanLI/Optimus',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Seminar on Large Language Models (COMP790-101 at UNC Chapel '\n",
|
||||
" 'Hill, Fall 2022)',\n",
|
||||
" 'title': 'llm-seminar',\n",
|
||||
" 'link': 'https://github.com/craffel/llm-seminar',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'A central, open resource for data and tools related to '\n",
|
||||
" 'chain-of-thought reasoning in large language models. Developed @ '\n",
|
||||
" 'Samwald research group: https://samwald.info/',\n",
|
||||
" 'title': 'ThoughtSource',\n",
|
||||
" 'link': 'https://github.com/OpenBioLink/ThoughtSource',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'A comprehensive list of papers using large language/multi-modal '\n",
|
||||
" 'models for Robotics/RL, including papers, codes, and related '\n",
|
||||
" 'websites',\n",
|
||||
" 'title': 'Awesome-LLM-Robotics',\n",
|
||||
" 'link': 'https://github.com/GT-RIPL/Awesome-LLM-Robotics',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Tools for curating biomedical training data for large-scale '\n",
|
||||
" 'language modeling',\n",
|
||||
" 'title': 'biomedical',\n",
|
||||
" 'link': 'https://github.com/bigscience-workshop/biomedical',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'ChatGPT @ Home: Large Language Model (LLM) chatbot application, '\n",
|
||||
" 'written by ChatGPT',\n",
|
||||
" 'title': 'ChatGPT-at-Home',\n",
|
||||
" 'link': 'https://github.com/Sentdex/ChatGPT-at-Home',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Design and Deploy Large Language Model Apps',\n",
|
||||
" 'title': 'dust',\n",
|
||||
" 'link': 'https://github.com/dust-tt/dust',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Polyglot: Large Language Models of Well-balanced Competence in '\n",
|
||||
" 'Multi-languages',\n",
|
||||
" 'title': 'polyglot',\n",
|
||||
" 'link': 'https://github.com/EleutherAI/polyglot',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'Code release for \"Learning Video Representations from Large '\n",
|
||||
" 'Language Models\"',\n",
|
||||
" 'title': 'LaViLa',\n",
|
||||
" 'link': 'https://github.com/facebookresearch/LaViLa',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'SmoothQuant: Accurate and Efficient Post-Training Quantization '\n",
|
||||
" 'for Large Language Models',\n",
|
||||
" 'title': 'smoothquant',\n",
|
||||
" 'link': 'https://github.com/mit-han-lab/smoothquant',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'},\n",
|
||||
" {'snippet': 'This repository contains the code, data, and models of the paper '\n",
|
||||
" 'titled \"XL-Sum: Large-Scale Multilingual Abstractive '\n",
|
||||
" 'Summarization for 44 Languages\" published in Findings of the '\n",
|
||||
" 'Association for Computational Linguistics: ACL-IJCNLP 2021.',\n",
|
||||
" 'title': 'xl-sum',\n",
|
||||
" 'link': 'https://github.com/csebuetnlp/xl-sum',\n",
|
||||
" 'engines': ['github'],\n",
|
||||
" 'category': 'it'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = search.results(\n",
|
||||
" \"large language model\", num_results=20, engines=[\"github\", \"gitlab\"]\n",
|
||||
")\n",
|
||||
"pprint.pp(results)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"anaconda-cloud": {},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,138 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dc23c48e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SerpAPI\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the SerpAPI component to search the web."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "54bf5afd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import SerpAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "31f8f382",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "25ce0225",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Barack Hussein Obama II'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"Obama's first name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fe3ee213",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Custom Parameters\n",
|
||||
"You can also customize the SerpAPI wrapper with arbitrary parameters. For example, in the below example we will use `bing` instead of `google`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "deffcc8b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"params = {\n",
|
||||
" \"engine\": \"bing\",\n",
|
||||
" \"gl\": \"us\",\n",
|
||||
" \"hl\": \"en\",\n",
|
||||
"}\n",
|
||||
"search = SerpAPIWrapper(params=params)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2c752d08",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Barack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American presi…New content will be added above the current area of focus upon selectionBarack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American president of the United States. He previously served as a U.S. senator from Illinois from 2005 to 2008 and as an Illinois state senator from 1997 to 2004, and previously worked as a civil rights lawyer before entering politics.Wikipediabarackobama.com'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"search.run(\"Obama's first name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e0a1dc1c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"\n",
|
||||
"# You can create the tool to pass to an agent\n",
|
||||
"repl_tool = Tool(\n",
|
||||
" name=\"python_repl\",\n",
|
||||
" description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
|
||||
