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
@@ -0,0 +1,165 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eb1c0ea9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Aleph Alpha\n",
|
||||
"\n",
|
||||
"There are two possible ways to use Aleph Alpha's semantic embeddings. If you have texts with a dissimilar structure (e.g. a Document and a Query) you would want to use asymmetric embeddings. Conversely, for texts with comparable structures, symmetric embeddings are the suggested approach."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9ecc84f9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Asymmetric"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "8a920a89",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import AlephAlphaAsymmetricSemanticEmbedding"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "f2d04da3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"document = \"This is a content of the document\"\n",
|
||||
"query = \"What is the contnt of the document?\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e6ecde96",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = AlephAlphaAsymmetricSemanticEmbedding()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "90e68411",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([document])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "55903233",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b8c00aab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Symmetric"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "eabb763a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import AlephAlphaSymmetricSemanticEmbedding"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "0ad799f7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test text\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "af86dc10",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = AlephAlphaSymmetricSemanticEmbedding()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d292536f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c704a7cf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "33492471",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c3852491",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# AzureOpenAI\n",
|
||||
"\n",
|
||||
"Let's load the OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1b40f827",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# set the environment variables needed for openai package to know to reach out to azure\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
|
||||
"os.environ[\"OPENAI_API_BASE\"] = \"https://<your-endpoint.openai.azure.com/\"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"your AzureOpenAI key\"\n",
|
||||
"os.environ[\"OPENAI_API_VERSION\"] = \"2023-05-15\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bb36d16c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import OpenAIEmbeddings\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings(deployment=\"your-embeddings-deployment-name\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "228abcbb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "60dd7fad",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "83bc1a72",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,77 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Bedrock Embeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2dbe40fa-7c0b-4bcb-a712-230bf613a42f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install boto3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "282239c8-e03a-4abc-86c1-ca6120231a20",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import BedrockEmbeddings\n",
|
||||
"\n",
|
||||
"embeddings = BedrockEmbeddings(\n",
|
||||
" credentials_profile_name=\"bedrock-admin\", endpoint_url=\"custom_endpoint_url\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "19a46868-4bed-40cd-89ca-9813fbfda9cb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings.embed_query(\"This is a content of the document\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cf0349c4-6408-4342-8691-69276a388784",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings.embed_documents([\"This is a content of the document\"])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,210 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "9597802c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Clarifai\n",
|
||||
"\n",
|
||||
">[Clarifai](https://www.clarifai.com/) is an AI Platform that provides the full AI lifecycle ranging from data exploration, data labeling, model training, evaluation, and inference.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with `Clarifai` [models](https://clarifai.com/explore/models). Text embedding models in particular can be found [here](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22model_type_id%22%2C%22value%22%3A%5B%22text-embedder%22%5D%7D%5D).\n",
|
||||
"\n",
|
||||
