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 +1,163 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "90cd3ded",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Cassandra Chat Message History\n",
|
||||
"\n",
|
||||
">[Apache Cassandra®](https://cassandra.apache.org) is a NoSQL, row-oriented, highly scalable and highly available database, well suited for storing large amounts of data.\n",
|
||||
"\n",
|
||||
"Cassandra is a good choice for storing chat message history because it is easy to scale and can handle a large number of writes.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Cassandra to store chat message history.\n",
|
||||
"\n",
|
||||
"To run this notebook you need either a running Cassandra cluster or a DataStax Astra DB instance running in the cloud (you can get one for free at [datastax.com](https://astra.datastax.com)). Check [cassio.org](https://cassio.org/start_here/) for more information."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d7092199",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install \"cassio>=0.0.7\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e3d97b65",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Please provide database connection parameters and secrets:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "163d97f0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"database_mode = (input(\"\\n(C)assandra or (A)stra DB? \")).upper()\n",
|
||||
"\n",
|
||||
"keyspace_name = input(\"\\nKeyspace name? \")\n",
|
||||
"\n",
|
||||
"if database_mode == \"A\":\n",
|
||||
" ASTRA_DB_APPLICATION_TOKEN = getpass.getpass('\\nAstra DB Token (\"AstraCS:...\") ')\n",
|
||||
" #\n",
|
||||
" ASTRA_DB_SECURE_BUNDLE_PATH = input(\"Full path to your Secure Connect Bundle? \")\n",
|
||||
"elif database_mode == \"C\":\n",
|
||||
" CASSANDRA_CONTACT_POINTS = input(\n",
|
||||
" \"Contact points? (comma-separated, empty for localhost) \"\n",
|
||||
" ).strip()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "55860b2d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### depending on whether local or cloud-based Astra DB, create the corresponding database connection \"Session\" object"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8dff2798",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from cassandra.cluster import Cluster\n",
|
||||
"from cassandra.auth import PlainTextAuthProvider\n",
|
||||
"\n",
|
||||
"if database_mode == \"C\":\n",
|
||||
" if CASSANDRA_CONTACT_POINTS:\n",
|
||||
" cluster = Cluster(\n",
|
||||
" [cp.strip() for cp in CASSANDRA_CONTACT_POINTS.split(\",\") if cp.strip()]\n",
|
||||
" )\n",
|
||||
" else:\n",
|
||||
" cluster = Cluster()\n",
|
||||
" session = cluster.connect()\n",
|
||||
"elif database_mode == \"A\":\n",
|
||||
" ASTRA_DB_CLIENT_ID = \"token\"\n",
|
||||
" cluster = Cluster(\n",
|
||||
" cloud={\n",
|
||||
" \"secure_connect_bundle\": ASTRA_DB_SECURE_BUNDLE_PATH,\n",
|
||||
" },\n",
|
||||
" auth_provider=PlainTextAuthProvider(\n",
|
||||
" ASTRA_DB_CLIENT_ID,\n",
|
||||
" ASTRA_DB_APPLICATION_TOKEN,\n",
|
||||
" ),\n",
|
||||
" )\n",
|
||||
" session = cluster.connect()\n",
|
||||
"else:\n",
|
||||
" raise NotImplementedError"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36c163e8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Creation and usage of the Chat Message History"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import CassandraChatMessageHistory\n",
|
||||
"\n",
|
||||
"message_history = CassandraChatMessageHistory(\n",
|
||||
" session_id=\"test-session\",\n",
|
||||
" session=session,\n",
|
||||
" keyspace=keyspace_name,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"message_history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"message_history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"message_history.messages"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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 +1,374 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Dynamodb Chat Message History\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Dynamodb to store chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3f608be0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed boto3."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "030d784f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, create the DynamoDB Table where we will be storing messages:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "93ce1811",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import boto3\n",
|
||||
"\n",
|
||||
"# Get the service resource.\n",
|
||||
"dynamodb = boto3.resource(\"dynamodb\")\n",
|
||||
"\n",
|
||||
"# Create the DynamoDB table.\n",
|
||||
"table = dynamodb.create_table(\n",
|
||||
" TableName=\"SessionTable\",\n",
|
||||
" KeySchema=[{\"AttributeName\": \"SessionId\", \"KeyType\": \"HASH\"}],\n",
|
||||
" AttributeDefinitions=[{\"AttributeName\": \"SessionId\", \"AttributeType\": \"S\"}],\n",
|
||||
" BillingMode=\"PAY_PER_REQUEST\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Wait until the table exists.\n",
|
||||
"table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"SessionTable\")\n",
|
||||
"\n",
|
||||
"# Print out some data about the table.\n",
|
||||