" func=search.run,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,165 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "dc23c48e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Twilio\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the [Twilio](https://www.twilio.com) API wrapper to send a message through SMS or [Twilio Messaging Channels](https://www.twilio.com/docs/messaging/channels).\n",
|
||||
"\n",
|
||||
"Twilio Messaging Channels facilitates integrations with 3rd party messaging apps and lets you send messages through WhatsApp Business Platform (GA), Facebook Messenger (Public Beta) and Google Business Messages (Private Beta)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "c1a33b13",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"To use this tool you need to install the Python Twilio package `twilio`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "98b544b9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install twilio"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "f7e883ae",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You'll also need to set up a Twilio account and get your credentials. You'll need your Account String Identifier (SID) and your Auth Token. You'll also need a number to send messages from.\n",
|
||||
"\n",
|
||||
"You can either pass these in to the TwilioAPIWrapper as named parameters `account_sid`, `auth_token`, `from_number`, or you can set the environment variables `TWILIO_ACCOUNT_SID`, `TWILIO_AUTH_TOKEN`, `TWILIO_FROM_NUMBER`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "36c133be",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Sending an SMS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "54bf5afd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities.twilio import TwilioAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "31f8f382",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"twilio = TwilioAPIWrapper(\n",
|
||||
" # account_sid=\"foo\",\n",
|
||||
" # auth_token=\"bar\",\n",
|
||||
" # from_number=\"baz,\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5009d763",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"twilio.run(\"hello world\", \"+16162904619\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "de022dc9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Sending a WhatsApp Message"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "a594d0bc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You'll need to link your WhatsApp Business Account with Twilio. You'll also need to make sure that the number to send messages from is configured as a WhatsApp Enabled Sender on Twilio and registered with WhatsApp."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "94508aa0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities.twilio import TwilioAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e4b81750",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"twilio = TwilioAPIWrapper(\n",
|
||||
" # account_sid=\"foo\",\n",
|
||||
" # auth_token=\"bar\",\n",
|
||||
" # from_number=\"whatsapp: baz,\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1181041b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"twilio.run(\"hello world\", \"whatsapp: +16162904619\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,93 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Wikipedia\n",
|
||||
"\n",
|
||||
">[Wikipedia](https://wikipedia.org/) is a multilingual free online encyclopedia written and maintained by a community of volunteers, known as Wikipedians, through open collaboration and using a wiki-based editing system called MediaWiki. `Wikipedia` is the largest and most-read reference work in history.\n",
|
||||
"\n",
|
||||
"First, you need to install `wikipedia` python package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "961b3689",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install wikipedia"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "8d32b39a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import WikipediaQueryRun\n",
|
||||
"from langchain.utilities import WikipediaAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2a50dd27",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"wikipedia = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "34bb5968",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Page: Hunter × Hunter\\nSummary: Hunter × Hunter (stylized as HUNTER×HUNTER and pronounced \"hunter hunter\") is a Japanese manga series written and illustrated by Yoshihiro Togashi. It has been serialized in Shueisha\\'s shōnen manga magazine Weekly Shōnen Jump since March 1998, although the manga has frequently gone on extended hiatuses since 2006. Its chapters have been collected in 37 tankōbon volumes as of November 2022. The story focuses on a young boy named Gon Freecss who discovers that his father, who left him at a young age, is actually a world-renowned Hunter, a licensed professional who specializes in fantastical pursuits such as locating rare or unidentified animal species, treasure hunting, surveying unexplored enclaves, or hunting down lawless individuals. Gon departs on a journey to become a Hunter and eventually find his father. Along the way, Gon meets various other Hunters and encounters the paranormal.