"To use Clarifai, you must have an account and a Personal Access Token (PAT) key. \n",
|
||||
"[Check here](https://clarifai.com/settings/security) to get or create a PAT."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "2a773d8d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "91ea14ce-831d-409a-a88f-30353acdabd1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Install required dependencies\n",
|
||||
"!pip install clarifai"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "426f1156",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Imports\n",
|
||||
"Here we will be setting the personal access token. You can find your PAT under [settings/security](https://clarifai.com/settings/security) in your Clarifai account."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "3f5dc9d7-65e3-4b5b-9086-3327d016cfe0",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Please login and get your API key from https://clarifai.com/settings/security\n",
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
"CLARIFAI_PAT = getpass()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "6fb585dd",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Import the required modules\n",
|
||||
"from langchain.embeddings import ClarifaiEmbeddings\n",
|
||||
"from langchain import PromptTemplate, LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "16521ed2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Input\n",
|
||||
"Create a prompt template to be used with the LLM Chain:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "035dea0f",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Question: {question}\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "c8905eac",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup\n",
|
||||
"Set the user id and app id to the application in which the model resides. You can find a list of public models on https://clarifai.com/explore/models\n",
|
||||
"\n",
|
||||
"You will have to also initialize the model id and if needed, the model version id. Some models have many versions, you can choose the one appropriate for your task."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "1fe9bf15",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"USER_ID = \"openai\"\n",
|
||||
"APP_ID = \"embed\"\n",
|
||||
"MODEL_ID = \"text-embedding-ada\"\n",
|
||||
"\n",
|
||||
"# You can provide a specific model version as the model_version_id arg.\n",
|
||||
"# MODEL_VERSION_ID = \"MODEL_VERSION_ID\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "3f3458d9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Initialize a Clarifai embedding model\n",
|
||||
"embeddings = ClarifaiEmbeddings(\n",
|
||||
" pat=CLARIFAI_PAT, user_id=USER_ID, app_id=APP_ID, model_id=MODEL_ID\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "a641dbd9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "32b4d5f4-2b8e-4681-856f-19a3dd141ae4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "47076457-1880-48ac-970f-872ead6f0d94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,98 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "42f76e43",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Cohere\n",
|
||||
"\n",
|
||||
"Let's load the Cohere Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "6b82f59f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import CohereEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "26895c60",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = CohereEmbeddings(cohere_api_key=cohere_api_key)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "eea52814",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "fbe167bf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "38ad3b20",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# DashScope\n",
|
||||
"\n",
|
||||
"Let's load the DashScope Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import DashScopeEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = DashScopeEmbeddings(\n",
|
||||
" model=\"text-embedding-v1\", dashscope_api_key=\"your-dashscope-api-key\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)\n",
|
||||
"print(query_result)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])\n",
|
||||
"print(doc_results)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "chatgpt",
|
||||
"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"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,134 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# DeepInfra\n",
|
||||
"\n",
|
||||
"[DeepInfra](https://deepinfra.com/?utm_source=langchain) is a serverless inference as a service that provides access to a [variety of LLMs](https://deepinfra.com/models?utm_source=langchain) and [embeddings models](https://deepinfra.com/models?type=embeddings&utm_source=langchain). This notebook goes over how to use LangChain with DeepInfra for text embeddings."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# sign up for an account: https://deepinfra.com/login?utm_source=langchain\n",
