mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 13:06:03 +00:00
(WIP) agents (#171)
This commit is contained in:
Harrison Chase
GitHub
192
docs/getting_started/agents.ipynb
Normal file
192
docs/getting_started/agents.ipynb
Normal file
@@ -0,0 +1,192 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5436020b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Agents\n",
|
||||
"Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input. In these types of chains, there is a \"agent\" (backed by an LLM) which has access to a suite of tools. Depending on the user input, the agent can then decide which, if any, of these tools to call.\n",
|
||||
"\n",
|
||||
"When used correctly agents can be extremely powerful. The purpose of this notebook is to show you how to easily use agents through the simplest, highest level API. If you want more low level control over various components, check out the documentation for custom agents (coming soon). For a list of supported agent types and their specifications, see [here](../explanation/agents.md)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3c6226b9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Concepts\n",
|
||||
"\n",
|
||||
"In order to understand agents, you should understand the following concepts:\n",
|
||||
"\n",
|
||||
"- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
|
||||
"- LLM: The language model powering the agent.\n",
|
||||
"- AgentType: The type of agent to use. This should be a string. For a list of supported agents, see [here](../explanation/agents.md). Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "05d4b21e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tools\n",
|
||||
"When constructing your own agent, you will need to provide it with a list of Tools that it can use. A Tool is defined as below.\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"class Tool(NamedTuple):\n",
|
||||
" \"\"\"Interface for tools.\"\"\"\n",
|
||||
"\n",
|
||||
" name: str\n",
|
||||
" func: Callable[[str], str]\n",
|
||||
" description: Optional[str] = None\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2558a02d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Loading an agent\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "36ed392e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Import things that are needed generically\n",
|
||||
"from langchain.agents import initialize_agent, Tool\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "56ff7670",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Load the tool configs that are needed.\n",
|
||||
"from langchain import LLMMathChain, SerpAPIChain\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"search = SerpAPIChain()\n",
|
||||
"llm_math_chain = LLMMathChain(llm=llm, 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\"\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",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5b93047d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Construct the agent. We will use the default agent type here.\n",
|
||||
"# See documentation for a full list of options.\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"agent = initialize_agent(tools, llm, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "6f96a891",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Harry Styles age\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 28^0.23\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"28^0.23\u001b[32;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"print(28**0.23)\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
|
||||
"\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'2.1520202182226886'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2f0852ff",
|
||||
"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": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
# Using Chains
|
||||
# LLM Chains
|
||||
|
||||
Calling an LLM is a great first step, but it's just the beginning.
|
||||
Normally when you use an LLM in an application, you are not sending user input directly to the LLM.
|
||||
@@ -33,7 +33,5 @@ Now we can run that can only specifying the product!
|
||||
chain.run("colorful socks")
|
||||
```
|
||||
|
||||
There we go! There's the first chain.
|
||||
|
||||
That is it for the Getting Started example.
|
||||
As a next step, we would suggest checking out the more complex chains in the [Demos section](/examples/demos)
|
||||
There we go! There's the first chain - an LLM Chain.
|
||||
This is one of the simpler types of chains, but understanding how it works will set you up well for working with more complex chains.