\\nHunter × Hunter was adapted into a 62-episode anime television series produced by Nippon Animation and directed by Kazuhiro Furuhashi, which ran on Fuji Television from October 1999 to March 2001. Three separate original video animations (OVAs) totaling 30 episodes were subsequently produced by Nippon Animation and released in Japan from 2002 to 2004. A second anime television series by Madhouse aired on Nippon Television from October 2011 to September 2014, totaling 148 episodes, with two animated theatrical films released in 2013. There are also numerous audio albums, video games, musicals, and other media based on Hunter × Hunter.\\nThe manga has been translated into English and released in North America by Viz Media since April 2005. Both television series have been also licensed by Viz Media, with the first series having aired on the Funimation Channel in 2009 and the second series broadcast on Adult Swim\\'s Toonami programming block from April 2016 to June 2019.\\nHunter × Hunter has been a huge critical and financial success and has become one of the best-selling manga series of all time, having over 84 million copies in circulation by July 2022.\\n\\nPage: Hunter × Hunter (2011 TV series)\\nSummary: Hunter × Hunter is an anime television series that aired from 2011 to 2014 based on Yoshihiro Togashi\\'s manga series Hunter × Hunter. The story begins with a young boy named Gon Freecss, who one day discovers that the father who he thought was dead, is in fact alive and well. He learns that his father, Ging, is a legendary \"Hunter\", an individual who has proven themselves an elite member of humanity. Despite the fact that Ging left his son with his relatives in order to pursue his own dreams, Gon becomes determined to follow in his father\\'s footsteps, pass the rigorous \"Hunter Examination\", and eventually find his father to become a Hunter in his own right.\\nThis new Hunter × Hunter anime was announced on July 24, 2011. It is a complete reboot starting from the beginning of the original manga, with no connection to the first anime television series from 1999. Produced by Nippon TV, VAP, Shueisha and Madhouse, the series is directed by Hiroshi Kōjina, with Atsushi Maekawa and Tsutomu Kamishiro handling series composition, Takahiro Yoshimatsu designing the characters and Yoshihisa Hirano composing the music. Instead of having the old cast reprise their roles for the new adaptation, the series features an entirely new cast to voice the characters. The new series premiered airing weekly on Nippon TV and the nationwide Nippon News Network from October 2, 2011. The series started to be collected in both DVD and Blu-ray format on January 25, 2012. Viz Media has licensed the anime for a DVD/Blu-ray release in North America with an English dub. On television, the series began airing on Adult Swim\\'s Toonami programming block on April 17, 2016, and ended on June 23, 2019.The anime series\\' opening theme is alternated between the song \"Departure!\" and an alternate version titled \"Departure! -Second Version-\" both sung by Galneryus\\' voc'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"wikipedia.run(\"HUNTER X HUNTER\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "245a954a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Wolfram Alpha\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the wolfram alpha component.\n",
|
||||
"\n",
|
||||
"First, you need to set up your Wolfram Alpha developer account and get your APP ID:\n",
|
||||
"\n",
|
||||
"1. Go to wolfram alpha and sign up for a developer account [here](https://developer.wolframalpha.com/)\n",
|
||||
"2. Create an app and get your APP ID\n",
|
||||
"3. pip install wolframalpha\n",
|
||||
"\n",
|
||||
"Then we will need to set some environment variables:\n",
|
||||
"1. Save your APP ID into WOLFRAM_ALPHA_APPID env variable"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "961b3689",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install wolframalpha"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "34bb5968",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"WOLFRAM_ALPHA_APPID\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "ac4910f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "84b8f773",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"wolfram = WolframAlphaAPIWrapper()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "068991a6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'x = 2/5'"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"wolfram.run(\"What is 2x+5 = -3x + 7?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "028f4cba",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.7"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "acb64858",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# YouTubeSearchTool\n",
|
||||
"\n",
|
||||
"This notebook shows how to use a tool to search YouTube\n",
|
||||
"\n",
|
||||