|
||||
"\n",
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
"DEEPINFRA_API_TOKEN = getpass()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"DEEPINFRA_API_TOKEN\"] = DEEPINFRA_API_TOKEN"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import DeepInfraEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = DeepInfraEmbeddings(\n",
|
||||
" model_id=\"sentence-transformers/clip-ViT-B-32\",\n",
|
||||
" query_instruction=\"\",\n",
|
||||
" embed_instruction=\"\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs = [\"Dog is not a cat\", \"Beta is the second letter of Greek alphabet\"]\n",
|
||||
"document_result = embeddings.embed_documents(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"What is the first letter of Greek alphabet\"\n",
|
||||
"query_result = embeddings.embed_query(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Cosine similarity between \"Dog is not a cat\" and query: 0.7489097144129355\n",
|
||||
"Cosine similarity between \"Beta is the second letter of Greek alphabet\" and query: 0.9519380640702013\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"query_numpy = np.array(query_result)\n",
|
||||
"for doc_res, doc in zip(document_result, docs):\n",
|
||||
" document_numpy = np.array(doc_res)\n",
|
||||
" similarity = np.dot(query_numpy, document_numpy) / (\n",
|
||||
" np.linalg.norm(query_numpy) * np.linalg.norm(document_numpy)\n",
|
||||
" )\n",
|
||||
" print(f'Cosine similarity between \"{doc}\" and query: {similarity}')"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.10"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,268 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "1eZl1oaVUNeC"
|
||||
},
|
||||
"source": [
|
||||
"# Elasticsearch\n",
|
||||
"Walkthrough of how to generate embeddings using a hosted embedding model in Elasticsearch\n",
|
||||
"\n",
|
||||
"The easiest way to instantiate the `ElasticsearchEmbeddings` class it either\n",
|
||||
"- using the `from_credentials` constructor if you are using Elastic Cloud\n",
|
||||
"- or using the `from_es_connection` constructor with any Elasticsearch cluster"
|
||||
],
|
||||
"id": "72644940"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "6dJxqebov4eU"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip -q install elasticsearch langchain"
|
||||
],
|
||||
"id": "298759cb"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "RV7C3DUmv4aq"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import elasticsearch\n",
|
||||
"from langchain.embeddings.elasticsearch import ElasticsearchEmbeddings"
|
||||
],
|
||||
"id": "76489aff"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "MrT3jplJvp09"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Define the model ID\n",
|
||||
"model_id = \"your_model_id\""
|
||||
],
|
||||
"id": "57bfdc82"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "j5F-nwLVS_Zu"
|
||||
},
|
||||
"source": [
|
||||
"## Testing with `from_credentials`\n",
|
||||
"This required an Elastic Cloud `cloud_id`"
|
||||
],
|
||||
"id": "0ffad1ec"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "svtdnC-dvpxR"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Instantiate ElasticsearchEmbeddings using credentials\n",
|
||||
"embeddings = ElasticsearchEmbeddings.from_credentials(\n",
|
||||
" model_id,\n",
|
||||
" es_cloud_id=\"your_cloud_id\",\n",
|
||||
" es_user=\"your_user\",\n",
|
||||
" es_password=\"your_password\",\n",
|
||||
")"
|
||||
],
|
||||
"id": "fc2e9dcb"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "7DXZAK7Kvpth"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create embeddings for multiple documents\n",
|
||||
"documents = [\n",
|
||||
" \"This is an example document.\",\n",
|
||||
" \"Another example document to generate embeddings for.\",\n",
|
||||
"]\n",
|
||||
"document_embeddings = embeddings.embed_documents(documents)"
|
||||
],
|
||||
"id": "8ee7f1fc"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "K8ra75W_vpqy"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print document embeddings\n",
|
||||
"for i, embedding in enumerate(document_embeddings):\n",
|
||||
" print(f\"Embedding for document {i+1}: {embedding}\")"
|
||||
],
|
||||
"id": "0b9d8471"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "V4Q5kQo9vpna"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create an embedding for a single query\n",
|
||||
"query = \"This is a single query.\"\n",
|
||||
"query_embedding = embeddings.embed_query(query)"
|
||||
],
|
||||
"id": "3989ab23"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "O0oQDzGKvpkz"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print query embedding\n",
|
||||
"print(f\"Embedding for query: {query_embedding}\")"
|
||||
],
|
||||
"id": "0da6d2bf"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "rHN03yV6TJ5q"
|
||||
},
|
||||
"source": [
|
||||
