forked from Archives/langchain
docs/fix links (#6498)
Davis Chase
11 months ago
committed by
GitHub
parent
ae6196507d
commit
3298bf4f00
@ -1,474 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5371a9bb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tracing Walkthrough\n",
|
||||
"\n",
|
||||
"There are two recommended ways to trace your LangChains:\n",
|
||||
"\n",
|
||||
"1. Setting the `LANGCHAIN_TRACING` environment variable to \"true\".\n",
|
||||
"1. Using a context manager with tracing_enabled() to trace a particular block of code.\n",
|
||||
"\n",
|
||||
"**Note** if the environment variable is set, all code will be traced, regardless of whether or not it's within the context manager."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "17c04cc6-c93d-4b6c-a033-e897577f4ed1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LANGCHAIN_TRACING\"] = \"true\"\n",
|
||||
"\n",
|
||||
"## Uncomment below if using hosted setup.\n",
|
||||
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://langchain-api-gateway-57eoxz8z.uc.gateway.dev\"\n",
|
||||
"\n",
|
||||
"## Uncomment below if you want traces to be recorded to \"my_session\" instead of \"default\".\n",
|
||||
"# os.environ[\"LANGCHAIN_SESSION\"] = \"my_session\"\n",
|
||||
"\n",
|
||||
"## Better to set this environment variable in the terminal\n",
|
||||
"## Uncomment below if using hosted version. Replace \"my_api_key\" with your actual API Key.\n",
|
||||
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"my_api_key\"\n",
|
||||
"\n",
|
||||
"import langchain\n",
|
||||
"from langchain.agents import Tool, initialize_agent, load_tools\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.callbacks import tracing_enabled\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "1b62cd48",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"llm-math\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^.123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4829eb1d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Agent run with tracing using a chat model\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" ChatOpenAI(temperature=0),\n",
|
||||
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "76abfd82",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 5 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.2193914912400514\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Both of the agent runs will be traced because the environment variable is set\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")\n",
|
||||
"with tracing_enabled() as session:\n",
|
||||
" agent.run(\"What is 5 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "fe833c33-033f-4806-be0c-cc3d147db13d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 5 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.2193914912400514\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Now, we unset the environment variable and use a context manager.\n",
|
||||
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
|
||||
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
|
||||
"\n",
|
||||
"# here, we are writing traces to \"my_test_session\"\n",
|
||||
"with tracing_enabled(\"my_session\") as session:\n",
|
||||
" assert session\n",
|
||||
" agent.run(\"What is 5 raised to .123243 power?\") # this should be traced\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\") # this should not be traced"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "b34105a4-be8e-46e4-8abe-01adba3ba727",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 3^0.123\u001b[0m\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^0.123\u001b[0m\u001b[32;1m\u001b[1;3mAny number raised to the power of 0 is 1, but I'm not sure about a decimal power.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 1^.123\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.1446847956963533\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0889970153361064\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0'"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# The context manager is concurrency safe:\n",
|
||||
"import asyncio\n",
|
||||
"\n",
|
||||
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
|
||||
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
|
||||
"\n",
|
||||
"questions = [f\"What is {i} raised to .123 power?\" for i in range(1, 4)]\n",
|
||||
"\n",
|
||||
"# start a background task\n",
|
||||
"task = asyncio.create_task(agent.arun(questions[0])) # this should not be traced\n",
|
||||
"with tracing_enabled() as session:\n",
|
||||
" assert session\n",
|
||||
" tasks = [agent.arun(q) for q in questions[1:3]] # these should be traced\n",
|
||||
" await asyncio.gather(*tasks)\n",
|
||||
"\n",
|
||||
"await task"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c552a5dd-cbca-48b9-90e6-930076006f78",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## [Beta] Tracing V2\n",
|
||||
"\n",
|
||||
"We are rolling out a newer version of our tracing service with more features coming soon. Here are the instructions on how to use it to trace your runs.\n",
|
||||
"\n",
|
||||
"To use, you can use the `tracing_v2_enabled` context manager or set `LANGCHAIN_TRACING_V2 = 'true'`\n",
|
||||
"\n",
|
||||
"**Option 1 (Local)**: \n",
|
||||
"* Run the local LangChainPlus Server\n",
|
||||
"```\n",
|
||||
"pip install --upgrade langchain\n",
|
||||
"langchain plus start\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"**Option 2 (Hosted)**:\n",
|
||||
"* After making an account an grabbing a LangChainPlus API Key, set the `LANGCHAIN_ENDPOINT` and `LANGCHAIN_API_KEY` environment variables"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "87027b0d-3a61-47cf-8a65-3002968be7f9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