"print(table.item_count)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1a9b310b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## DynamoDBChatMessageHistory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"0\")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
|
||||
" AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "955f1b15",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## DynamoDBChatMessageHistory with Custom Endpoint URL\n",
|
||||
"\n",
|
||||
"Sometimes it is useful to specify the URL to the AWS endpoint to connect to. For instance, when you are running locally against [Localstack](https://localstack.cloud/). For those cases you can specify the URL via the `endpoint_url` parameter in the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "225713c8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = DynamoDBChatMessageHistory(\n",
|
||||
" table_name=\"SessionTable\",\n",
|
||||
" session_id=\"0\",\n",
|
||||
" endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "3b33c988",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Agent with DynamoDB Memory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f92d9499",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.utilities import PythonREPL\n",
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
"message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
|
||||
"memory = ConversationBufferMemory(\n",
|
||||
" memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "1167eeba",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"python_repl = PythonREPL()\n",
|
||||
"\n",
|
||||
"# You can create the tool to pass to an agent\n",
|
||||
"tools = [\n",
|
||||
" 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",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "fce085c5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
" memory=memory,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "952a3103",
|
||||
"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",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Hello! How can I assist you today?\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hello! How can I assist you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Hello!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "54c4aaf4",
|
||||
"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",
|
||||
" \"action\": \"python_repl\",\n",
|
||||
" \"action_input\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nurl = 'https://en.wikipedia.org/wiki/Twitter'\\nresponse = requests.get(url)\\nsoup = BeautifulSoup(response.content, 'html.parser')\\nowner = soup.find('th', text='Owner').find_next_sibling('td').text.strip()\\nprint(owner)\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mX Corp. (2023–present)Twitter, Inc. (2006–2023)\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"X Corp. (2023–present)Twitter, Inc. (2006–2023)\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'X Corp. (2023–present)Twitter, Inc. (2006–2023)'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Who owns Twitter?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "f9013118",
|
||||
"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",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Hello Bob! How can I assist you today?\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hello Bob! How can I assist you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"My name is Bob.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "405e5315",
|
||||
"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",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Your name is Bob.\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Your name is Bob.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Who am I?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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 +1,199 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "eg0Hwptz9g5q"
|
||||
},
|
||||
"source": [
|
||||
"# Entity Memory with SQLite storage\n",
|
||||
"\n",
|
||||
"In this walkthrough we'll create a simple conversation chain which uses ConversationEntityMemory backed by a SqliteEntityStore."
|
||||
],
|
||||
"id": "d464a12a"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"id": "2wUMSUoF8ffn"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import ConversationChain\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.memory import ConversationEntityMemory\n",
|
||||
"from langchain.memory.entity import SQLiteEntityStore\n",
|
||||
"from langchain.memory.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE"
|
||||
],
|
||||
"id": "db59b901"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"id": "8TpJZti99gxV"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"entity_store = SQLiteEntityStore()\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"memory = ConversationEntityMemory(llm=llm, entity_store=entity_store)\n",
|
||||
"conversation = ConversationChain(\n",
|
||||
" llm=llm,\n",
|
||||
" prompt=ENTITY_MEMORY_CONVERSATION_TEMPLATE,\n",
|
||||
" memory=memory,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
],
|
||||
"id": "ca6dee29"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "HEAHG1L79ca1"
|
||||
},
|
||||
"source": [
|
||||
"Notice the usage of `EntitySqliteStore` as parameter to `entity_store` on the `memory` property."