"## Testing with Existing Elasticsearch client connection\n",
|
||||
"This can be used with any Elasticsearch deployment"
|
||||
],
|
||||
"id": "32700096"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "GMQcJDwBTJFm"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create Elasticsearch connection\n",
|
||||
"es_connection = Elasticsearch(\n",
|
||||
" hosts=[\"https://es_cluster_url:port\"], basic_auth=(\"user\", \"password\")\n",
|
||||
")"
|
||||
],
|
||||
"id": "0bc60465"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "WTYIU4u3TJO1"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Instantiate ElasticsearchEmbeddings using es_connection\n",
|
||||
"embeddings = ElasticsearchEmbeddings.from_es_connection(\n",
|
||||
" model_id,\n",
|
||||
" es_connection,\n",
|
||||
")"
|
||||
],
|
||||
"id": "8085843b"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "4gdAUHwoTJO3"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create embeddings for multiple documents\n",
|
||||
"documents = [\n",
|
||||
" \"This is an example document.\",\n",
|
||||
" \"Another example document to generate embeddings for.\",\n",
|
||||
"]\n",
|
||||
"document_embeddings = embeddings.embed_documents(documents)"
|
||||
],
|
||||
"id": "59a90bf3"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "RC_-tov6TJO3"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print document embeddings\n",
|
||||
"for i, embedding in enumerate(document_embeddings):\n",
|
||||
" print(f\"Embedding for document {i+1}: {embedding}\")"
|
||||
],
|
||||
"id": "54b18673"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "6GEnHBqETJO3"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create an embedding for a single query\n",
|
||||
"query = \"This is a single query.\"\n",
|
||||
"query_embedding = embeddings.embed_query(query)"
|
||||
],
|
||||
"id": "a4812d5e"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "-kyUQAXDTJO4"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print query embedding\n",
|
||||
"print(f\"Embedding for query: {query_embedding}\")"
|
||||
],
|
||||
"id": "c6c69916"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": []
|
||||
},
|
||||
"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 +1,147 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Embaas\n",
|
||||
"\n",
|
||||
"[embaas](https://embaas.io) is a fully managed NLP API service that offers features like embedding generation, document text extraction, document to embeddings and more. You can choose a [variety of pre-trained models](https://embaas.io/docs/models/embeddings).\n",
|
||||
"\n",
|
||||
"In this tutorial, we will show you how to use the embaas Embeddings API to generate embeddings for a given text.\n",
|
||||
"\n",
|
||||
"### Prerequisites\n",
|
||||
"Create your free embaas account at [https://embaas.io/register](https://embaas.io/register) and generate an [API key](https://embaas.io/dashboard/api-keys)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set API key\n",
|
||||
"embaas_api_key = \"YOUR_API_KEY\"\n",
|
||||
"# or set environment variable\n",
|
||||
"os.environ[\"EMBAAS_API_KEY\"] = \"YOUR_API_KEY\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import EmbaasEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = EmbaasEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-10T11:17:55.940265Z",
|
||||
"start_time": "2023-06-10T11:17:55.938517Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create embeddings for a single document\n",
|
||||
"doc_text = \"This is a test document.\"\n",
|
||||
"doc_text_embedding = embeddings.embed_query(doc_text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print created embedding\n",
|
||||
"print(doc_text_embedding)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-10T11:19:25.237161Z",
|
||||
"start_time": "2023-06-10T11:19:25.235320Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Create embeddings for multiple documents\n",
|
||||
"doc_texts = [\"This is a test document.\", \"This is another test document.\"]\n",
|
||||
"doc_texts_embeddings = embeddings.embed_documents(doc_texts)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print created embeddings\n",
|
||||
"for i, doc_text_embedding in enumerate(doc_texts_embeddings):\n",
|
||||
" print(f\"Embedding for document {i + 1}: {doc_text_embedding}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-10T11:22:26.139769Z",
|
||||
"start_time": "2023-06-10T11:22:26.138357Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Using a different model and/or custom instruction\n",
|
||||
"embeddings = EmbaasEmbeddings(\n",
|
||||
" model=\"instructor-large\",\n",
|
||||
" instruction=\"Represent the Wikipedia document for retrieval\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"For more detailed information about the embaas Embeddings API, please refer to [the official embaas API documentation](https://embaas.io/api-reference)."
