mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-02 19:47:13 +00:00
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
This commit is contained in:
Harrison Chase
GitHub
192
docs/modules/agents/examples/intermediate_steps.ipynb
Normal file
192
docs/modules/agents/examples/intermediate_steps.ipynb
Normal file
@@ -0,0 +1,192 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5436020b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Intermediate Steps\n",
|
||||
"\n",
|
||||
"In order to get more visibility into what an agent is doing, we can also return intermediate steps. This comes in the form of an extra key in the return value, which is a list of (action, observation) tuples."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "b2b0d119",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import load_tools\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1b440b8a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Initialize the components needed for the agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "36ed392e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0, model_name='text-davinci-002')\n",
|
||||
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1d329c3d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Initialize the agent with `return_intermediate_steps=True`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "6abf3b08",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True, return_intermediate_steps=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "837211e8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I should look up Olivia Wilde's boyfriend's age\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Olivia Wilde's boyfriend's age\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should use the calculator to raise that number to the 0.23 power\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 28^0.23\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 2.1520202182226886\u001b[0m\n",
|
||||
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"response = agent({\"input\":\"How old is Olivia Wilde's boyfriend? What is that number raised to the 0.23 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "e1a39a23",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[(AgentAction(tool='Search', tool_input=\"Olivia Wilde's boyfriend's age\", log=' I should look up Olivia Wilde\\'s boyfriend\\'s age\\nAction: Search\\nAction Input: \"Olivia Wilde\\'s boyfriend\\'s age\"'), '28 years'), (AgentAction(tool='Calculator', tool_input='28^0.23', log=' I should use the calculator to raise that number to the 0.23 power\\nAction: Calculator\\nAction Input: 28^0.23'), 'Answer: 2.1520202182226886\\n')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# The actual return type is a NamedTuple for the agent action, and then an observation\n",
|
||||
"print(response[\"intermediate_steps\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "6365bb69",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[\n",
|
||||
" [\n",
|
||||
" [\n",
|
||||
" \"Search\",\n",
|
||||
" \"Olivia Wilde's boyfriend's age\",\n",
|
||||
" \" I should look up Olivia Wilde's boyfriend's age\\nAction: Search\\nAction Input: \\\"Olivia Wilde's boyfriend's age\\\"\"\n",
|
||||
" ],\n",
|
||||
" \"28 years\"\n",
|
||||
" ],\n",
|
||||
" [\n",
|
||||
" [\n",
|
||||
" \"Calculator\",\n",
|
||||
" \"28^0.23\",\n",
|
||||
" \" I should use the calculator to raise that number to the 0.23 power\\nAction: Calculator\\nAction Input: 28^0.23\"\n",
|
||||
" ],\n",
|
||||
" \"Answer: 2.1520202182226886\\n\"\n",
|
||||
" ]\n",
|
||||
"]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"print(json.dumps(response[\"intermediate_steps\"], indent=2))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e7776981",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8dc69fc3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.9.0 64-bit ('llm-env')",
|
||||
"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": "3.9.0"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user