|
||||
],
|
||||
"id": "f9b4c3a0"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 437
|
||||
},
|
||||
"id": "BzXphJWf_TAZ",
|
||||
"outputId": "de7fc966-e0fd-4daf-a9bd-4743455ea774"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are an assistant to a human, powered by a large language model trained by OpenAI.\n",
|
||||
"\n",
|
||||
"You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
|
||||
"\n",
|
||||
"You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
|
||||
"\n",
|
||||
"Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
|
||||
"\n",
|
||||
"Context:\n",
|
||||
"{'Deven': 'Deven is working on a hackathon project with Sam.', 'Sam': 'Sam is working on a hackathon project with Deven.'}\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Last line:\n",
|
||||
"Human: Deven & Sam are working on a hackathon project\n",
|
||||
"You:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' That sounds like a great project! What kind of project are they working on?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.run(\"Deven & Sam are working on a hackathon project\")"
|
||||
],
|
||||
"id": "297e78a6"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 35
|
||||
},
|
||||
"id": "YsFE3hBjC6gl",
|
||||
"outputId": "56ab5ca9-e343-41b5-e69d-47541718a9b4"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Deven is working on a hackathon project with Sam.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.memory.entity_store.get(\"Deven\")"
|
||||
],
|
||||
"id": "7e71f1dc"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Sam is working on a hackathon project with Deven.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.memory.entity_store.get(\"Sam\")"
|
||||
],
|
||||
"id": "316f2e8d"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [],
|
||||
"id": "b85f8427"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "venv",
|
||||
"language": "python",
|
||||
"name": "venv"
|
||||
},
|
||||
"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 +1,9 @@
|
||||
---
|
||||
sidebar_position: 0
|
||||
---
|
||||
|
||||
# Memory
|
||||
|
||||
import DocCardList from "@theme/DocCardList";
|
||||
|
||||
<DocCardList />
|
||||
@@ -0,0 +1,86 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Momento Chat Message History\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use [Momento Cache](https://gomomento.com) to store chat message history using the `MomentoChatMessageHistory` class. See the Momento [docs](https://docs.momentohq.com/getting-started) for more detail on how to get set up with Momento.\n",
|
||||
"\n",
|
||||
"Note that, by default we will create a cache if one with the given name doesn't already exist.\n",
|
||||
"\n",
|
||||
"You'll need to get a Momento auth token to use this class. This can either be passed in to a momento.CacheClient if you'd like to instantiate that directly, as a named parameter `auth_token` to `MomentoChatMessageHistory.from_client_params`, or can just be set as an environment variable `MOMENTO_AUTH_TOKEN`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from datetime import timedelta\n",
|
||||
"\n",
|
||||
"from langchain.memory import MomentoChatMessageHistory\n",
|
||||
"\n",
|
||||
"session_id = \"foo\"\n",
|
||||
"cache_name = \"langchain\"\n",
|
||||
"ttl = timedelta(days=1)\n",
|
||||
"history = MomentoChatMessageHistory.from_client_params(\n",
|
||||
" session_id,\n",
|
||||
" cache_name,\n",
|
||||
" ttl,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
|
||||
" AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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 +1,91 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Mongodb Chat Message History\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Mongodb to store chat message history.\n",
|
||||
"\n",
|
||||
"MongoDB is a source-available cross-platform document-oriented database program. Classified as a NoSQL database program, MongoDB uses JSON-like documents with optional schemas.\n",
|
||||
"\n",
|
||||
"MongoDB is developed by MongoDB Inc. and licensed under the Server Side Public License (SSPL). - [Wikipedia](https://en.wikipedia.org/wiki/MongoDB)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "47a601d2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Provide the connection string to connect to the MongoDB database\n",
|
||||
"connection_string = \"mongodb://mongo_user:password123@mongo:27017\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import MongoDBChatMessageHistory\n",
|
||||
"\n",
|
||||
"message_history = MongoDBChatMessageHistory(\n",
|
||||