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": 1
|
||||
}
|
||||
@@ -0,0 +1,80 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f9c02c78",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Fake Embeddings\n",
|
||||
"\n",
|
||||
"LangChain also provides a fake embedding class. You can use this to test your pipelines."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "2ffc2e4b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import FakeEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "80777571",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = FakeEmbeddings(size=1352)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "3ec9d8f0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "3b9ae9e1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Cloud Platform Vertex AI PaLM \n",
|
||||
"\n",
|
||||
"Note: This is seperate from the Google PaLM integration. Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
|
||||
"\n",
|
||||
"PaLM API on Vertex AI is a Preview offering, subject to the Pre-GA Offerings Terms of the [GCP Service Specific Terms](https://cloud.google.com/terms/service-terms). \n",
|
||||
"\n",
|
||||
"Pre-GA products and features may have limited support, and changes to pre-GA products and features may not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages). Further, by using PaLM API on Vertex AI, you agree to the Generative AI Preview [terms and conditions](https://cloud.google.com/trustedtester/aitos) (Preview Terms).\n",
|
||||
"\n",
|
||||
"For PaLM API on Vertex AI, you can process personal data as outlined in the Cloud Data Processing Addendum, subject to applicable restrictions and obligations in the Agreement (as defined in the Preview Terms).\n",
|
||||
"\n",
|
||||
"To use Vertex AI PaLM you must have the `google-cloud-aiplatform` Python package installed and either:\n",
|
||||
"- Have credentials configured for your environment (gcloud, workload identity, etc...)\n",
|
||||
"- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n",
|
||||
"\n",
|
||||
"This codebase uses the `google.auth` library which first looks for the application credentials variable mentioned above, and then looks for system-level auth.\n",
|
||||
"\n",
|
||||
"For more information, see: \n",
|
||||
"- https://cloud.google.com/docs/authentication/application-default-credentials#GAC\n",
|
||||
"- https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install google-cloud-aiplatform"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import VertexAIEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = VertexAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "cc99336516f23363341912c6723b01ace86f02e26b4290be1efc0677e2e2ec24"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,117 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d63d56c2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# GPT4All\n",
|
||||
"\n",
|
||||
"This notebook explains how to use [GPT4All embeddings](https://docs.gpt4all.io/gpt4all_python_embedding.html#gpt4all.gpt4all.Embed4All) with LangChain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cdd68231",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! pip install gpt4all"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "08f267d6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import GPT4AllEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "0120e939",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|████████████████████████| 45.5M/45.5M [00:02<00:00, 18.5MiB/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Model downloaded at: /Users/rlm/.cache/gpt4all/ggml-all-MiniLM-L6-v2-f16.bin\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"objc[45711]: Class GGMLMetalClass is implemented in both /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libreplit-mainline-metal.dylib (0x29fe18208) and /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libllamamodel-mainline-metal.dylib (0x2a0244208). One of the two will be used. Which one is undefined.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"gpt4all_embd = GPT4AllEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "53134a38",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "a55adf9f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = gpt4all_embd.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "6ebd42d7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = gpt4all_embd.embed_documents([text])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,97 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ed47bb62",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Hugging Face Hub\n",
|
||||
"Let's load the Hugging Face Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "861521a9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import HuggingFaceEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "ff9be586",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = HuggingFaceEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "d0a98ae9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "5d6c682b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "bb5e74c0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
---
|
||||
sidebar_position: 0
|
||||
---
|
||||
|
||||
# Text embedding models
|
||||
|
||||
import DocCardList from "@theme/DocCardList";
|
||||
|
||||
<DocCardList />
|
||||
@@ -0,0 +1,98 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "59428e05",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# InstructEmbeddings\n",
|
||||
"Let's load the HuggingFace instruct Embeddings class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "92c5b61e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import HuggingFaceInstructEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "062547b9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"load INSTRUCTOR_Transformer\n",
|
||||
"max_seq_length 512\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"embeddings = HuggingFaceInstructEmbeddings(\n",
|
||||
" query_instruction=\"Represent the query for retrieval: \"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "e1dcc4bd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "90f0db94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,103 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1c0cf975",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Jina\n",
