mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-23 11:30:37 +00:00
(WIP) agents (#171)
This commit is contained in:
Harrison Chase
GitHub
13
docs/examples/agents.rst
Normal file
13
docs/examples/agents.rst
Normal 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
|
||||
@@ -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"
|
||||
}
|
||||
89
docs/examples/agents/react.ipynb
Normal file
89
docs/examples/agents/react.ipynb
Normal 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
|
||||
}
|
||||
@@ -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
15
docs/examples/chains.rst
Normal 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
|
||||
@@ -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,
|
||||
@@ -1,10 +0,0 @@
|
||||
Demos
|
||||
=====
|
||||
|
||||
The examples here are all end-to-end chains of specific applications.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
|
||||
demos/*
|
||||
@@ -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
|
||||
}
|
||||
@@ -1,265 +0,0 @@
|
||||
{
|
||||
"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