" connection_string=connection_string, session_id=\"test-session\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"message_history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"message_history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
|
||||
" AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"message_history.messages"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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 +1,193 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Motörhead Memory\n",
|
||||
"[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"See instructions at [Motörhead](https://github.com/getmetal/motorhead) for running the server locally.\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory.motorhead_memory import MotorheadMemory\n",
|
||||
"from langchain import OpenAI, LLMChain, PromptTemplate\n",
|
||||
"\n",
|
||||
"template = \"\"\"You are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Human: {human_input}\n",
|
||||
"AI:\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"chat_history\", \"human_input\"], template=template\n",
|
||||
")\n",
|
||||
"memory = MotorheadMemory(\n",
|
||||
" session_id=\"testing-1\", url=\"http://localhost:8080\", memory_key=\"chat_history\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"await memory.init()\n",
|
||||
"# loads previous state from Motörhead 🤘\n",
|
||||
"\n",
|
||||
"llm_chain = LLMChain(\n",
|
||||
" llm=OpenAI(),\n",
|
||||
" prompt=prompt,\n",
|
||||
" verbose=True,\n",
|
||||
" memory=memory,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hi Bob, nice to meet you! How are you doing today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"hi im bob\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI: Hi Bob, nice to meet you! How are you doing today?\n",
|
||||
"Human: whats my name?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' You said your name is Bob. Is that correct?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"whats my name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI: Hi Bob, nice to meet you! How are you doing today?\n",
|
||||
"Human: whats my name?\n",
|
||||
"AI: You said your name is Bob. Is that correct?\n",
|
||||
"Human: whats for dinner?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" I'm sorry, I'm not sure what you're asking. Could you please rephrase your question?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"whats for dinner?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,198 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Motörhead Memory (Managed)\n",
|
||||
"[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"See instructions at [Motörhead](https://docs.getmetal.io/motorhead/introduction) for running the managed version of Motorhead. You can retrieve your `api_key` and `client_id` by creating an account on [Metal](https://getmetal.io).\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory.motorhead_memory import MotorheadMemory\n",
|
||||
"from langchain import OpenAI, LLMChain, PromptTemplate\n",
|
||||
"\n",
|
||||
"template = \"\"\"You are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Human: {human_input}\n",
|
||||
"AI:\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"chat_history\", \"human_input\"], \n",
|
||||
" template=template\n",
|
||||
")\n",
|
||||
"memory = MotorheadMemory(\n",
|
||||
" api_key=\"YOUR_API_KEY\",\n",
|
||||
" client_id=\"YOUR_CLIENT_ID\"\n",
|
||||
" session_id=\"testing-1\",\n",
|
||||
" memory_key=\"chat_history\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"await memory.init(); # loads previous state from Motörhead 🤘\n",
|
||||
"\n",
|
||||
"llm_chain = LLMChain(\n",
|
||||
" llm=OpenAI(), \n",
|
||||
" prompt=prompt, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=memory,\n",
|
||||
")\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hi Bob, nice to meet you! How are you doing today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"hi im bob\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI: Hi Bob, nice to meet you! How are you doing today?\n",
|
||||
"Human: whats my name?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' You said your name is Bob. Is that correct?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"whats my name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"Human: hi im bob\n",
|
||||
"AI: Hi Bob, nice to meet you! How are you doing today?\n",
|
||||
"Human: whats my name?\n",
|
||||
"AI: You said your name is Bob. Is that correct?\n",
|
||||
