github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 20:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

(WIP) agents (#171)

Browse Source
This commit is contained in:
Harrison Chase
2022-11-22 06:16:26 -08:00
committed by GitHub
parent 22bd12a097
commit d3a7429f61
46 changed files with 1111 additions and 733 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/examples/agents.rst Normal file
View File

@@ -0,0 +1,13 @@
Agents
======
The examples here are all end-to-end agents for specific applications.
.. toctree::
:maxdepth: 1
:glob:
:caption: Agents
agents/mrkl.ipynb
agents/react.ipynb
agents/self_ask_with_search.ipynb

103
docs/examples/demos/mrkl.ipynb → docs/examples/agents/mrkl.ipynb
View File

@@ -7,7 +7,7 @@
"source": [
"# MRKL\n",
"\n",
"This notebook showcases using the MRKL chain to route between tasks"
"This notebook showcases using an agent to replicate the MRKL chain."
]
},
{
@@ -26,13 +26,13 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain import LLMMathChain, OpenAI, SerpAPIChain, MRKLChain, SQLDatabase, SQLDatabaseChain\n",
"from langchain.chains.mrkl.base import ChainConfig"
"from langchain import LLMMathChain, OpenAI, SerpAPIChain, SQLDatabase, SQLDatabaseChain\n",
"from langchain.agents import initialize_agent, Tool"
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 2,
"id": "07e96d99",
"metadata": {},
"outputs": [],
@@ -42,39 +42,38 @@
"llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
"db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
"chains = [\n",
" ChainConfig(\n",
" action_name = \"Search\",\n",
" action=search.run,\n",
" action_description=\"useful for when you need to answer questions about current events\"\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",
" ChainConfig(\n",
" action_name=\"Calculator\",\n",
" action=llm_math_chain.run,\n",
" action_description=\"useful for when you need to answer questions about math\"\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",
" \n",
" ChainConfig(\n",
" action_name=\"FooBar DB\",\n",
" action=db_chain.run,\n",
" action_description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question\"\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\"\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 3,
"id": "a069c4b6",
"metadata": {},
"outputs": [],
"source": [
"mrkl = MRKLChain.from_chains(llm, chains, verbose=True)"
"mrkl = initialize_agent(tools, llm, agent_type=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 4,
"id": "e603cd7d",
"metadata": {},
"outputs": [
@@ -82,38 +81,34 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
"Thought:\u001b[102m I need to find the age of Olivia Wilde's boyfriend\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[104mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[102m I need to find the age of Harry Styles\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[104m28 years\u001b[0m\n",
"Thought:\u001b[102m I need to calculate 28 to the 0.23 power\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[102m\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[103m2.1520202182226886\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[103mAnswer: 2.1520202182226886\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[102m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m"
]
},
{
@@ -122,7 +117,7 @@
"'2.1520202182226886'"
]
},
"execution_count": 6,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -133,7 +128,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 5,
"id": "a5c07010",
"metadata": {},
"outputs": [
@@ -141,41 +136,37 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
"Thought:\u001b[102m I need to find an album called 'The Storm Before the Calm'\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
"Action: Search\n",
"Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
"Observation: \u001b[104mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[102m I need to check if Alanis is in the FooBar database\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Does Alanis Morissette exist in the FooBar database?\n",
"SQLQuery:\u001b[102m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[103m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[102m Yes\u001b[0m\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[101m Yes\u001b[0m\n",
"Thought:\u001b[102m I need to find out what albums of Alanis's are in the FooBar database\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What albums by Alanis Morissette are in the FooBar database?\n",
"SQLQuery:\u001b[102m SELECT Title FROM Album WHERE ArtistId = (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette')\u001b[0m\n",
"SQLResult: \u001b[103m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[102m Jagged Little Pill\u001b[0m\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[101m Jagged Little Pill\u001b[0m\n",
"Thought:\u001b[102m I now know the final answer\n",
"Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m"
]
},
{
@@ -184,7 +175,7 @@
"'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
]
},
"execution_count": 10,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}