|
||||
265
docs/getting_started/sequential_chains.ipynb
Normal file
265
docs/getting_started/sequential_chains.ipynb
Normal file
@@ -0,0 +1,265 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4f73605d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Sequential Chains"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3b235f7a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The next step after calling a language model is make a series of calls to a language model. This is particularly useful when you want to take the output from one call and use it as the input to another.\n",
|
||||
"\n",
|
||||
"In this notebook we will walk through some examples for how to do this, using sequential chains. Sequential chains are defined as a series of chains, called in deterministic order. There are two types of sequential chains:\n",
|
||||
"\n",
|
||||
"- `SimpleSequentialChain`: The simplest form of sequential chains, where each step has a singular input/output, and the output of one step is the input to the next.\n",
|
||||
"- `SequentialChain`: A more general form of sequential chains, allowing for multiple inputs/outputs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5162794e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## SimpleSequentialChain\n",
|
||||
"\n",
|
||||
"In this series of chains, each individual chain has a single input and a single output, and the output of one step is used as input to the next.\n",
|
||||
"\n",
|
||||
"Let's walk through a toy example of doing this, where the first chain takes in the title of an imaginary play and then generates a synopsis for that title, and the second chain takes in the synopsis of that play and generates an imaginary review for that play."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "3f2f9b8c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import LLMChain\n",
|
||||
"from langchain.prompts import PromptTemplate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "b8237d1a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is an LLMChain to write a synopsis given a title of a play.\n",
|
||||
"llm = OpenAI(temperature=.7)\n",
|
||||
"template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
|
||||
"\n",
|
||||
"Title: {title}\n",
|
||||
"Playwright: This is a synopsis for the above play:\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
|
||||
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "4a391730",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is an LLMChain to write a review of a play given a synopsis.\n",
|
||||
"llm = OpenAI(temperature=.7)\n",
|
||||
"template = \"\"\"You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.\n",
|
||||
"\n",
|
||||
"Play Synopsis:\n",
|
||||
"{synopsis}\n",
|
||||
"Review from a New York Times play critic of the above play:\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"synopsis\"], template=template)\n",
|
||||
"review_chain = LLMChain(llm=llm, prompt=prompt_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "9368bd63",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is the overall chain where we run these two chains in sequence.\n",
|
||||
"from langchain.chains import SimpleSequentialChain\n",
|
||||
"overall_chain = SimpleSequentialChain(chains=[synopsis_chain, review_chain], verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "d39e15f5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[36;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"A young couple, John and Mary, are enjoying a day at the beach. As the sun sets, they share a romantic moment. However, their happiness is short-lived, as a tragic accident claims John's life. Mary is left devastated by the loss of her husband.\u001b[0m\n",
|
||||
"\u001b[33;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"review = overall_chain.run(\"Tragedy at sunset on the beach\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "c6649a01",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(review)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c3f1549a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Sequential Chain\n",
|
||||
"Of course, not all sequential chains will be as simple as passing a single string as an argument and getting a single string as output for all steps in the chain. In this next example, we will experiment with more complex chains that involve multiple inputs, and where there also multiple final outputs. \n",
|
||||
"\n",
|
||||
"Of particular importance is how we name the input/output variable names. In the above example we didn't have to think about that because we were just passing the output of one chain directly as input to the next, but here we do have worry about that because we have multiple inputs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "02016a51",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is an LLMChain to write a synopsis given a title of a play and the era it is set in.\n",
|
||||
"llm = OpenAI(temperature=.7)\n",
|
||||
"template = \"\"\"You are a playwright. Given the title of play and the era it is set in, it is your job to write a synopsis for that title.\n",
|
||||
"\n",
|
||||
"Title: {title}\n",
|
||||
"Era: {era}\n",
|
||||
"Playwright: This is a synopsis for the above play:\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"title\", 'era'], template=template)\n",
|
||||
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"synopsis\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "8bd38cc2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is an LLMChain to write a review of a play given a synopsis.\n",
|
||||
"llm = OpenAI(temperature=.7)\n",
|
||||
"template = \"\"\"You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.\n",
|
||||
"\n",
|
||||
"Play Synopsis:\n",
|
||||
"{synopsis}\n",
|
||||
"Review from a New York Times play critic of the above play:\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"synopsis\"], template=template)\n",
|
||||
"review_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"review\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "524523af",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is the overall chain where we run these two chains in sequence.\n",
|
||||
"from langchain.chains import SequentialChain\n",
|
||||
"overall_chain = SequentialChain(\n",
|
||||
" chains=[synopsis_chain, review_chain],\n",
|
||||
" input_variables=[\"era\", \"title\"],\n",
|
||||
" # Here we return multiple variables\n",
|
||||
" output_variables=[\"synopsis\", \"review\"],\n",
|
||||
" verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "3fd3a7be",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[1mChain 0\u001b[0m:\n",
|
||||
"{'synopsis': \"\\n\\nThe play is set in Victorian England and follows the tragic story of a young woman who drowns while swimming at sunset on the beach. Her body is found the next morning by a fisherman who raises the alarm. The young woman's family and friends are devastated by her death and the play ends with their mourning her loss.\"}\n",
|
||||
"\n",
|
||||
"\u001b[1mChain 1\u001b[0m:\n",
|
||||
"{'review': '\\n\\n\"The play is a tragedy, pure and simple. It is the story of a young woman\\'s death, told through the eyes of those who loved her. It is a sad, beautiful play that will stay with you long after you\\'ve seen it. The acting is superb, and the writing is exquisite. If you are looking for a play that will touch your heart and make you think, this is it.\"'}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"review = overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6be70d27",
|
||||
"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": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user