"Human: whats for dinner?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" I'm sorry, I'm not sure what you're asking. Could you please rephrase your question?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.run(\"whats for dinner?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Postgres Chat Message History\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Postgres to store chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import PostgresChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = PostgresChatMessageHistory(\n",
|
||||
" connection_string=\"postgresql://postgres:mypassword@localhost/chat_history\",\n",
|
||||
" session_id=\"foo\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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 +1,81 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Redis Chat Message History\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Redis to store chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import RedisChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = RedisChatMessageHistory(\"foo\")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[AIMessage(content='whats up?', additional_kwargs={}),\n",
|
||||
" HumanMessage(content='hi!', additional_kwargs={})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8af285f8",
|
||||
"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 +1,422 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Zep Memory\n",
|
||||
"\n",
|
||||
"## REACT Agent Chat Message History with Zep - A long-term memory store for LLM applications.\n",
|
||||
"\n",
|
||||
"This notebook demonstrates how to use the [Zep Long-term Memory Store](https://docs.getzep.com/) as memory for your chatbot.\n",
|
||||
"\n",
|
||||
"We'll demonstrate:\n",
|
||||
"\n",
|
||||
"1. Adding conversation history to the Zep memory store.\n",
|
||||
"2. Running an agent and having message automatically added to the store.\n",
|
||||
"3. Viewing the enriched messages.\n",
|
||||
"4. Vector search over the conversation history.\n",
|
||||
"\n",
|
||||
"### More on Zep:\n",
|
||||
"\n",
|
||||
"Zep stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.\n",
|
||||
"\n",
|
||||
"Key Features:\n",
|
||||
"\n",
|
||||
"- **Fast!** Zep’s async extractors operate independently of the your chat loop, ensuring a snappy user experience.\n",
|
||||
"- **Long-term memory persistence**, with access to historical messages irrespective of your summarization strategy.\n",
|
||||
"- **Auto-summarization** of memory messages based on a configurable message window. A series of summaries are stored, providing flexibility for future summarization strategies.\n",
|
||||
"- **Hybrid search** over memories and metadata, with messages automatically embedded on creation.\n",
|
||||
"- **Entity Extractor** that automatically extracts named entities from messages and stores them in the message metadata.\n",
|
||||
"- **Auto-token counting** of memories and summaries, allowing finer-grained control over prompt assembly.\n",
|
||||
"- Python and JavaScript SDKs.\n",
|
||||
"\n",
|
||||
"Zep project: [https://github.com/getzep/zep](https://github.com/getzep/zep)\n",
|
||||
"Docs: [https://docs.getzep.com/](https://docs.getzep.com/)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:20:49.003167Z",
|
||||
"start_time": "2023-07-09T19:20:47.446370Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import ZepMemory\n",
|
||||
"from langchain.retrievers import ZepRetriever\n",
|
||||
"from langchain import OpenAI\n",
|
||||
"from langchain.schema import HumanMessage, AIMessage\n",
|
||||
"from langchain.utilities import WikipediaAPIWrapper\n",
|
||||
"from langchain.agents import initialize_agent, AgentType, Tool\n",
|
||||
"from uuid import uuid4\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Set this to your Zep server URL\n",
|
||||
"ZEP_API_URL = \"http://localhost:8000\"\n",
|
||||
"\n",
|
||||
"session_id = str(uuid4()) # This is a unique identifier for the user"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:14.378234Z",
|
||||
"start_time": "2023-07-09T19:20:49.005041Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Provide your OpenAI key\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"openai_key = getpass.getpass()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:16.329934Z",
|
||||
"start_time": "2023-07-09T19:23:14.345580Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Provide your Zep API key. Note that this is optional. See https://docs.getzep.com/deployment/auth\n",
|
||||
"\n",
|
||||
"zep_api_key = getpass.getpass()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Initialize the Zep Chat Message History Class and initialize the Agent\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:16.528212Z",
|
||||
