github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-04 20:46:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

support memory for functions (#6165)

Browse Source 
#### Before submitting
Add memory support for `OpenAIFunctionsAgent` like
`StructuredChatAgent`.


#### Who can review?
 @hwchase17

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Fei Wang
2023-06-19 10:00:40 +08:00
committed by GitHub
parent b2b9ded12f
commit 50556f3b35
5 changed files with 507 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

233
docs/extras/modules/agents/how_to/add_memory_openai_functions.ipynb Normal file
View File

@@ -0,0 +1,233 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0c9954e9",
"metadata": {},
"source": [
"# Add Memory to OpenAI Functions Agent\n",
"\n",
"This notebook goes over how to add memory to OpenAI Functions agent."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ac594f26",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.4) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from langchain import (\n",
" LLMMathChain,\n",
" OpenAI,\n",
" SerpAPIWrapper,\n",
" SQLDatabase,\n",
" SQLDatabaseChain,\n",
")\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.agents import AgentType\n",
"from langchain.chat_models import ChatOpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1e7844e7",
"metadata": {},
"outputs": [],
"source": [
"llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
"search = SerpAPIWrapper()\n",
"llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
"tools = [\n",
" Tool(\n",
" name=\"Search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
" ),\n",
" Tool(\n",
" name=\"Calculator\",\n",
" func=llm_math_chain.run,\n",
" description=\"useful for when you need to answer questions about math\",\n",
" ),\n",
" Tool(\n",
" name=\"FooBar-DB\",\n",
" func=db_chain.run,\n",
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\",\n",
" ),\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "54ca3b82",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import MessagesPlaceholder\n",
"from langchain.memory import ConversationBufferMemory\n",
"agent_kwargs = {\n",
" \"extra_prompt_messages\": [MessagesPlaceholder(variable_name=\"memory\")],\n",
"}\n",
"memory = ConversationBufferMemory(memory_key=\"memory\", return_messages=True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "81af5658",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(\n",
" tools, \n",
" llm, \n",
" agent=AgentType.OPENAI_FUNCTIONS, \n",
" verbose=True, \n",
" agent_kwargs=agent_kwargs, \n",
" memory=memory\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8ab08f43",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mHello! How can I assist you today?\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Hello! How can I assist you today?'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"hi\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "520a81f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mNice to meet you, Bob! How can I help you today?\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Nice to meet you, Bob! How can I help you today?'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"my name is bob\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8bc4a69f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mYour name is Bob.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Your name is Bob.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats my name\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "40def1b7",
"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
}

173
docs/extras/modules/agents/how_to/use_toolkits_with_openai_functions.ipynb Normal file
View File

@@ -0,0 +1,173 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "af49b410",
"metadata": {},
"source": [
"# Use ToolKits with OpenAI Functions\n",
"\n",
"This notebook shows how to use the OpenAI functions agent with arbitrary toolkits."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "af6496bd",
"metadata": {},
"outputs": [],
"source": [
"from langchain import (\n",
" LLMMathChain,\n",
" OpenAI,\n",
" SerpAPIWrapper,\n",
" SQLDatabase,\n",
" SQLDatabaseChain,\n",
")\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.agents import AgentType\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
"from langchain.schema import SystemMessage"
]
},
{
"cell_type": "markdown",
"id": "1b7ee35f",
"metadata": {},
"source": [
"Load the toolkit"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "0423c32c",
"metadata": {},
"outputs": [],
"source": [
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
"toolkit = SQLDatabaseToolkit(llm=ChatOpenAI(), db=db)"
]
},
{
"cell_type": "markdown",
"id": "203fa80a",
"metadata": {},
"source": [
"Set a system message specific to that toolkit"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e4edb101",
"metadata": {},
"outputs": [],
"source": [
"agent_kwargs = {\n",
" \"system_message\": SystemMessage(content=\"You are an expert SQL data analyst.\")\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "e0c67b60",
"metadata": {},
"outputs": [],
"source": [
"llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
"agent = initialize_agent(\n",
" toolkit.get_tools(), \n",
" llm, \n",
" agent=AgentType.OPENAI_FUNCTIONS, \n",
" verbose=True, \n",
" agent_kwargs=agent_kwargs,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "93619811",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `sql_db_query` with `{'query': 'SELECT COUNT(DISTINCT artist_name) AS num_artists FROM artists'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such table: artists\n",
"[SQL: SELECT COUNT(DISTINCT artist_name) AS num_artists FROM artists]\n",
"(Background on this error at: https://sqlalche.me/e/20/e3q8)\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `sql_db_list_tables` with `{}`\n",
"\n",
"\n",
"\u001b[0m\u001b[38;5;200m\u001b[1;3mMediaType, Track, Playlist, sales_table, Customer, Genre, PlaylistTrack, Artist, Invoice, Album, InvoiceLine, Employee\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `sql_db_query` with `{'query': 'SELECT COUNT(DISTINCT artist_id) AS num_artists FROM Artist'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: artist_id\n",
"[SQL: SELECT COUNT(DISTINCT artist_id) AS num_artists FROM Artist]\n",
"(Background on this error at: https://sqlalche.me/e/20/e3q8)\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `sql_db_query` with `{'query': 'SELECT COUNT(DISTINCT Name) AS num_artists FROM Artist'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m[(275,)]\u001b[0m\u001b[32;1m\u001b[1;3mThere are 275 different artists in the database.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 275 different artists in the database.'"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many different artists are there?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "34415bad",
"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
}