|
||||
"\n",
|
||||
"Let's load the Jina Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d94c62b4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import JinaEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "523a09e3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = JinaEmbeddings(\n",
|
||||
" jina_auth_token=jina_auth_token, model_name=\"ViT-B-32::openai\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b212bd5a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "57db66bd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b790fd09",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6f3607a0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the above example, `ViT-B-32::openai`, OpenAI's pretrained `ViT-B-32` model is used. For a full list of models, see [here](https://cloud.jina.ai/user/inference/model/63dca9df5a0da83009d519cd)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cd5f148e",
|
||||
"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 +1,88 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Llama-cpp\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Llama-cpp embeddings within LangChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install llama-cpp-python"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import LlamaCppEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llama = LlamaCppEmbeddings(model_path=\"/path/to/model/ggml-model-q4_0.bin\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = llama.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = llama.embed_documents([text])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": 2
|
||||
}
|
||||
@@ -0,0 +1,147 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MiniMax\n",
|
||||
"\n",
|
||||
"[MiniMax](https://api.minimax.chat/document/guides/embeddings?id=6464722084cdc277dfaa966a) offers an embeddings service.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with MiniMax Inference for text embedding."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:15.397075Z",
|
||||
"start_time": "2023-05-24T15:13:15.387540Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"MINIMAX_GROUP_ID\"] = \"MINIMAX_GROUP_ID\"\n",
|
||||
"os.environ[\"MINIMAX_API_KEY\"] = \"MINIMAX_API_KEY\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:17.176956Z",
|
||||
"start_time": "2023-05-24T15:13:15.399076Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import MiniMaxEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:17.193751Z",
|
||||
"start_time": "2023-05-24T15:13:17.182053Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = MiniMaxEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:17.844903Z",
|
||||
"start_time": "2023-05-24T15:13:17.198751Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_text = \"This is a test query.\"\n",
|
||||
"query_result = embeddings.embed_query(query_text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:18.605339Z",
|
||||
"start_time": "2023-05-24T15:13:17.845906Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"document_text = \"This is a test document.\"\n",
|
||||
"document_result = embeddings.embed_documents([document_text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-05-24T15:13:18.620432Z",
|
||||
"start_time": "2023-05-24T15:13:18.608335Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Cosine similarity between document and query: 0.1573236279277012\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"query_numpy = np.array(query_result)\n",
|
||||
"document_numpy = np.array(document_result[0])\n",
|
||||
"similarity = np.dot(query_numpy, document_numpy) / (\n",
|
||||
" np.linalg.norm(query_numpy) * np.linalg.norm(document_numpy)\n",
|
||||
")\n",
|
||||
"print(f\"Cosine similarity between document and query: {similarity}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": "3.11.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ModelScope\n",
|
||||
"\n",
|
||||
"Let's load the ModelScope Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import ModelScopeEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model_id = \"damo/nlp_corom_sentence-embedding_english-base\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = ModelScopeEmbeddings(model_id=model_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "chatgpt",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"name": "python",
|
||||
"version": "3.9.15"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,111 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MosaicML embeddings\n",
|
||||
"\n",
|
||||
"[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with MosaicML Inference for text embedding."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# sign up for an account: https://forms.mosaicml.com/demo?utm_source=langchain\n",
|
||||
"\n",
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
"MOSAICML_API_TOKEN = getpass()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"MOSAICML_API_TOKEN\"] = MOSAICML_API_TOKEN"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import MosaicMLInstructorEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = MosaicMLInstructorEmbeddings(\n",
|
||||
" query_instruction=\"Represent the query for retrieval: \"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_text = \"This is a test query.\"\n",
|
||||
"query_result = embeddings.embed_query(query_text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"document_text = \"This is a test document.\"\n",
|
||||
"document_result = embeddings.embed_documents([document_text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"query_numpy = np.array(query_result)\n",
|
||||
"document_numpy = np.array(document_result[0])\n",
|
||||
"similarity = np.dot(query_numpy, document_numpy) / (\n",
|
||||
" np.linalg.norm(query_numpy) * np.linalg.norm(document_numpy)\n",
|
||||
")\n",
|
||||
"print(f\"Cosine similarity between document and query: {similarity}\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6802946f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# NLP Cloud\n",
|
||||
"\n",
|
||||
"NLP Cloud is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
|
||||
"\n",
|
||||