"start_time": "2023-07-09T19:23:16.279045Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = WikipediaAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to search online for answers. You should ask targeted questions\",\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# Set up Zep Chat History\n",
|
||||
"memory = ZepMemory(\n",
|
||||
" session_id=session_id,\n",
|
||||
" url=ZEP_API_URL,\n",
|
||||
" api_key=zep_api_key,\n",
|
||||
" memory_key=\"chat_history\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Initialize the agent\n",
|
||||
"llm = OpenAI(temperature=0, openai_api_key=openai_key)\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
" memory=memory,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Add some history data\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:16.659484Z",
|
||||
"start_time": "2023-07-09T19:23:16.532090Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Preload some messages into the memory. The default message window is 12 messages. We want to push beyond this to demonstrate auto-summarization.\n",
|
||||
"test_history = [\n",
|
||||
" {\"role\": \"human\", \"content\": \"Who was Octavia Butler?\"},\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American\"\n",
|
||||
" \" science fiction author.\"\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" {\"role\": \"human\", \"content\": \"Which books of hers were made into movies?\"},\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"The most well-known adaptation of Octavia Butler's work is the FX series\"\n",
|
||||
" \" Kindred, based on her novel of the same name.\"\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" {\"role\": \"human\", \"content\": \"Who were her contemporaries?\"},\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R.\"\n",
|
||||
" \" Delany, and Joanna Russ.\"\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" {\"role\": \"human\", \"content\": \"What awards did she win?\"},\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur\"\n",
|
||||
" \" Fellowship.\"\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"human\",\n",
|
||||
" \"content\": \"Which other women sci-fi writers might I want to read?\",\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": \"You might want to read Ursula K. Le Guin or Joanna Russ.\",\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"human\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"Write a short synopsis of Butler's book, Parable of the Sower. What is it\"\n",
|
||||
" \" about?\"\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": (\n",
|
||||
" \"Parable of the Sower is a science fiction novel by Octavia Butler,\"\n",
|
||||
" \" published in 1993. It follows the story of Lauren Olamina, a young woman\"\n",
|
||||
" \" living in a dystopian future where society has collapsed due to\"\n",
|
||||
" \" environmental disasters, poverty, and violence.\"\n",
|
||||
" ),\n",
|
||||
" \"metadata\": {\"foo\": \"bar\"},\n",
|
||||
" },\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"for msg in test_history:\n",
|
||||
" memory.chat_memory.add_message(\n",
|
||||
" HumanMessage(content=msg[\"content\"])\n",
|
||||
" if msg[\"role\"] == \"human\"\n",
|
||||
" else AIMessage(content=msg[\"content\"]),\n",
|
||||
" metadata=msg.get(\"metadata\", {}),\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Run the agent\n",
|
||||
"\n",
|
||||
"Doing so will automatically add the input and response to the Zep memory.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:19.348822Z",
|
||||
"start_time": "2023-07-09T19:23:16.660130Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new chain...\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3mThought: Do I need to use a tool? No\n",
|
||||
"AI: Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.\u001B[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.'"
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\n",
|
||||
" input=\"What is the book's relevance to the challenges facing contemporary society?\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Inspect the Zep memory\n",
|
||||
"\n",
|
||||
"Note the summary, and that the history has been enriched with token counts, UUIDs, and timestamps.\n",
|
||||
"\n",
|
||||
"Summaries are biased towards the most recent messages.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:23:41.042254Z",
|
||||
"start_time": "2023-07-09T19:23:41.016815Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The human inquires about Octavia Butler. The AI identifies her as an American science fiction author. The human then asks which books of hers were made into movies. The AI responds by mentioning the FX series Kindred, based on her novel of the same name. The human then asks about her contemporaries, and the AI lists Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"system :\n",