0
docs/examples/demos/natbot.py → docs/examples/agents/natbot.py
View File

89
docs/examples/agents/react.ipynb Normal file
View File

@@ -0,0 +1,89 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "82140df0",
"metadata": {},
"source": [
"# ReAct\n",
"\n",
"This notebook showcases using an agent to implement the ReAct logic."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "4e272b47",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, Wikipedia\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.agents.react.base import DocstoreExplorer\n",
"docstore=DocstoreExplorer(Wikipedia())\n",
"tools = [\n",
" Tool(\n",
" name=\"Search\",\n",
" func=docstore.search\n",
" ),\n",
" Tool(\n",
" name=\"Lookup\",\n",
" func=docstore.lookup\n",
" )\n",
"]\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"react = initialize_agent(tools, llm, agent_type=\"react-docstore\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8078c8f1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
"Thought 1:"
]
}
],
"source": [
"question = \"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\"\n",
"react.run(question)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ff64e81",
"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
}

27
docs/examples/demos/self_ask_with_search.ipynb → docs/examples/agents/self_ask_with_search.ipynb
View File

@@ -20,23 +20,19 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[102m Yes.\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[103mCarlos Alcaraz won the 2022 Men's single title while Poland's Iga Swiatek won the Women's single title defeating Tunisian's Ons Jabeur..\u001b[0m\u001b[102m\n",
"Follow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[103mEl Palmar, Murcia, Spain.\u001b[0m\u001b[102m\n",
"So the final answer is: El Palmar, Murcia, Spain\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"Intermediate answer: \u001b[36;1m\u001b[1;3mCarlos Alcaraz\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mEl Palmar, Spain\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the final answer is: El Palmar, Spain\u001b[0m"
]
},
{
"data": {
"text/plain": [
"'\\nSo the final answer is: El Palmar, Murcia, Spain'"
"'El Palmar, Spain'"
]
},
"execution_count": 1,
@@ -45,12 +41,19 @@
}
],
"source": [
"from langchain import SelfAskWithSearchChain, OpenAI, SerpAPIChain\n",
"from langchain import OpenAI, SerpAPIChain\n",
"from langchain.agents import initialize_agent, Tool\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"search = SerpAPIChain()\n",
"tools = [\n",
" Tool(\n",
" name=\"Intermediate Answer\",\n",
" func=search.run\n",
" )\n",
"]\n",
"\n",
"self_ask_with_search = SelfAskWithSearchChain(llm=llm, search_chain=search, verbose=True)\n",
"self_ask_with_search = initialize_agent(tools, llm, agent_type=\"self-ask-with-search\", verbose=True)\n",
"\n",
"self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
]

15
docs/examples/chains.rst Normal file
View File

@@ -0,0 +1,15 @@
Chains
======
The examples here are all end-to-end chains for specific applications.
.. toctree::
:maxdepth: 1
:glob:
:caption: Chains
chains/llm_chain.ipynb
chains/llm_math.ipynb
chains/map_reduce.ipynb
chains/sqlite.ipynb
chains/vector_db_qa.ipynb

6
docs/examples/demos/simple_prompts.ipynb → docs/examples/chains/llm_chain.ipynb
View File

@@ -5,9 +5,9 @@
"id": "d8a5c5d4",
"metadata": {},
"source": [
"# Simple Example\n",
"# LLM Chain\n",
"\n",
"This notebook showcases a simple chain."
"This notebook showcases a simple LLM chain."
]
},
{
@@ -81,7 +81,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.7"
"version": "3.7.6"
}
},
"nbformat": 4,

0
docs/examples/demos/llm_math.ipynb → docs/examples/chains/llm_math.ipynb
View File

0
docs/examples/demos/map reduce.ipynb → docs/examples/chains/map_reduce.ipynb
View File

0
docs/examples/demos/sqlite.ipynb → docs/examples/chains/sqlite.ipynb
View File

0
docs/examples/demos/vector_db_qa.ipynb → docs/examples/chains/vector_db_qa.ipynb
View File