"The [embeddings](https://docs.nlpcloud.com/#embeddings) endpoint offers several models:\n",
|
||||
"\n",
|
||||
"* `paraphrase-multilingual-mpnet-base-v2`: Paraphrase Multilingual MPNet Base V2 is a very fast model based on Sentence Transformers that is perfectly suited for embeddings extraction in more than 50 languages (see the full list here).\n",
|
||||
"\n",
|
||||
"* `gpt-j`: GPT-J returns advanced embeddings. It might return better results than Sentence Transformers based models (see above) but it is also much slower.\n",
|
||||
"\n",
|
||||
"* `dolphin`: Dolphin returns advanced embeddings. It might return better results than Sentence Transformers based models (see above) but it is also much slower. It natively understands the following languages: Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, French, German, Hungarian, Italian, Japanese, Polish, Portuguese, Romanian, Russian, Serbian, Slovenian, Spanish, Swedish, and Ukrainian."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "490d7923",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! pip install nlpcloud"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "6a39ed4b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import NLPCloudEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "c105d8cd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"NLPCLOUD_API_KEY\"] = \"xxx\"\n",
|
||||
"nlpcloud_embd = NLPCloudEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "cca84023",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "26868d0f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = nlpcloud_embd.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "0c171c2f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = nlpcloud_embd.embed_documents([text])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,159 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "278b6c63",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenAI\n",
|
||||
"\n",
|
||||
"Let's load the OpenAI Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "0be1af71",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import OpenAIEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "2c66e5da",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "01370375",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "bfb6142c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "0356c3b7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bb61bbeb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's load the OpenAI Embedding class with first generation models (e.g. text-search-ada-doc-001/text-search-ada-query-001). Note: These are not recommended models - see [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c0b072cc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a56b70f5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "14aefb64",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3c39ed33",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e3221db6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# if you are behind an explicit proxy, you can use the OPENAI_PROXY environment variable to pass through\n",
|
||||
"os.environ[\"OPENAI_PROXY\"] = \"http://proxy.yourcompany.com:8080\""
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.11.1 64-bit",
|
||||
"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": "3.11.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,136 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1f83f273",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SageMaker Endpoint Embeddings\n",
|
||||
"\n",
|
||||
"Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
|
||||
"\n",
|
||||
"For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). **Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
|
||||
"\n",
|
||||
"Change from\n",
|
||||
"\n",
|
||||
"`return {\"vectors\": sentence_embeddings[0].tolist()}`\n",
|
||||
"\n",
|
||||
"to:\n",
|
||||
"\n",
|
||||
"`return {\"vectors\": sentence_embeddings.tolist()}`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "88d366bd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip3 install langchain boto3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "1e9b926a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from typing import Dict, List\n",
|
||||
"from langchain.embeddings import SagemakerEndpointEmbeddings\n",
|
||||
"from langchain.llms.sagemaker_endpoint import ContentHandlerBase\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"class ContentHandler(ContentHandlerBase):\n",
|
||||
" content_type = \"application/json\"\n",
|
||||
" accepts = \"application/json\"\n",
|
||||
"\n",
|
||||
" def transform_input(self, inputs: list[str], model_kwargs: Dict) -> bytes:\n",
|
||||
" input_str = json.dumps({\"inputs\": inputs, **model_kwargs})\n",
|
||||
" return input_str.encode(\"utf-8\")\n",
|
||||
"\n",
|
||||
" def transform_output(self, output: bytes) -> List[List[float]]:\n",
|
||||
" response_json = json.loads(output.read().decode(\"utf-8\"))\n",
|
||||
" return response_json[\"vectors\"]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"content_handler = ContentHandler()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"embeddings = SagemakerEndpointEmbeddings(\n",
|
||||
" # endpoint_name=\"endpoint-name\",\n",
|
||||
" # credentials_profile_name=\"credentials-profile-name\",\n",
|
||||
" endpoint_name=\"huggingface-pytorch-inference-2023-03-21-16-14-03-834\",\n",
|
||||
" region_name=\"us-east-1\",\n",
|
||||
" content_handler=content_handler,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fe9797b8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "76f1b752",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fff99b21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,195 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eec4efda",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Self Hosted Embeddings\n",
|
||||
"Let's load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d338722a",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import (\n",
|
||||
" SelfHostedEmbeddings,\n",
|
||||
" SelfHostedHuggingFaceEmbeddings,\n",
|
||||
" SelfHostedHuggingFaceInstructEmbeddings,\n",
|
||||
")\n",
|
||||