"Adapted from [https://github.com/venuv/langchain_yt_tools](https://github.com/venuv/langchain_yt_tools)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9bb15d4a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#! pip install youtube_search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "cc1c83e2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import YouTubeSearchTool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "becb262b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool = YouTubeSearchTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "6bbc4211",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"['/watch?v=VcVfceTsD0A&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=gPfriiHBBek&pp=ygUMbGV4IGZyaWVkbWFu']\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"lex friedman\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7f772147",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can also specify the number of results that are returned"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "682fdb33",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"['/watch?v=VcVfceTsD0A&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=YVJ8gTnDC4Y&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=Udh22kuLebg&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=gPfriiHBBek&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=L_Guz73e6fw&pp=ygUMbGV4IGZyaWVkbWFu']\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool.run(\"lex friedman,5\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bb5e1659",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,377 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "16763ed3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Zapier Natural Language Actions API\n",
|
||||
"\\\n",
|
||||
"Full docs here: https://nla.zapier.com/start/\n",
|
||||
"\n",
|
||||
"**Zapier Natural Language Actions** gives you access to the 5k+ apps, 20k+ actions on Zapier's platform through a natural language API interface.\n",
|
||||
"\n",
|
||||
"NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets, Microsoft Teams, and thousands more apps: https://zapier.com/apps\n",
|
||||
"\n",
|
||||
"Zapier NLA handles ALL the underlying API auth and translation from natural language --> underlying API call --> return simplified output for LLMs. The key idea is you, or your users, expose a set of actions via an oauth-like setup window, which you can then query and execute via a REST API.\n",
|
||||
"\n",
|
||||
"NLA offers both API Key and OAuth for signing NLA API requests.\n",
|
||||
"\n",
|
||||
"1. Server-side (API Key): for quickly getting started, testing, and production scenarios where LangChain will only use actions exposed in the developer's Zapier account (and will use the developer's connected accounts on Zapier.com)\n",
|
||||
"\n",
|
||||
"2. User-facing (Oauth): for production scenarios where you are deploying an end-user facing application and LangChain needs access to end-user's exposed actions and connected accounts on Zapier.com\n",
|
||||
"\n",
|
||||
"This quick start will focus mostly on the server-side use case for brevity. Jump to [Example Using OAuth Access Token](#oauth) to see a short example how to set up Zapier for user-facing situations. Review [full docs](https://nla.zapier.com/start/) for full user-facing oauth developer support.\n",
|
||||
"\n",
|
||||
"This example goes over how to use the Zapier integration with a `SimpleSequentialChain`, then an `Agent`.\n",
|
||||
"In code, below:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "5cf33377",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# get from https://platform.openai.com/\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"\")\n",
|
||||
"\n",
|
||||
"# get from https://nla.zapier.com/docs/authentication/ after logging in):\n",
|
||||
"os.environ[\"ZAPIER_NLA_API_KEY\"] = os.environ.get(\"ZAPIER_NLA_API_KEY\", \"\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4881b484-1b97-478f-b206-aec407ceff66",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example with Agent\n",
|
||||
"Zapier tools can be used with an agent. See the example below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "b2044b17-c941-4ffb-8a03-027a35e2df81",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.agents.agent_toolkits import ZapierToolkit\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.utilities.zapier import ZapierNLAWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "7b505eeb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## step 0. expose gmail 'find email' and slack 'send channel message' actions\n",
|
||||
"\n",
|
||||
"# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
|
||||
"# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "cab18227-c232-4214-9256-bb8dd352266c",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"zapier = ZapierNLAWrapper()\n",
|
||||
"toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "f94713de-b64d-465f-a087-00288b5f80ec",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find the email and summarize it.\n",
|
||||
"Action: Gmail: Find Email\n",
|
||||
"Action Input: Find the latest email from Silicon Valley Bank\u001b[0m\n",
|
||||
"Observation: \u001b[31;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.\n",
|
||||
"Action: Slack: Send Channel Message\n",
|
||||
"Action Input: Send a slack message to the #test-zapier channel with the text \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m{\"message__text\": \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\", \"message__permalink\": \"https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259\", \"channel\": \"C04TSGU0RA7\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:58:52Z\", \"message__bot_profile__icons__image_36\": \"https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png\", \"message__blocks[]block_id\": \"kdZZ\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\n",
|
||||
" \"Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack.\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bcdea831",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example with SimpleSequentialChain\n",
|
||||