|
||||
" {'content': 'The human inquires about Octavia Butler. The AI identifies her as an American science fiction author. The human then asks which books of hers were made into movies. The AI responds by mentioning the FX series Kindred, based on her novel of the same name. The human then asks about her contemporaries, and the AI lists Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.', 'additional_kwargs': {}}\n",
|
||||
"human :\n",
|
||||
" {'content': 'What awards did she win?', 'additional_kwargs': {'uuid': '6b733f0b-6778-49ae-b3ec-4e077c039f31', 'created_at': '2023-07-09T19:23:16.611232Z', 'token_count': 8, 'metadata': {'system': {'entities': [], 'intent': 'The subject is inquiring about the awards that someone, whose identity is not specified, has won.'}}}, 'example': False}\n",
|
||||
"ai :\n",
|
||||
" {'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'additional_kwargs': {'uuid': '2f6d80c6-3c08-4fd4-8d4e-7bbee341ac90', 'created_at': '2023-07-09T19:23:16.618947Z', 'token_count': 21, 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 14, 'Start': 0, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 33, 'Start': 19, 'Text': 'the Hugo Award'}], 'Name': 'the Hugo Award'}, {'Label': 'EVENT', 'Matches': [{'End': 81, 'Start': 57, 'Text': 'the MacArthur Fellowship'}], 'Name': 'the MacArthur Fellowship'}], 'intent': 'The subject is stating that Octavia Butler received the Hugo Award, the Nebula Award, and the MacArthur Fellowship.'}}}, 'example': False}\n",
|
||||
"human :\n",
|
||||
" {'content': 'Which other women sci-fi writers might I want to read?', 'additional_kwargs': {'uuid': 'ccdcc901-ea39-4981-862f-6fe22ab9289b', 'created_at': '2023-07-09T19:23:16.62678Z', 'token_count': 14, 'metadata': {'system': {'entities': [], 'intent': 'The subject is seeking recommendations for additional women science fiction writers to explore.'}}}, 'example': False}\n",
|
||||
"ai :\n",
|
||||
" {'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'additional_kwargs': {'uuid': '7977099a-0c62-4c98-bfff-465bbab6c9c3', 'created_at': '2023-07-09T19:23:16.631721Z', 'token_count': 18, 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': 'The subject is suggesting that the person should consider reading the works of Ursula K. Le Guin or Joanna Russ.'}}}, 'example': False}\n",
|
||||
"human :\n",
|
||||
" {'content': \"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", 'additional_kwargs': {'uuid': 'e439b7e6-286a-4278-a8cb-dc260fa2e089', 'created_at': '2023-07-09T19:23:16.63623Z', 'token_count': 23, 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 32, 'Start': 26, 'Text': 'Butler'}], 'Name': 'Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 61, 'Start': 41, 'Text': 'Parable of the Sower'}], 'Name': 'Parable of the Sower'}], 'intent': 'The subject is requesting a brief summary or explanation of the book \"Parable of the Sower\" by Butler.'}}}, 'example': False}\n",
|
||||
"ai :\n",
|
||||
" {'content': 'Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', 'additional_kwargs': {'uuid': '6760489b-19c9-41aa-8b45-fae6cb1d7ee6', 'created_at': '2023-07-09T19:23:16.647524Z', 'token_count': 56, 'metadata': {'foo': 'bar', 'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}, {'Label': 'PERSON', 'Matches': [{'End': 65, 'Start': 51, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'DATE', 'Matches': [{'End': 84, 'Start': 80, 'Text': '1993'}], 'Name': '1993'}, {'Label': 'PERSON', 'Matches': [{'End': 124, 'Start': 110, 'Text': 'Lauren Olamina'}], 'Name': 'Lauren Olamina'}], 'intent': 'The subject is providing information about the novel \"Parable of the Sower\" by Octavia Butler, including its genre, publication date, and a brief summary of the plot.'}}}, 'example': False}\n",
|
||||
"human :\n",
|
||||
" {'content': \"What is the book's relevance to the challenges facing contemporary society?\", 'additional_kwargs': {'uuid': '7dbbbb93-492b-4739-800f-cad2b6e0e764', 'created_at': '2023-07-09T19:23:19.315182Z', 'token_count': 15, 'metadata': {'system': {'entities': [], 'intent': 'The subject is asking about the relevance of a book to the challenges currently faced by society.'}}}, 'example': False}\n",
|
||||
"ai :\n",
|
||||
" {'content': 'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.', 'additional_kwargs': {'uuid': '3e14ac8f-b7c1-4360-958b-9f3eae1f784f', 'created_at': '2023-07-09T19:23:19.332517Z', 'token_count': 66, 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}], 'intent': 'The subject is providing an analysis and evaluation of the novel \"Parable of the Sower\" and highlighting its relevance to contemporary societal challenges.'}}}, 'example': False}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def print_messages(messages):\n",