"import runhouse as rh"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "146559e8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# For an on-demand A100 with GCP, Azure, or Lambda\n",
|
||||
"gpu = rh.cluster(name=\"rh-a10x\", instance_type=\"A100:1\", use_spot=False)\n",
|
||||
"\n",
|
||||
"# For an on-demand A10G with AWS (no single A100s on AWS)\n",
|
||||
"# gpu = rh.cluster(name='rh-a10x', instance_type='g5.2xlarge', provider='aws')\n",
|
||||
"\n",
|
||||
"# For an existing cluster\n",
|
||||
"# gpu = rh.cluster(ips=['<ip of the cluster>'],\n",
|
||||
"# ssh_creds={'ssh_user': '...', 'ssh_private_key':'<path_to_key>'},\n",
|
||||
"# name='my-cluster')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1230f7df",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = SelfHostedHuggingFaceEmbeddings(hardware=gpu)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "2684e928",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1dc5e606",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cef9cc54",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And similarly for SelfHostedHuggingFaceInstructEmbeddings:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "81a17ca3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = SelfHostedHuggingFaceInstructEmbeddings(hardware=gpu)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5a33d1c8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now let's load an embedding model with a custom load function:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "c4af5679",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_pipeline():\n",
|
||||
" from transformers import (\n",
|
||||
" AutoModelForCausalLM,\n",
|
||||
" AutoTokenizer,\n",
|
||||
" pipeline,\n",
|
||||
" ) # Must be inside the function in notebooks\n",
|
||||
"\n",
|
||||
" model_id = \"facebook/bart-base\"\n",
|
||||
" tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
|
||||
" model = AutoModelForCausalLM.from_pretrained(model_id)\n",
|
||||
" return pipeline(\"feature-extraction\", model=model, tokenizer=tokenizer)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def inference_fn(pipeline, prompt):\n",
|
||||
" # Return last hidden state of the model\n",
|
||||
" if isinstance(prompt, list):\n",
|
||||
" return [emb[0][-1] for emb in pipeline(prompt)]\n",
|
||||
" return pipeline(prompt)[0][-1]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8654334b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = SelfHostedEmbeddings(\n",
|
||||
" model_load_fn=get_pipeline,\n",
|
||||
" hardware=gpu,\n",
|
||||
" model_reqs=[\"./\", \"torch\", \"transformers\"],\n",
|
||||
" inference_fn=inference_fn,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fc1bfd0f",
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,122 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ed47bb62",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Sentence Transformers Embeddings\n",
|
||||
"\n",
|
||||
"[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
|
||||
"\n",
|
||||
"SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "06c9f47d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
|
||||
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!pip install sentence_transformers > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "861521a9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import HuggingFaceEmbeddings, SentenceTransformerEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ff9be586",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
|
||||
"# Equivalent to SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d0a98ae9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "5d6c682b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "bb5e74c0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text, \"This is not a test document.\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,116 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Spacy Embedding\n",
|
||||
"\n",
|
||||
"### Loading the Spacy embedding class to generate and query embeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Import the necessary classes"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.spacy_embeddings import SpacyEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Initialize SpacyEmbeddings.This will load the Spacy model into memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embedder = SpacyEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"texts = [\n",
|
||||
" \"The quick brown fox jumps over the lazy dog.\",\n",
|
||||
" \"Pack my box with five dozen liquor jugs.\",\n",
|
||||
" \"How vexingly quick daft zebras jump!\",\n",
|
||||
" \"Bright vixens jump; dozy fowl quack.\",\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = embedder.embed_documents(texts)\n",
|
||||
"for i, embedding in enumerate(embeddings):\n",
|
||||
" print(f\"Embedding for document {i+1}: {embedding}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"Quick foxes and lazy dogs.\"\n",
|
||||
"query_embedding = embedder.embed_query(query)\n",
|
||||
"print(f\"Embedding for query: {query_embedding}\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,118 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fff4734f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# TensorflowHub\n",
|
||||
"Let's load the TensorflowHub Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f822104b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import TensorflowHubEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "bac84e46",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2023-01-30 23:53:01.652176: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
|
||||
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
|
||||
"2023-01-30 23:53:34.362802: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
|
||||
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"embeddings = TensorflowHubEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "4790d770",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "f556dcdb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "76f1b752",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fff99b21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"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": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user