"If you need more explicit control, use a chain, like below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "10a46e7e",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import LLMChain, TransformChain, SimpleSequentialChain\n",
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
"from langchain.tools.zapier.tool import ZapierNLARunAction\n",
|
||||
"from langchain.utilities.zapier import ZapierNLAWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "b9358048",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## step 0. expose gmail 'find email' and slack 'send direct message' actions\n",
|
||||
"\n",
|
||||
"# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
|
||||
"# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first\n",
|
||||
"\n",
|
||||
"actions = ZapierNLAWrapper().list()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "4e80f461",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## step 1. gmail find email\n",
|
||||
"\n",
|
||||
"GMAIL_SEARCH_INSTRUCTIONS = \"Grab the latest email from Silicon Valley Bank\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def nla_gmail(inputs):\n",
|
||||
" action = next(\n",
|
||||
" (a for a in actions if a[\"description\"].startswith(\"Gmail: Find Email\")), None\n",
|
||||
" )\n",
|
||||
" return {\n",
|
||||
" \"email_data\": ZapierNLARunAction(\n",
|
||||
" action_id=action[\"id\"],\n",
|
||||
" zapier_description=action[\"description\"],\n",
|
||||
" params_schema=action[\"params\"],\n",
|
||||
" ).run(inputs[\"instructions\"])\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"gmail_chain = TransformChain(\n",
|
||||
" input_variables=[\"instructions\"],\n",
|
||||
" output_variables=[\"email_data\"],\n",
|
||||
" transform=nla_gmail,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "46893233",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## step 2. generate draft reply\n",
|
||||
"\n",
|
||||
"template = \"\"\"You are an assisstant who drafts replies to an incoming email. Output draft reply in plain text (not JSON).\n",
|
||||
"\n",
|
||||
"Incoming email:\n",
|
||||
"{email_data}\n",
|
||||
"\n",
|
||||
"Draft email reply:\"\"\"\n",
|
||||
"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"email_data\"], template=template)\n",
|
||||
"reply_chain = LLMChain(llm=OpenAI(temperature=0.7), prompt=prompt_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "cd85c4f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## step 3. send draft reply via a slack direct message\n",
|
||||
"\n",
|
||||
"SLACK_HANDLE = \"@Ankush Gola\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def nla_slack(inputs):\n",
|
||||
" action = next(\n",
|
||||
" (\n",
|
||||
" a\n",
|
||||
" for a in actions\n",
|
||||
" if a[\"description\"].startswith(\"Slack: Send Direct Message\")\n",
|
||||
" ),\n",
|
||||
" None,\n",
|
||||
" )\n",
|
||||
" instructions = f'Send this to {SLACK_HANDLE} in Slack: {inputs[\"draft_reply\"]}'\n",
|
||||
" return {\n",
|
||||
" \"slack_data\": ZapierNLARunAction(\n",
|
||||
" action_id=action[\"id\"],\n",
|
||||
" zapier_description=action[\"description\"],\n",
|
||||
" params_schema=action[\"params\"],\n",
|
||||
" ).run(instructions)\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"slack_chain = TransformChain(\n",
|
||||
" input_variables=[\"draft_reply\"],\n",
|
||||
" output_variables=[\"slack_data\"],\n",
|
||||
" transform=nla_slack,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "4829cab4",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
|
||||
"\u001b[36;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
|
||||
"\u001b[33;1m\u001b[1;3m\n",
|
||||
"Dear Silicon Valley Bridge Bank, \n",
|
||||
"\n",
|
||||
"Thank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \n",
|
||||
"\n",
|
||||
"Best regards, \n",
|
||||
"[Your Name]\u001b[0m\n",
|
||||
"\u001b[38;5;200m\u001b[1;3m{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[['text']]\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\\\n\\\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\\\n\\\\nBest regards, \\\\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[[\\'text\\']]\", \"message__blocks[]elements[]type\": \"[\\'rich_text_section\\']\"}'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"## finally, execute\n",
|
||||
"\n",
|
||||
"overall_chain = SimpleSequentialChain(\n",
|
||||
" chains=[gmail_chain, reply_chain, slack_chain], verbose=True\n",
|
||||
")\n",
|
||||
"overall_chain.run(GMAIL_SEARCH_INSTRUCTIONS)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "09ff954e-45f2-4595-92ea-91627abde4a0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## <a id=\"oauth\">Example Using OAuth Access Token</a>\n",
|
||||
"The below snippet shows how to initialize the wrapper with a procured OAuth access token. Note the argument being passed in as opposed to setting an environment variable. Review the [authentication docs](https://nla.zapier.com/docs/authentication/#oauth-credentials) for full user-facing oauth developer support.\n",
|
||||
"\n",
|
||||
"The developer is tasked with handling the OAuth handshaking to procure and refresh the access token."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7c6835c8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"zapier = ZapierNLAWrapper(zapier_nla_oauth_access_token=\"<fill in access token here>\")\n",
|
||||
"toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\n",
|
||||
" \"Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack.\"\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user