|
||||
" for m in messages:\n",
|
||||
" print(m.type, \":\\n\", m.dict())\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"print(memory.chat_memory.zep_summary)\n",
|
||||
"print(\"\\n\")\n",
|
||||
"print_messages(memory.chat_memory.messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Vector search over the Zep memory\n",
|
||||
"\n",
|
||||
"Zep provides native vector search over historical conversation memory via the `ZepRetriever`.\n",
|
||||
"\n",
|
||||
"You can use the `ZepRetriever` with chains that support passing in a Langchain `Retriever` object.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-07-09T19:24:30.781893Z",
|
||||
"start_time": "2023-07-09T19:24:30.595650Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'uuid': 'ccdcc901-ea39-4981-862f-6fe22ab9289b', 'created_at': '2023-07-09T19:23:16.62678Z', 'role': 'human', 'content': 'Which other women sci-fi writers might I want to read?', 'metadata': {'system': {'entities': [], 'intent': 'The subject is seeking recommendations for additional women science fiction writers to explore.'}}, 'token_count': 14} 0.9119619869747062\n",
|
||||
"{'uuid': '7977099a-0c62-4c98-bfff-465bbab6c9c3', 'created_at': '2023-07-09T19:23:16.631721Z', 'role': 'ai', 'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': 'The subject is suggesting that the person should consider reading the works of Ursula K. Le Guin or Joanna Russ.'}}, 'token_count': 18} 0.8534346954749745\n",
|
||||
"{'uuid': 'b05e2eb5-c103-4973-9458-928726f08655', 'created_at': '2023-07-09T19:23:16.603098Z', 'role': 'ai', 'content': \"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 16, 'Start': 0, 'Text': \"Octavia Butler's\"}], 'Name': \"Octavia Butler's\"}, {'Label': 'ORG', 'Matches': [{'End': 58, 'Start': 41, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 76, 'Start': 60, 'Text': 'Samuel R. Delany'}], 'Name': 'Samuel R. Delany'}, {'Label': 'PERSON', 'Matches': [{'End': 93, 'Start': 82, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': \"The subject is stating that Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\"}}, 'token_count': 27} 0.8523831524040919\n",
|
||||
"{'uuid': 'e346f02b-f854-435d-b6ba-fb394a416b9b', 'created_at': '2023-07-09T19:23:16.556587Z', 'role': 'human', 'content': 'Who was Octavia Butler?', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 8, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}], 'intent': 'The subject is asking for information about the identity or background of Octavia Butler.'}}, 'token_count': 8} 0.8236355436055457\n",
|
||||
"{'uuid': '42ff41d2-c63a-4d5b-b19b-d9a87105cfc3', 'created_at': '2023-07-09T19:23:16.578022Z', 'role': 'ai', 'content': 'Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 0, 'Text': 'Octavia Estelle Butler'}], 'Name': 'Octavia Estelle Butler'}, {'Label': 'DATE', 'Matches': [{'End': 37, 'Start': 24, 'Text': 'June 22, 1947'}], 'Name': 'June 22, 1947'}, {'Label': 'DATE', 'Matches': [{'End': 57, 'Start': 40, 'Text': 'February 24, 2006'}], 'Name': 'February 24, 2006'}, {'Label': 'NORP', 'Matches': [{'End': 74, 'Start': 66, 'Text': 'American'}], 'Name': 'American'}], 'intent': 'The subject is providing information about Octavia Estelle Butler, who was an American science fiction author.'}}, 'token_count': 31} 0.8206687242257686\n",
|
||||
"{'uuid': '2f6d80c6-3c08-4fd4-8d4e-7bbee341ac90', 'created_at': '2023-07-09T19:23:16.618947Z', 'role': 'ai', 'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 14, 'Start': 0, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 33, 'Start': 19, 'Text': 'the Hugo Award'}], 'Name': 'the Hugo Award'}, {'Label': 'EVENT', 'Matches': [{'End': 81, 'Start': 57, 'Text': 'the MacArthur Fellowship'}], 'Name': 'the MacArthur Fellowship'}], 'intent': 'The subject is stating that Octavia Butler received the Hugo Award, the Nebula Award, and the MacArthur Fellowship.'}}, 'token_count': 21} 0.8199012397683285\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"retriever = ZepRetriever(\n",
|
||||
" session_id=session_id,\n",
|
||||
" url=ZEP_API_URL,\n",
|
||||
" api_key=zep_api_key,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"search_results = memory.chat_memory.search(\"who are some famous women sci-fi authors?\")\n",
|
||||
"for r in search_results:\n",
|
||||
" if r.dist > 0.8: # Only print results with similarity of 0.8 or higher\n",
|
||||
" print(r.message, r.dist)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
Reference in New Issue
Block a user