|
||||
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.langchain.plus\" # Uncomment this line if you want to use the hosted version\n",
|
||||
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"<YOUR-LANGCHAINPLUS-API-KEY>\" # Uncomment this line if you want to use the hosted version."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "5b4f49a2-7d09-4601-a8ba-976f0517c64c",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import langchain\n",
|
||||
"from langchain.agents import Tool, initialize_agent, load_tools\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.callbacks import tracing_enabled\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "029b4a57-dc49-49de-8f03-53c292144e09",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"llm-math\"], llm=llm)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "91a85fb2-6027-4bd0-b1fe-2a3b3b79e2dd",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^.123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f2291e9f-02f3-4b55-bd3d-d719de815df1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 73 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 348 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 239 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 253 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 117 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 94 KiB |
@ -1,196 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "9502d5b0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenAI Functions Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases using an agent that uses the OpenAI functions ability to respond to the prompts of the user using a Large Language Model\n",
|
||||
"\n",
|
||||
"Install openai,google-search-results packages which are required as the langchain packages call them internally\n",
|
||||
"\n",
|
||||
">pip install openai google-search-results\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "c0a83623",
|
||||
"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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "86198d9c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The agent is given ability to perform 3 search functionalities with the respective tools\n",
|
||||
"\n",
|
||||
"SerpAPIWrapper:\n",
|
||||
">This initializes the SerpAPIWrapper for search functionality (search).\n",
|
||||
"\n",
|
||||
"LLMMathChain Initialization:\n",
|
||||
">This component provides math-related functionality.\n",
|
||||
"\n",
|
||||
"SQL Database Initialization:\n",
|
||||
">This component provides the agent to query in Custom Data Base.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6fefaba2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Initialize the OpenAI language model\n",
|
||||
"#Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual OpenAI key.\n",
|
||||
"llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\",openai_api_key=\"<your_api_key>\")\n",
|
||||
"\n",
|
||||
"# Initialize the SerpAPIWrapper for search functionality\n",
|
||||
"#Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual SerpAPI key.\n",
|
||||
"search = SerpAPIWrapper(serpapi_api_key=\"<your_api_key>\")\n",
|
||||
"\n",
|
||||
"# Initialize the LLMMathChain\n",
|
||||
"llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
|
||||
"\n",
|
||||
"# Initialize the SQL database using the Chinook database file\n",
|
||||
"# Replace the file location to the custom Data Base\n",
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
|
||||
"\n",
|
||||
"# Initialize the SQLDatabaseChain with the OpenAI language model and SQL database\n",
|
||||
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
|
||||
"\n",
|
||||
"# Define a list of tools offered by the agent\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
|
||||
" description=\"Useful 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 when you need to answer questions about math.\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"FooBar-DB\",\n",
|
||||
" func=db_chain.run,\n",
|
||||
" description=\"Useful when you need to answer questions about FooBar. Input should be in the form of a question containing full context.\"\n",
|
||||
" )\n",
|
||||
"]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "9ff6cee9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mrkl = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "ba8e4cbe",
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"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: `Search` with `{'query': 'Leo DiCaprio girlfriend'}`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3mAmidst his casual romance with Gigi, Leo allegedly entered a relationship with 19-year old model, Eden Polani, in February 2023.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `Calculator` with `{'expression': '19^0.43'}`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"19^0.43\u001b[32;1m\u001b[1;3m```text\n",
|
||||
"19**0.43\n",
|
||||
"```\n",
|
||||
"...numexpr.evaluate(\"19**0.43\")...\n",
|
||||
"\u001b[0m\n",
|
||||
"Answer: \u001b[33;1m\u001b[1;3m3.547023357958959\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\u001b[33;1m\u001b[1;3mAnswer: 3.547023357958959\u001b[0m\u001b[32;1m\u001b[1;3mLeo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Leo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mrkl.run(\n",
|
||||
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9f5f6743",
|
||||
"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
|
||||
}
|
||||
Loading…
Reference in New Issue