10
docs/examples/demos.rst
View File

@@ -1,10 +0,0 @@
Demos
=====
The examples here are all end-to-end chains of specific applications.
.. toctree::
:maxdepth: 1
:glob:
demos/*

98
docs/examples/demos/react.ipynb
View File

@@ -1,98 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "82140df0",
"metadata": {},
"source": [
"# ReAct\n",
"\n",
"This notebook showcases the implementation of the ReAct chain logic."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "4e272b47",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, ReActChain, Wikipedia\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"react = ReActChain(llm=llm, docstore=Wikipedia(), verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8078c8f1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
"Thought 1:\u001b[102m I need to search David Chanoff and find the U.S. Navy admiral he\n",
"collaborated with.\n",
"Action 1: Search[David Chanoff]\u001b[0m\n",
"Observation 1: \u001b[103mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
"Thought 2:\u001b[102m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
"Action 2: Search[William J. Crowe]\u001b[0m\n",
"Observation 2: \u001b[103mWilliam James Crowe Jr. (January 2, 1925 – October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
"Thought 3:\u001b[102m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton. So the answer is Bill Clinton.\n",
"Action 3: Finish[Bill Clinton]\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Bill Clinton'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"question = \"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\"\n",
"react.run(question)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0a6bd3b4",
"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
}

28
docs/explanation/agents.md Normal file
View File

@@ -0,0 +1,28 @@
# Agents
Agents use an LLM to determine which tools to call and in what order.
Here are the supported types of agents available in LangChain.
For a tutorial on how to load agents, see [here](/getting_started/agents.ipynb).
### `zero-shot-react-description`
This agent uses the ReAct framework to determine which tool to use
based solely on the tool's description. Any number of tools can be provided.
This agent requires that a description is provided for each tool.
### `react-docstore`
This agent uses the ReAct framework to interact with a docstore. Two tools must
be provided: a `Search` tool and a `Lookup` tool (they must be named exactly as so).
The `Search` tool should search for a document, while the `Lookup` tool should lookup
a term in the most recently found document.
This agent is equivalent to the
original [ReAct paper](https://arxiv.org/pdf/2210.03629.pdf), specifically the Wikipedia example.
### `self-ask-with-search`
This agent utilizes a single tool that should be named `Intermediate Answer`.
This tool should be able to lookup factual answers to questions. This agent
is equivalent to the original [self ask with search paper](https://ofir.io/self-ask.pdf),
where a Google search API was provided as the tool.

4
docs/explanation/core_concepts.md
View File

@@ -25,3 +25,7 @@ These are datastores that store documents. They expose a method for passing in a
## Chains
These are pipelines that combine multiple of the above ideas.
They vary greatly in complexity and are combination of generic, highly configurable pipelines and more narrow (but usually more complex) pipelines.
## Agents
As opposed to a chain, whether the steps to be taken are known ahead of time, agents
use an LLM to determine which tools to call and in what order.

4
docs/explanation/glossary.md
View File

@@ -29,7 +29,7 @@ This induces the to model to think about what action to take, then take it.
Resources:
- [Paper](https://arxiv.org/pdf/2210.03629.pdf)
- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/examples/react.ipynb)
- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/docs/examples/agents/react.ipynb)
### Self-ask
@@ -38,7 +38,7 @@ In this method, the model explicitly asks itself follow-up questions, which are
Resources:
- [Paper](https://ofir.io/self-ask.pdf)
- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/examples/self_ask_with_search.ipynb)
- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/docs/examples/agents/self_ask_with_search.ipynb)
### Prompt Chaining

192
docs/getting_started/agents.ipynb Normal file
View 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
}

8
docs/getting_started/chains.md → docs/getting_started/llm_chain.md
View File

@@ -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.

0
docs/examples/demos/sequential_chains.ipynb → docs/getting_started/sequential_chains.ipynb
View File

82
docs/index.rst
View File

@@ -8,12 +8,75 @@ create a truly powerful app - the real power comes when you are able to
combine them with other sources of computation or knowledge.
This library is aimed at assisting in the development of those types of applications.
It aims to create:
1. a comprehensive collection of pieces you would ever want to combine
2. a flexible interface for combining pieces into a single comprehensive "chain"
3. a schema for easily saving and sharing those chains
There are three main areas (with a forth coming soon) that LangChain is designed to help with.
These are, in increasing order of complexity:
1. LLM and Prompts
2. Chains
3. Agents
4. (Coming Soon) Memory
Let's go through these categories and for each one identify key concepts (to clarify terminology) as well as the problems in this area LangChain helps solve.
**LLMs and Prompts**
Calling out to an LLM once is pretty easy, with most of them being behind well documented APIs.
However, there are still some challenges going from that to an application running in production that LangChain attempts to address.
*Key Concepts*
- LLM: A large language model, in particular a text-to-text model.
- Prompt: The input to a language model. Typically this is not simply a hardcoded string but rather a combination of a template, some examples, and user input.
- Prompt Template: An object responsible for constructing the final prompt to pass to a LLM.
*Problems solved*
- Switching costs: by exposing a standard interface for all the top LLM providers, LangChain makes it easy to switch from one provider to another, whether it be for production use cases or just for testing stuff out.
- Prompt management: managing your prompts is easy when you only have one simple one, but can get tricky when you have a bunch or when they start to get more complex. LangChain provides a standard way for storing, constructing, and referencing prompts.
- Prompt optimization: despite the underlying models getting better and better, there is still currently a need for carefully constructing prompts.
**Chains**
Using an LLM in isolation is fine for some simple applications, but many more complex ones require chaining LLMs - either with eachother or with other experts.
LangChain provides several parts to help with that.
*Key Concepts*
- Tools: APIs designed for assisting with a particular use case (search, databases, Python REPL, etc). Prompt templates, LLMs, and chains can also be considered tools.
- Chains: A combination of multiple tools in a deterministic manner.
*Problems solved*
- Standard interface for working with Chains
- Easy way to construct chains of LLMs
- Lots of integrations with other tools that you may want to use in conjunction with LLMs
- End-to-end chains for common workflows (database question/answer, recursive summarization, etc)
**Agents**
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” 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.
*Key Concepts*
- Tools: same as above.
- Agent: An LLM-powered class responsible for determining which tools to use and in what order.
*Problems solved*
- Standard agent interfaces
- A selection of powerful agents to choose from
- Common chains that can be used as tools
**Memory**
Coming soon.
Documentation Structure
=======================
The documentation is structured into the following sections:
@@ -25,7 +88,9 @@ The documentation is structured into the following sections:
getting_started/installation.md
getting_started/environment.md
getting_started/llm.md
getting_started/chains.md
getting_started/llm_chain.md
getting_started/sequential_chains.md
getting_started/agents.ipynb
Goes over a simple walk through and tutorial for getting started setting up a simple chain that generates a company name based on what the company makes.
Covers installation, environment set up, calling LLMs, and using prompts.
@@ -37,9 +102,10 @@ Start here if you haven't used LangChain before.
:caption: How-To Examples
:name: examples
examples/demos.rst
examples/integrations.rst
examples/prompts.rst
examples/integrations.rst
examples/chains.rst
examples/agents.rst
examples/model_laboratory.ipynb
More elaborate examples and walk-throughs of particular
@@ -62,6 +128,7 @@ common tasks or cool demos.
modules/text_splitter
modules/vectorstore
modules/chains
modules/agents
Full API documentation. This is the place to look if you want to
@@ -74,6 +141,7 @@ see detailed information about the various classes, methods, and APIs.
:name: resources
explanation/core_concepts.md
explanation/agents.md
explanation/glossary.md
Discord <https://discord.gg/6adMQxSpJS>

7
docs/modules/agents.rst Normal file
View File

@@ -0,0 +1,7 @@
:mod:`langchain.agents`
===============================
.. automodule:: langchain.agents
:members:
:undoc-members: