github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-01 19:12:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Start cookbook and move stuff from use cases (#11636)

Browse Source
This commit is contained in:
Bagatur
2023-10-11 12:27:13 -07:00
committed by GitHub
parent 99adcdb1c9
commit cf86447623
98 changed files with 522 additions and 2126 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
cookbook/autogpt/autogpt.ipynb Normal file
View File

@@ -0,0 +1,212 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "14f8b67b",
"metadata": {},
"source": [
"# AutoGPT\n",
"\n",
"Implementation of https://github.com/Significant-Gravitas/Auto-GPT but with LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)"
]
},
{
"cell_type": "markdown",
"id": "192496a7",
"metadata": {},
"source": [
"## Set up tools\n",
"\n",
"We'll set up an AutoGPT with a search tool, and write-file tool, and a read-file tool"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7c2c9b54",
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities import SerpAPIWrapper\n",
"from langchain.agents import Tool\n",
"from langchain.tools.file_management.write import WriteFileTool\n",
"from langchain.tools.file_management.read import ReadFileTool\n",
"\n",
"search = SerpAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name=\"search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
" ),\n",
" WriteFileTool(),\n",
" ReadFileTool(),\n",
"]"
]
},
{
"cell_type": "markdown",
"id": "8e39ee28",
"metadata": {},
"source": [
"## Set up memory\n",
"\n",
"The memory here is used for the agents intermediate steps"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "72bc204d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain.docstore import InMemoryDocstore\n",
"from langchain.embeddings import OpenAIEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "1df7b724",
"metadata": {},
"outputs": [],
"source": [
"# Define your embedding model\n",
"embeddings_model = OpenAIEmbeddings()\n",
"# Initialize the vectorstore as empty\n",
"import faiss\n",
"\n",
"embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
]
},
{
"cell_type": "markdown",
"id": "e40fd657",
"metadata": {},
"source": [
"## Setup model and AutoGPT\n",
"\n",
"Initialize everything! We will use ChatOpenAI model"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3393bc23",
"metadata": {},
"outputs": [],
"source": [
"from langchain_experimental.autonomous_agents import AutoGPT\n",
"from langchain.chat_models import ChatOpenAI"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "709c08c2",
"metadata": {},
"outputs": [],
"source": [
"agent = AutoGPT.from_llm_and_tools(\n",
" ai_name=\"Tom\",\n",
" ai_role=\"Assistant\",\n",
" tools=tools,\n",
" llm=ChatOpenAI(temperature=0),\n",
" memory=vectorstore.as_retriever(),\n",
")\n",
"# Set verbose to be true\n",
"agent.chain.verbose = True"
]
},
{
"cell_type": "markdown",
"id": "f0f208d9",
"metadata": {
"collapsed": false
},
"source": [
"## Run an example\n",
"\n",
"Here we will make it write a weather report for SF"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d119d788",
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"agent.run([\"write a weather report for SF today\"])"
]
},
{
"cell_type": "markdown",
"id": "f13f8322",
"metadata": {
"collapsed": false
},
"source": [
"## Chat History Memory\n",
"\n",
"In addition to the memory that holds the agent immediate steps, we also have a chat history memory. By default, the agent will use 'ChatMessageHistory' and it can be changed. This is useful when you want to use a different type of memory for example 'FileChatHistoryMemory'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2a81f5ad",
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from langchain.memory.chat_message_histories import FileChatMessageHistory\n",
"\n",
"agent = AutoGPT.from_llm_and_tools(\n",
" ai_name=\"Tom\",\n",
" ai_role=\"Assistant\",\n",
" tools=tools,\n",
" llm=ChatOpenAI(temperature=0),\n",
" memory=vectorstore.as_retriever(),\n",
" chat_history_memory=FileChatMessageHistory(\"chat_history.txt\"),\n",
")"
]
},
{
"cell_type": "markdown",
"id": "b1403008",
"metadata": {
"collapsed": false
},
"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
}

649
cookbook/autogpt/marathon_times.ipynb Normal file
View File

@@ -0,0 +1,649 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "14f8b67b",
"metadata": {},
"source": [
"## AutoGPT example finding Winning Marathon Times\n",
"\n",
"* Implementation of https://github.com/Significant-Gravitas/Auto-GPT \n",
"* With LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ef972313-c05a-4c49-8fd1-03e599e21033",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# !pip install bs4\n",
"# !pip install nest_asyncio"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1cff42fd",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# General\n",
"import os\n",
"import pandas as pd\n",
"from langchain_experimental.autonomous_agents import AutoGPT\n",
"from langchain.chat_models import ChatOpenAI\n",
"\n",
"from langchain.agents.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
"from langchain.docstore.document import Document\n",
"import asyncio\n",
"import nest_asyncio\n",
"\n",
"\n",
"# Needed synce jupyter runs an async eventloop\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "01283ac7-1da0-41ba-8011-bd455d21dd82",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
]
},
{
"cell_type": "markdown",
"id": "192496a7",
"metadata": {},
"source": [
"### Set up tools\n",
"\n",
"* We'll set up an AutoGPT with a `search` tool, and `write-file` tool, and a `read-file` tool, a web browsing tool, and a tool to interact with a CSV file via a python REPL"
]
},
{
"cell_type": "markdown",
"id": "708a426f",
"metadata": {},
"source": [
"Define any other `tools` you want to use below:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cef4c150-0ef1-4a33-836b-01062fec134e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Tools\n",
"import os\n",
"from contextlib import contextmanager\n",
"from typing import Optional\n",
"from langchain.agents import tool\n",
"from langchain.tools.file_management.read import ReadFileTool\n",
"from langchain.tools.file_management.write import WriteFileTool\n",
"\n",
"ROOT_DIR = \"./data/\"\n",
"\n",
"\n",
"@contextmanager\n",
"def pushd(new_dir):\n",
" \"\"\"Context manager for changing the current working directory.\"\"\"\n",
" prev_dir = os.getcwd()\n",
" os.chdir(new_dir)\n",
" try:\n",
" yield\n",
" finally:\n",
" os.chdir(prev_dir)\n",
"\n",
"\n",
"@tool\n",
"def process_csv(\n",
" csv_file_path: str, instructions: str, output_path: Optional[str] = None\n",
") -> str:\n",
" \"\"\"Process a CSV by with pandas in a limited REPL.\\\n",
" Only use this after writing data to disk as a csv file.\\\n",
" Any figures must be saved to disk to be viewed by the human.\\\n",
" Instructions should be written in natural language, not code. Assume the dataframe is already loaded.\"\"\"\n",
" with pushd(ROOT_DIR):\n",
" try:\n",
" df = pd.read_csv(csv_file_path)\n",
" except Exception as e:\n",
" return f\"Error: {e}\"\n",
" agent = create_pandas_dataframe_agent(llm, df, max_iterations=30, verbose=True)\n",
" if output_path is not None:\n",
" instructions += f\" Save output to disk at {output_path}\"\n",
" try:\n",
" result = agent.run(instructions)\n",
" return result\n",
" except Exception as e:\n",
" return f\"Error: {e}\""
]
},
{
"cell_type": "markdown",
"id": "69975008-654a-4cbb-bdf6-63c8bae07eaa",
"metadata": {
"tags": []
},
"source": [
"**Browse a web page with PlayWright**"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "6bb5e47b-0f54-4faa-ae42-49a28fa5497b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# !pip install playwright\n",
"# !playwright install"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "26b497d7-8e52-4c7f-8e7e-da0a48820a3c",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"async def async_load_playwright(url: str) -> str:\n",
" \"\"\"Load the specified URLs using Playwright and parse using BeautifulSoup.\"\"\"\n",
" from bs4 import BeautifulSoup\n",
" from playwright.async_api import async_playwright\n",
"\n",
" results = \"\"\n",
" async with async_playwright() as p:\n",
" browser = await p.chromium.launch(headless=True)\n",
" try:\n",
" page = await browser.new_page()\n",
" await page.goto(url)\n",
"\n",
" page_source = await page.content()\n",
" soup = BeautifulSoup(page_source, \"html.parser\")\n",
"\n",
" for script in soup([\"script\", \"style\"]):\n",
" script.extract()\n",
"\n",
" text = soup.get_text()\n",
" lines = (line.strip() for line in text.splitlines())\n",
" chunks = (phrase.strip() for line in lines for phrase in line.split(\" \"))\n",
" results = \"\\n\".join(chunk for chunk in chunks if chunk)\n",
" except Exception as e:\n",
" results = f\"Error: {e}\"\n",
" await browser.close()\n",
" return results\n",
"\n",
"\n",
"def run_async(coro):\n",
" event_loop = asyncio.get_event_loop()\n",
" return event_loop.run_until_complete(coro)\n",
"\n",
"\n",
"@tool\n",
"def browse_web_page(url: str) -> str:\n",
" \"\"\"Verbose way to scrape a whole webpage. Likely to cause issues parsing.\"\"\"\n",
" return run_async(async_load_playwright(url))"
]
},
{
"cell_type": "markdown",
"id": "5ea71762-67ca-4e75-8c4d-00563064be71",
"metadata": {},
"source": [
"**Q&A Over a webpage**\n",
"\n",
"Help the model ask more directed questions of web pages to avoid cluttering its memory"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1842929d-f18d-4edc-9fdd-82c929181141",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"\n",
"from pydantic import Field\n",
"from langchain.chains.qa_with_sources.loading import (\n",
" load_qa_with_sources_chain,\n",
" BaseCombineDocumentsChain,\n",
")\n",
"\n",
"\n",
"def _get_text_splitter():\n",
" return RecursiveCharacterTextSplitter(\n",
" # Set a really small chunk size, just to show.\n",
" chunk_size=500,\n",
" chunk_overlap=20,\n",
" length_function=len,\n",
" )\n",
"\n",
"\n",
"class WebpageQATool(BaseTool):\n",
" name = \"query_webpage\"\n",
" description = (\n",
" \"Browse a webpage and retrieve the information relevant to the question.\"\n",
" )\n",
" text_splitter: RecursiveCharacterTextSplitter = Field(\n",
" default_factory=_get_text_splitter\n",
" )\n",
" qa_chain: BaseCombineDocumentsChain\n",
"\n",
" def _run(self, url: str, question: str) -> str:\n",
" \"\"\"Useful for browsing websites and scraping the text information.\"\"\"\n",
" result = browse_web_page.run(url)\n",
" docs = [Document(page_content=result, metadata={\"source\": url})]\n",
" web_docs = self.text_splitter.split_documents(docs)\n",
" results = []\n",
" # TODO: Handle this with a MapReduceChain\n",
" for i in range(0, len(web_docs), 4):\n",
" input_docs = web_docs[i : i + 4]\n",
" window_result = self.qa_chain(\n",
" {\"input_documents\": input_docs, \"question\": question},\n",
" return_only_outputs=True,\n",
" )\n",
" results.append(f\"Response from window {i} - {window_result}\")\n",
" results_docs = [\n",
" Document(page_content=\"\\n\".join(results), metadata={\"source\": url})\n",
" ]\n",
" return self.qa_chain(\n",
" {\"input_documents\": results_docs, \"question\": question},\n",
" return_only_outputs=True,\n",
" )\n",
"\n",
" async def _arun(self, url: str, question: str) -> str:\n",
" raise NotImplementedError"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "e6f72bd0",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"query_website_tool = WebpageQATool(qa_chain=load_qa_with_sources_chain(llm))"
]
},
{
"cell_type": "markdown",
"id": "8e39ee28",
"metadata": {},
"source": [
"### Set up memory\n",
"\n",
"* The memory here is used for the agents intermediate steps"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "1df7b724",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Memory\n",
"import faiss\n",
"from langchain.vectorstores import FAISS\n",
"from langchain.docstore import InMemoryDocstore\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.tools.human.tool import HumanInputRun\n",
"\n",
"embeddings_model = OpenAIEmbeddings()\n",
"embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
]
},
{
"cell_type": "markdown",
"id": "e40fd657",
"metadata": {},
"source": [
"### Setup model and AutoGPT\n",
"\n",
"`Model set-up`"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "1233caf3-fbc9-4acb-9faa-01008200633d",
"metadata": {},
"outputs": [],
"source": [
"# !pip install duckduckgo_search\n",
"web_search = DuckDuckGoSearchRun()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "88c8b184-67d7-4c35-84ae-9b14bef8c4e3",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"tools = [\n",
" web_search,\n",
" WriteFileTool(root_dir=\"./data\"),\n",
" ReadFileTool(root_dir=\"./data\"),\n",
" process_csv,\n",
" query_website_tool,\n",
" # HumanInputRun(), # Activate if you want the permit asking for help from the human\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "709c08c2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"agent = AutoGPT.from_llm_and_tools(\n",
" ai_name=\"Tom\",\n",
" ai_role=\"Assistant\",\n",
" tools=tools,\n",
" llm=llm,\n",
" memory=vectorstore.as_retriever(search_kwargs={\"k\": 8}),\n",
" # human_in_the_loop=True, # Set to True if you want to add feedback at each step.\n",
")\n",
"# agent.chain.verbose = True"
]
},
{
"cell_type": "markdown",
"id": "fc9b51ba",
"metadata": {},
"source": [
"### AutoGPT for Querying the Web\n",
" \n",
" \n",
"I've spent a lot of time over the years crawling data sources and cleaning data. Let's see if AutoGPT can help with this!\n",
"\n",
"Here is the prompt for looking up recent boston marathon times and converting them to tabular form."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "64455d70-a134-4d11-826a-33e34c2ce287",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I need to find the winning Boston Marathon times for the past 5 years. I can use the DuckDuckGo Search command to search for this information.\",\n",
" \"reasoning\": \"Using DuckDuckGo Search will help me gather information on the winning times without complications.\",\n",
" \"plan\": \"- Use DuckDuckGo Search to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will use the DuckDuckGo Search command to find the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"DuckDuckGo Search\",\n",
" \"args\": {\n",
" \"query\": \"winning Boston Marathon times for the past 5 years ending in 2022\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"The DuckDuckGo Search command did not provide the specific information I need. I must switch my approach and use query_webpage command to browse a webpage containing the Boston Marathon winning times for the past 5 years.\",\n",
" \"reasoning\": \"The query_webpage command may give me more accurate and comprehensive results compared to the search command.\",\n",
" \"plan\": \"- Use query_webpage command to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
" \"criticism\": \"I may face difficulty in finding the right webpage with the desired information.\",\n",
" \"speak\": \"I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"DuckDuckGo Search\",\n",
" \"args\": {\n",
" \"query\": \"site with winning Boston Marathon times for the past 5 years ending in 2022\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.\",\n",
" \"reasoning\": \"The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more accurate and comprehensive results.\",\n",
" \"plan\": \"- Use query_webpage command to find the winning Boston Marathon times\\\\n- Generate a table with the year, name, country of origin, and times\\\\n- Ensure there are no legal complications\",\n",
" \"criticism\": \"I may face difficulty in finding the right webpage with the desired information.\",\n",
" \"speak\": \"I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"query_webpage\",\n",
" \"args\": {\n",
" \"url\": \"https://en.wikipedia.org/wiki/List_of_winners_of_the_Boston_Marathon\",\n",
" \"question\": \"What were the winning Boston Marathon times for the past 5 years ending in 2022?\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I have already found the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the information.\",\n",
" \"reasoning\": \"Using the information I already have, I can create a table containing year, name, country of origin, and times.\",\n",
" \"plan\": \"- Write the marathon data to a CSV file\\n- Process the CSV file to display the table\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"write_file\",\n",
" \"args\": {\n",
" \"file_path\": \"boston_marathon_winners.csv\",\n",
" \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,KEN,2:06:51\\n2021,Benson Kipruto,KEN,2:09:51\\n2019,Lawrence Cherono,KEN,2:07:57\\n2018,Yuki Kawauchi,JPN,2:15:58\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I have retrieved the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the year, name, country of origin, and times.\",\n",
" \"reasoning\": \"Creating a table will help organize the data in a clear and accessible format.\",\n",
" \"plan\": \"- Write the data to a CSV file\\n- Process the CSV file to generate the table\\n- Complete the task\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will generate a table with the year, name, country of origin, and winning times using the recently retrieved data.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"write_file\",\n",
" \"args\": {\n",
" \"file_path\": \"winning_boston_marathon_data.csv\",\n",
" \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,KEN,2:06:51\\n2021,Benson Kipruto,KEN,2:09:51\\n2019,Lawrence Cherono,KEN,2:07:57\\n2018,Yuki Kawauchi,JPN,2:15:58\\n\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I have found the winning Boston Marathon times for the past five years ending in 2022. Next, I need to create a table with the year, name, country of origin, and times.\",\n",
" \"reasoning\": \"Generating a table will help organize the information in a structured format.\",\n",
" \"plan\": \"- Create a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will generate a table with the winning Boston Marathon times for the past 5 years ending in 2022.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"write_file\",\n",
" \"args\": {\n",
" \"file_path\": \"winning_times.csv\",\n",
" \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,Kenya,2:06:51\\n2021,Benson Kipruto,Kenya,2:09:51\\n2020,Canceled due to COVID-19 pandemic,,\\n2019,Lawrence Cherono,Kenya,2:07:57\\n2018,Yuki Kawauchi,Japan,2:15:58\"\n",
" }\n",
" }\n",
"}\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I need to process the CSV file to generate the table with the year, name, country of origin, and winning times.\",\n",
" \"reasoning\": \"I have already written the data to a file named 'winning_times.csv'. Now, I need to process this CSV file to properly display the data as a table.\",\n",
" \"plan\": \"- Use the process_csv command to read the 'winning_times.csv' file and generate the table\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"process_csv\",\n",
" \"args\": {\n",
" \"csv_file_path\": \"winning_times.csv\",\n",
" \"instructions\": \"Read the CSV file and display the data as a table\"\n",
" }\n",
" }\n",
"}\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: The CSV file has already been read and saved into a pandas dataframe called `df`. Hence, I can simply display the data by printing the whole dataframe. Since `df.head()` returns the first 5 rows, I can use that to showcase the contents.\n",
"\n",
"Action: python_repl_ast\n",
"Action Input: print(df.head())\u001b[0m Year Name Country Time\n",
"0 2022 Evans Chebet Kenya 2:06:51\n",
"1 2021 Benson Kipruto Kenya 2:09:51\n",
"2 2020 Canceled due to COVID-19 pandemic NaN NaN\n",
"3 2019 Lawrence Cherono Kenya 2:07:57\n",
"4 2018 Yuki Kawauchi Japan 2:15:58\n",
"\n",
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI used the wrong tool to perform the action. I should have used the given data and not interacted with the Python shell. I can now provide the displayed data as the answer since the information in the printed dataframe would look like a table when typed as text.\n",
"\n",
"Final Answer: \n",
" Year Name Country Time\n",
"0 2022 Evans Chebet Kenya 2:06:51\n",
"1 2021 Benson Kipruto Kenya 2:09:51\n",
"2 2020 Canceled due to COVID-19 pandemic NaN NaN\n",
"3 2019 Lawrence Cherono Kenya 2:07:57\n",
"4 2018 Yuki Kawauchi Japan 2:15:58\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I already have the winning Boston Marathon times for the past 5 years saved in the file 'winning_times.csv'. Now, I need to process the CSV and display the table.\",\n",
" \"reasoning\": \"I am choosing the process_csv command because I already have the required data saved as a CSV file, and I can use this command to read and display the data as a table.\",\n",
" \"plan\": \"- Use the process_csv command to read the 'winning_times.csv' file and generate the table\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"process_csv\",\n",
" \"args\": {\n",
" \"csv_file_path\": \"winning_times.csv\",\n",
" \"instructions\": \"Read the CSV file and display the data as a table\"\n",
" }\n",
" }\n",
"}\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: Since the data is already loaded in a pandas dataframe, I just need to display the top rows of the dataframe.\n",
"Action: python_repl_ast\n",
"Action Input: df.head()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Year Name Country Time\n",
"0 2022 Evans Chebet Kenya 2:06:51\n",
"1 2021 Benson Kipruto Kenya 2:09:51\n",
"2 2020 Canceled due to COVID-19 pandemic NaN NaN\n",
"3 2019 Lawrence Cherono Kenya 2:07:57\n",
"4 2018 Yuki Kawauchi Japan 2:15:58\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
"Final Answer: \n",
" Year Name Country Time\n",
"0 2022 Evans Chebet Kenya 2:06:51\n",
"1 2021 Benson Kipruto Kenya 2:09:51\n",
"2 2020 Canceled due to COVID-19 pandemic NaN NaN\n",
"3 2019 Lawrence Cherono Kenya 2:07:57\n",
"4 2018 Yuki Kawauchi Japan 2:15:58\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"{\n",
" \"thoughts\": {\n",
" \"text\": \"I have already generated a table with the winning Boston Marathon times for the past 5 years. Now, I can finish the task.\",\n",
" \"reasoning\": \"I have completed the required actions and obtained the desired data. The task is complete.\",\n",
" \"plan\": \"- Use the finish command\",\n",
" \"criticism\": \"None\",\n",
" \"speak\": \"I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.\"\n",
" },\n",
" \"command\": {\n",
" \"name\": \"finish\",\n",
" \"args\": {\n",
" \"response\": \"I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.\"\n",
" }\n",
" }\n",
"}\n"
]
},
{
"data": {
"text/plain": [
"'I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.'"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\n",
" [\n",
" \"What were the winning boston marathon times for the past 5 years (ending in 2022)? Generate a table of the year, name, country of origin, and times.\"\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a6b4f96e",
"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": "3.8.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

257
cookbook/baby_agi.ipynb Normal file
View File

@@ -0,0 +1,257 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "517a9fd4",
"metadata": {},
"source": [
"# BabyAGI User Guide\n",
"\n",
"This notebook demonstrates how to implement [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima). BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.\n",
"\n",
"This guide will help you understand the components to create your own recursive agents.\n",
"\n",
"Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free)."
]
},
{
"cell_type": "markdown",
"id": "556af556",
"metadata": {},
"source": [
"## Install and Import Required Modules"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "c8a354b6",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from collections import deque\n",
"from typing import Dict, List, Optional, Any\n",
"\n",
"from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.llms import BaseLLM\n",
"from langchain.schema.vectorstore import VectorStore\n",
"from pydantic import BaseModel, Field\n",
"from langchain.chains.base import Chain\n",
"from langchain_experimental.autonomous_agents import BabyAGI"
]
},
{
"cell_type": "markdown",
"id": "09f70772",
"metadata": {},
"source": [
"## Connect to the Vector Store\n",
"\n",
"Depending on what vectorstore you use, this step may look different."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "794045d4",
"metadata": {},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain.docstore import InMemoryDocstore"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "6e0305eb",
"metadata": {},
"outputs": [],
"source": [
"# Define your embedding model\n",
"embeddings_model = OpenAIEmbeddings()\n",
"# Initialize the vectorstore as empty\n",
"import faiss\n",
"\n",
"embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
]
},
{
"cell_type": "markdown",
"id": "05ba762e",
"metadata": {},
"source": [
"### Run the BabyAGI\n",
"\n",
"Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3d220b69",
"metadata": {},
"outputs": [],
"source": [
"OBJECTIVE = \"Write a weather report for SF today\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "8a8e5543",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3d69899b",
"metadata": {},
"outputs": [],
"source": [
"# Logging of LLMChains\n",
"verbose = False\n",
"# If None, will keep on going forever\n",
"max_iterations: Optional[int] = 3\n",
"baby_agi = BabyAGI.from_llm(\n",
" llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f7957b51",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"1: Make a todo list\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"1: Make a todo list\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"\n",
"\n",
"1. Check the weather forecast for San Francisco today\n",
"2. Make note of the temperature, humidity, wind speed, and other relevant weather conditions\n",
"3. Write a weather report summarizing the forecast\n",
"4. Check for any weather alerts or warnings\n",
"5. Share the report with the relevant stakeholders\n",
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"2: Check the current temperature in San Francisco\n",
"3: Check the current humidity in San Francisco\n",
"4: Check the current wind speed in San Francisco\n",
"5: Check for any weather alerts or warnings in San Francisco\n",
"6: Check the forecast for the next 24 hours in San Francisco\n",
"7: Check the forecast for the next 48 hours in San Francisco\n",
"8: Check the forecast for the next 72 hours in San Francisco\n",
"9: Check the forecast for the next week in San Francisco\n",
"10: Check the forecast for the next month in San Francisco\n",
"11: Check the forecast for the next 3 months in San Francisco\n",
"1: Write a weather report for SF today\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"2: Check the current temperature in San Francisco\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"\n",
"\n",
"I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.\n",
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"3: Check the current UV index in San Francisco.\n",
"4: Check the current air quality in San Francisco.\n",
"5: Check the current precipitation levels in San Francisco.\n",
"6: Check the current cloud cover in San Francisco.\n",
"7: Check the current barometric pressure in San Francisco.\n",
"8: Check the current dew point in San Francisco.\n",
"9: Check the current wind direction in San Francisco.\n",
"10: Check the current humidity levels in San Francisco.\n",
"1: Check the current temperature in San Francisco to the average temperature for this time of year.\n",
"2: Check the current visibility in San Francisco.\n",
"11: Write a weather report for SF today.\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"3: Check the current UV index in San Francisco.\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"\n",
"\n",
"The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear sunscreen and protective clothing when outdoors.\n",
"\u001b[91m\u001b[1m\n",
"*****TASK ENDING*****\n",
"\u001b[0m\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'objective': 'Write a weather report for SF today'}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"baby_agi({\"objective\": OBJECTIVE})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "898a210b",
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

391
cookbook/baby_agi_with_agent.ipynb Normal file
View File

@@ -0,0 +1,391 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "517a9fd4",
"metadata": {},
"source": [
"# BabyAGI with Tools\n",
"\n",
"This notebook builds on top of [baby agi](baby_agi.html), but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information"
]
},
{
"cell_type": "markdown",
"id": "556af556",
"metadata": {},
"source": [
"## Install and Import Required Modules"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "c8a354b6",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from collections import deque\n",
"from typing import Dict, List, Optional, Any\n",
"\n",
"from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.llms import BaseLLM\n",
"from langchain.schema.vectorstore import VectorStore\n",
"from pydantic import BaseModel, Field\n",
"from langchain.chains.base import Chain\n",
"from langchain_experimental.autonomous_agents import BabyAGI"
]
},
{
"cell_type": "markdown",
"id": "09f70772",
"metadata": {},
"source": [
"## Connect to the Vector Store\n",
"\n",
"Depending on what vectorstore you use, this step may look different."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "794045d4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Note: you may need to restart the kernel to use updated packages.\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install faiss-cpu > /dev/null\n",
"%pip install google-search-results > /dev/null\n",
"from langchain.vectorstores import FAISS\n",
"from langchain.docstore import InMemoryDocstore"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "6e0305eb",
"metadata": {},
"outputs": [],
"source": [
"# Define your embedding model\n",
"embeddings_model = OpenAIEmbeddings()\n",
"# Initialize the vectorstore as empty\n",
"import faiss\n",
"\n",
"embedding_size = 1536\n",
"index = faiss.IndexFlatL2(embedding_size)\n",
"vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
]
},
{
"cell_type": "markdown",
"id": "0f3b72bf",
"metadata": {},
"source": [
"## Define the Chains\n",
"\n",
"BabyAGI relies on three LLM chains:\n",
"- Task creation chain to select new tasks to add to the list\n",
"- Task prioritization chain to re-prioritize tasks\n",
"- Execution Chain to execute the tasks\n",
"\n",
"\n",
"NOTE: in this notebook, the Execution chain will now be an agent."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b43cd580",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
"from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
"\n",
"todo_prompt = PromptTemplate.from_template(\n",
" \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
")\n",
"todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
"search = SerpAPIWrapper()\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=\"TODO\",\n",
" func=todo_chain.run,\n",
" description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
" ),\n",
"]\n",
"\n",
"\n",
"prefix = \"\"\"You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}.\"\"\"\n",
"suffix = \"\"\"Question: {task}\n",
"{agent_scratchpad}\"\"\"\n",
"prompt = ZeroShotAgent.create_prompt(\n",
" tools,\n",
" prefix=prefix,\n",
" suffix=suffix,\n",
" input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4b00ae2e",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
"tool_names = [tool.name for tool in tools]\n",
"agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
"agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "05ba762e",
"metadata": {},
"source": [
"### Run the BabyAGI\n",
"\n",
"Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3d220b69",
"metadata": {},
"outputs": [],
"source": [
"OBJECTIVE = \"Write a weather report for SF today\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "3d69899b",
"metadata": {},
"outputs": [],
"source": [
"# Logging of LLMChains\n",
"verbose = False\n",
"# If None, will keep on going forever\n",
"max_iterations: Optional[int] = 3\n",
"baby_agi = BabyAGI.from_llm(\n",
" llm=llm,\n",
" vectorstore=vectorstore,\n",
" task_execution_chain=agent_executor,\n",
" verbose=verbose,\n",
" max_iterations=max_iterations,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f7957b51",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"1: Make a todo list\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"1: Make a todo list\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to come up with a todo list\n",
"Action: TODO\n",
"Action Input: Write a weather report for SF today\u001b[0m\u001b[33;1m\u001b[1;3m\n",
"\n",
"1. Research current weather conditions in San Francisco\n",
"2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
"3. Analyze data to determine current weather trends\n",
"4. Write a brief introduction to the weather report\n",
"5. Describe current weather conditions in San Francisco\n",
"6. Discuss any upcoming weather changes\n",
"7. Summarize the weather report\n",
"8. Proofread and edit the report\n",
"9. Submit the report\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\n",
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
"3: Analyze data to determine any upcoming weather changes;\n",
"4: Research current weather forecasts for San Francisco;\n",
"5: Create a visual representation of the weather report;\n",
"6: Include relevant images and graphics in the report;\n",
"7: Format the report for readability;\n",
"8: Publish the report online;\n",
"9: Monitor the report for accuracy.\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to search for current weather conditions in San Francisco\n",
"Action: Search\n",
"Action Input: Current weather conditions in San Francisco\u001b[0m\u001b[36;1m\u001b[1;3mCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ...\u001b[0m\u001b[32;1m\u001b[1;3m I need to compile the data into a weather report\n",
"Action: TODO\n",
"Action Input: Compile data into a weather report\u001b[0m\u001b[33;1m\u001b[1;3m\n",
"\n",
"1. Gather data from reliable sources such as the National Weather Service, local weather stations, and other meteorological organizations.\n",
"\n",
"2. Analyze the data to identify trends and patterns.\n",
"\n",
"3. Create a chart or graph to visualize the data.\n",
"\n",
"4. Write a summary of the data and its implications.\n",
"\n",
"5. Compile the data into a report format.\n",
"\n",
"6. Proofread the report for accuracy and clarity.\n",
"\n",
"7. Publish the report to a website or other platform.\n",
"\n",
"8. Distribute the report to relevant stakeholders.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\n",
"\u001b[95m\u001b[1m\n",
"*****TASK LIST*****\n",
"\u001b[0m\u001b[0m\n",
"3: Format the report for readability;\n",
"4: Include relevant images and graphics in the report;\n",
"5: Compare the current weather conditions in San Francisco to the forecasted conditions;\n",
"6: Identify any potential weather-related hazards in the area;\n",
"7: Research historical weather patterns in San Francisco;\n",
"8: Identify any potential trends in the weather data;\n",
"9: Include relevant data sources in the report;\n",
"10: Summarize the weather report in a concise manner;\n",
"11: Include a summary of the forecasted weather conditions;\n",
"12: Include a summary of the current weather conditions;\n",
"13: Include a summary of the historical weather patterns;\n",
"14: Include a summary of the potential weather-related hazards;\n",
"15: Include a summary of the potential trends in the weather data;\n",
"16: Include a summary of the data sources used in the report;\n",
"17: Analyze data to determine any upcoming weather changes;\n",
"18: Research current weather forecasts for San Francisco;\n",
"19: Create a visual representation of the weather report;\n",
"20: Publish the report online;\n",
"21: Monitor the report for accuracy\n",
"\u001b[92m\u001b[1m\n",
"*****NEXT TASK*****\n",
"\u001b[0m\u001b[0m\n",
"3: Format the report for readability;\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to make sure the report is easy to read;\n",
"Action: TODO\n",
"Action Input: Make the report easy to read\u001b[0m\u001b[33;1m\u001b[1;3m\n",
"\n",
"1. Break up the report into sections with clear headings\n",
"2. Use bullet points and numbered lists to organize information\n",
"3. Use short, concise sentences\n",
"4. Use simple language and avoid jargon\n",
"5. Include visuals such as charts, graphs, and diagrams to illustrate points\n",
"6. Use bold and italicized text to emphasize key points\n",
"7. Include a table of contents and page numbers\n",
"8. Use a consistent font and font size throughout the report\n",
"9. Include a summary at the end of the report\n",
"10. Proofread the report for typos and errors\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[93m\u001b[1m\n",
"*****TASK RESULT*****\n",
"\u001b[0m\u001b[0m\n",
"The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\n",
"\u001b[91m\u001b[1m\n",
"*****TASK ENDING*****\n",
"\u001b[0m\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'objective': 'Write a weather report for SF today'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"baby_agi({\"objective\": OBJECTIVE})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "898a210b",
"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
}

707
cookbook/camel_role_playing.ipynb Normal file
View File

@@ -0,0 +1,707 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# CAMEL Role-Playing Autonomous Cooperative Agents\n",
"\n",
"This is a langchain implementation of paper: \"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society\".\n",
"\n",
"Overview:\n",
"\n",
"The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.\n",
"\n",
"The original implementation: https://github.com/lightaime/camel\n",
"\n",
"Project website: https://www.camel-ai.org/\n",
"\n",
"Arxiv paper: https://arxiv.org/abs/2303.17760\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from typing import List\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts.chat import (\n",
" SystemMessagePromptTemplate,\n",
" HumanMessagePromptTemplate,\n",
")\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define a CAMEL agent helper class"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class CAMELAgent:\n",
" def __init__(\n",
" self,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.init_messages()\n",
"\n",
" def reset(self) -> None:\n",
" self.init_messages()\n",
" return self.stored_messages\n",
"\n",
" def init_messages(self) -> None:\n",
" self.stored_messages = [self.system_message]\n",
"\n",
" def update_messages(self, message: BaseMessage) -> List[BaseMessage]:\n",
" self.stored_messages.append(message)\n",
" return self.stored_messages\n",
"\n",
" def step(\n",
" self,\n",
" input_message: HumanMessage,\n",
" ) -> AIMessage:\n",
" messages = self.update_messages(input_message)\n",
"\n",
" output_message = self.model(messages)\n",
" self.update_messages(output_message)\n",
"\n",
" return output_message"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup OpenAI API key and roles and task for role-playing"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
"\n",
"assistant_role_name = \"Python Programmer\"\n",
"user_role_name = \"Stock Trader\"\n",
"task = \"Develop a trading bot for the stock market\"\n",
"word_limit = 50 # word limit for task brainstorming"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a task specify agent for brainstorming and get the specified task"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n"
]
}
],
"source": [
"task_specifier_sys_msg = SystemMessage(content=\"You can make a task more specific.\")\n",
"task_specifier_prompt = \"\"\"Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.\n",
"Please make it more specific. Be creative and imaginative.\n",
"Please reply with the specified task in {word_limit} words or less. Do not add anything else.\"\"\"\n",
"task_specifier_template = HumanMessagePromptTemplate.from_template(\n",
" template=task_specifier_prompt\n",
")\n",
"task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))\n",
"task_specifier_msg = task_specifier_template.format_messages(\n",
" assistant_role_name=assistant_role_name,\n",
" user_role_name=user_role_name,\n",
" task=task,\n",
" word_limit=word_limit,\n",
")[0]\n",
"specified_task_msg = task_specify_agent.step(task_specifier_msg)\n",
"print(f\"Specified task: {specified_task_msg.content}\")\n",
"specified_task = specified_task_msg.content"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create inception prompts for AI assistant and AI user for role-playing"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"assistant_inception_prompt = \"\"\"Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!\n",
"We share a common interest in collaborating to successfully complete a task.\n",
"You must help me to complete the task.\n",
"Here is the task: {task}. Never forget our task!\n",
"I must instruct you based on your expertise and my needs to complete the task.\n",
"\n",
"I must give you one instruction at a time.\n",
"You must write a specific solution that appropriately completes the requested instruction.\n",
"You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\n",
"Do not add anything else other than your solution to my instruction.\n",
"You are never supposed to ask me any questions you only answer questions.\n",
"You are never supposed to reply with a flake solution. Explain your solutions.\n",
"Your solution must be declarative sentences and simple present tense.\n",
"Unless I say the task is completed, you should always start with:\n",
"\n",
"Solution: <YOUR_SOLUTION>\n",
"\n",
"<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.\n",
"Always end <YOUR_SOLUTION> with: Next request.\"\"\"\n",
"\n",
"user_inception_prompt = \"\"\"Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.\n",
"We share a common interest in collaborating to successfully complete a task.\n",
"I must help you to complete the task.\n",
"Here is the task: {task}. Never forget our task!\n",
"You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:\n",
"\n",
"1. Instruct with a necessary input:\n",
"Instruction: <YOUR_INSTRUCTION>\n",
"Input: <YOUR_INPUT>\n",
"\n",
"2. Instruct without any input:\n",
"Instruction: <YOUR_INSTRUCTION>\n",
"Input: None\n",
"\n",
"The \"Instruction\" describes a task or question. The paired \"Input\" provides further context or information for the requested \"Instruction\".\n",
"\n",
"You must give me one instruction at a time.\n",
"I must write a response that appropriately completes the requested instruction.\n",
"I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\n",
"You should instruct me not ask me questions.\n",
"Now you must start to instruct me using the two ways described above.\n",
"Do not add anything else other than your instruction and the optional corresponding input!\n",
"Keep giving me instructions and necessary inputs until you think the task is completed.\n",
"When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\n",
"Never say <CAMEL_TASK_DONE> unless my responses have solved your task.\"\"\""
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a helper helper to get system messages for AI assistant and AI user from role names and the task"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):\n",
" assistant_sys_template = SystemMessagePromptTemplate.from_template(\n",
" template=assistant_inception_prompt\n",
" )\n",
" assistant_sys_msg = assistant_sys_template.format_messages(\n",
" assistant_role_name=assistant_role_name,\n",
" user_role_name=user_role_name,\n",
" task=task,\n",
" )[0]\n",
"\n",
" user_sys_template = SystemMessagePromptTemplate.from_template(\n",
" template=user_inception_prompt\n",
" )\n",
" user_sys_msg = user_sys_template.format_messages(\n",
" assistant_role_name=assistant_role_name,\n",
" user_role_name=user_role_name,\n",
" task=task,\n",
" )[0]\n",
"\n",
" return assistant_sys_msg, user_sys_msg"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create AI assistant agent and AI user agent from obtained system messages"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"assistant_sys_msg, user_sys_msg = get_sys_msgs(\n",
" assistant_role_name, user_role_name, specified_task\n",
")\n",
"assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))\n",
"user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))\n",
"\n",
"# Reset agents\n",
"assistant_agent.reset()\n",
"user_agent.reset()\n",
"\n",
"# Initialize chats\n",
"user_msg = HumanMessage(\n",
" content=(\n",
" f\"{user_sys_msg.content}. \"\n",
" \"Now start to give me introductions one by one. \"\n",
" \"Only reply with Instruction and Input.\"\n",
" )\n",
")\n",
"\n",
"assistant_msg = HumanMessage(content=f\"{assistant_sys_msg.content}\")\n",
"assistant_msg = assistant_agent.step(user_msg)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Start role-playing session to solve the task!"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original task prompt:\n",
"Develop a trading bot for the stock market\n",
"\n",
"Specified task prompt:\n",
"Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Install the necessary Python libraries for data analysis and trading.\n",
"Input: None\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:\n",
"\n",
"```\n",
"pip install pandas numpy matplotlib ta-lib\n",
"```\n",
"\n",
"Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Import the necessary libraries in the Python script.\n",
"Input: None\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:\n",
"\n",
"```\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import talib as ta\n",
"```\n",
"\n",
"Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Load historical stock data into a pandas DataFrame.\n",
"Input: The path to the CSV file containing the historical stock data.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:\n",
"\n",
"```\n",
"df = pd.read_csv('path/to/csv/file.csv')\n",
"```\n",
"\n",
"This will load the historical stock data into a pandas DataFrame called `df`. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:\n",
"\n",
"```\n",
"df = df.set_index('date')\n",
"df = df.sort_index(ascending=True)\n",
"```\n",
"\n",
"This will set the date column as the index and sort the DataFrame in ascending order by date. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.\n",
"Input: The period for the short-term moving average and the period for the long-term moving average.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:\n",
"\n",
"```\n",
"short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
"long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
"```\n",
"\n",
"This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:\n",
"\n",
"```\n",
"new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
"new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
"```\n",
"\n",
"This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:\n",
"\n",
"```\n",
"new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
"```\n",
"\n",
"This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.\n",
"Input: The stop loss and profit target as percentages.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:\n",
"\n",
"```\n",
"stop_loss = stop_loss_percent / 100\n",
"profit_target = profit_target_percent / 100\n",
"\n",
"new_df['pnl'] = 0.0\n",
"buy_price = 0.0\n",
"for i in range(1, len(new_df)):\n",
" if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
" buy_price = new_df['close'][i]\n",
" elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
" sell_price = new_df['close'][i]\n",
" if sell_price <= buy_price * (1 - stop_loss):\n",
" new_df['pnl'][i] = -stop_loss\n",
" elif sell_price >= buy_price * (1 + profit_target):\n",
" new_df['pnl'][i] = profit_target\n",
" else:\n",
" new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
"```\n",
"\n",
"This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Calculate the total profit or loss for all trades.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:\n",
"\n",
"```\n",
"total_pnl = new_df['pnl'].sum()\n",
"```\n",
"\n",
"This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:\n",
"\n",
"```\n",
"plt.figure(figsize=(12,6))\n",
"plt.plot(new_df.index, new_df['close'], label='Close')\n",
"plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
"plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Price')\n",
"plt.title('Stock Data with Moving Averages')\n",
"plt.legend()\n",
"plt.show()\n",
"```\n",
"\n",
"This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Visualize the buy and sell signals using a scatter plot.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:\n",
"\n",
"```\n",
"buy_signals = new_df[new_df['signal'] == 1]\n",
"sell_signals = new_df[new_df['signal'] == -1]\n",
"\n",
"plt.figure(figsize=(12,6))\n",
"plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
"plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
"plt.plot(new_df.index, new_df['close'], label='Close')\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Price')\n",
"plt.title('Buy and Sell Signals')\n",
"plt.legend()\n",
"plt.show()\n",
"```\n",
"\n",
"This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Print the total profit or loss for all trades.\n",
"Input: None.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:\n",
"\n",
"```\n",
"print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
"```\n",
"\n",
"This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"Instruction: Finalize the code by putting all the code snippets together in a single Python script.\n",
"Input: The necessary inputs for each code snippet.\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Solution: Here is the complete Python script that puts all the code snippets together:\n",
"\n",
"```\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import talib as ta\n",
"\n",
"# Load historical stock data into a pandas DataFrame\n",
"df = pd.read_csv('path/to/csv/file.csv')\n",
"\n",
"# Preprocess the historical stock data\n",
"df = df.set_index('date')\n",
"df = df.sort_index(ascending=True)\n",
"\n",
"# Calculate the short-term and long-term moving averages\n",
"short_period = 10\n",
"long_period = 30\n",
"short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
"long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
"\n",
"# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages\n",
"new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
"new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
"\n",
"# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages\n",
"new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
"\n",
"# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target\n",
"stop_loss_percent = 5\n",
"profit_target_percent = 10\n",
"stop_loss = stop_loss_percent / 100\n",
"profit_target = profit_target_percent / 100\n",
"new_df['pnl'] = 0.0\n",
"buy_price = 0.0\n",
"for i in range(1, len(new_df)):\n",
" if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
" buy_price = new_df['close'][i]\n",
" elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
" sell_price = new_df['close'][i]\n",
" if sell_price <= buy_price * (1 - stop_loss):\n",
" new_df['pnl'][i] = -stop_loss\n",
" elif sell_price >= buy_price * (1 + profit_target):\n",
" new_df['pnl'][i] = profit_target\n",
" else:\n",
" new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
"\n",
"# Calculate the total profit or loss for all trades\n",
"total_pnl = new_df['pnl'].sum()\n",
"\n",
"# Visualize the stock data, short-term moving average, and long-term moving average using a line chart\n",
"plt.figure(figsize=(12,6))\n",
"plt.plot(new_df.index, new_df['close'], label='Close')\n",
"plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
"plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Price')\n",
"plt.title('Stock Data with Moving Averages')\n",
"plt.legend()\n",
"plt.show()\n",
"\n",
"# Visualize the buy and sell signals using a scatter plot\n",
"buy_signals = new_df[new_df['signal'] == 1]\n",
"sell_signals = new_df[new_df['signal'] == -1]\n",
"plt.figure(figsize=(12,6))\n",
"plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
"plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
"plt.plot(new_df.index, new_df['close'], label='Close')\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Price')\n",
"plt.title('Buy and Sell Signals')\n",
"plt.legend()\n",
"plt.show()\n",
"\n",
"# Print the total profit or loss for all trades\n",
"print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
"```\n",
"\n",
"You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.\n",
"\n",
"\n",
"AI User (Stock Trader):\n",
"\n",
"<CAMEL_TASK_DONE>\n",
"\n",
"\n",
"AI Assistant (Python Programmer):\n",
"\n",
"Great! Let me know if you need any further assistance.\n",
"\n",
"\n"
]
}
],
"source": [
"print(f\"Original task prompt:\\n{task}\\n\")\n",
"print(f\"Specified task prompt:\\n{specified_task}\\n\")\n",
"\n",
"chat_turn_limit, n = 30, 0\n",
"while n < chat_turn_limit:\n",
" n += 1\n",
" user_ai_msg = user_agent.step(assistant_msg)\n",
" user_msg = HumanMessage(content=user_ai_msg.content)\n",
" print(f\"AI User ({user_role_name}):\\n\\n{user_msg.content}\\n\\n\")\n",
"\n",
" assistant_ai_msg = assistant_agent.step(user_msg)\n",
" assistant_msg = HumanMessage(content=assistant_ai_msg.content)\n",
" print(f\"AI Assistant ({assistant_role_name}):\\n\\n{assistant_msg.content}\\n\\n\")\n",
" if \"<CAMEL_TASK_DONE>\" in user_msg.content:\n",
" break"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "camel",
"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"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}

693
cookbook/causal_program_aided_language_model.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1179
cookbook/code-analysis-deeplake.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

553
cookbook/custom_agent_with_plugin_retrieval.ipynb Normal file
View File

@@ -0,0 +1,553 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ba5f8741",
"metadata": {},
"source": [
"# Custom Agent with PlugIn Retrieval\n",
"\n",
"This notebook combines two concepts in order to build a custom agent that can interact with AI Plugins:\n",
"\n",
"1. [Custom Agent with Tool Retrieval](/docs/modules/agents/how_to/custom_agent_with_tool_retrieval.html): This introduces the concept of retrieving many tools, which is useful when trying to work with arbitrarily many plugins.\n",
"2. [Natural Language API Chains](/docs/use_cases/apis/openapi.html): This creates Natural Language wrappers around OpenAPI endpoints. This is useful because (1) plugins use OpenAPI endpoints under the hood, (2) wrapping them in an NLAChain allows the router agent to call it more easily.\n",
"\n",
"The novel idea introduced in this notebook is the idea of using retrieval to select not the tools explicitly, but the set of OpenAPI specs to use. We can then generate tools from those OpenAPI specs. The use case for this is when trying to get agents to use plugins. It may be more efficient to choose plugins first, then the endpoints, rather than the endpoints directly. This is because the plugins may contain more useful information for selection."
]
},
{
"cell_type": "markdown",
"id": "fea4812c",
"metadata": {},
"source": [
"## Set up environment\n",
"\n",
"Do necessary imports, etc."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9af9734e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import (\n",
" Tool,\n",
" AgentExecutor,\n",
" LLMSingleActionAgent,\n",
" AgentOutputParser,\n",
")\n",
"from langchain.prompts import StringPromptTemplate\n",
"from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
"from typing import List, Union\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"from langchain.agents.agent_toolkits import NLAToolkit\n",
"from langchain.tools.plugin import AIPlugin\n",
"import re"
]
},
{
"cell_type": "markdown",
"id": "2f91d8b4",
"metadata": {},
"source": [
"## Setup LLM"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a1a3b59c",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "6df0253f",
"metadata": {},
"source": [
"## Set up plugins\n",
"\n",
"Load and index plugins"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "becda2a1",
"metadata": {},
"outputs": [],
"source": [
"urls = [\n",
" \"https://datasette.io/.well-known/ai-plugin.json\",\n",
" \"https://api.speak.com/.well-known/ai-plugin.json\",\n",
" \"https://www.wolframalpha.com/.well-known/ai-plugin.json\",\n",
" \"https://www.zapier.com/.well-known/ai-plugin.json\",\n",
" \"https://www.klarna.com/.well-known/ai-plugin.json\",\n",
" \"https://www.joinmilo.com/.well-known/ai-plugin.json\",\n",
" \"https://slack.com/.well-known/ai-plugin.json\",\n",
" \"https://schooldigger.com/.well-known/ai-plugin.json\",\n",
"]\n",
"\n",
"AI_PLUGINS = [AIPlugin.from_url(url) for url in urls]"
]
},
{
"cell_type": "markdown",
"id": "17362717",
"metadata": {},
"source": [
"## Tool Retriever\n",
"\n",
"We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "77c4be4b",
"metadata": {},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.schema import Document"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9092a158",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.2 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load a Swagger 2.0 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
]
}
],
"source": [
"embeddings = OpenAIEmbeddings()\n",
"docs = [\n",
" Document(\n",
" page_content=plugin.description_for_model,\n",
" metadata={\"plugin_name\": plugin.name_for_model},\n",
" )\n",
" for plugin in AI_PLUGINS\n",
"]\n",
"vector_store = FAISS.from_documents(docs, embeddings)\n",
"toolkits_dict = {\n",
" plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
" for plugin in AI_PLUGINS\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "735a7566",
"metadata": {},
"outputs": [],
"source": [
"retriever = vector_store.as_retriever()\n",
"\n",
"\n",
"def get_tools(query):\n",
" # Get documents, which contain the Plugins to use\n",
" docs = retriever.get_relevant_documents(query)\n",
" # Get the toolkits, one for each plugin\n",
" tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
" # Get the tools: a separate NLAChain for each endpoint\n",
" tools = []\n",
" for tk in tool_kits:\n",
" tools.extend(tk.nla_tools)\n",
" return tools"
]
},
{
"cell_type": "markdown",
"id": "7699afd7",
"metadata": {},
"source": [
"We can now test this retriever to see if it seems to work."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "425f2886",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Milo.askMilo',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
" 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
" 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
" 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
" 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
" 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
" 'Speak.translate',\n",
" 'Speak.explainPhrase',\n",
" 'Speak.explainTask']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools = get_tools(\"What could I do today with my kiddo\")\n",
"[t.name for t in tools]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3aa88768",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Open_AI_Klarna_product_Api.productsUsingGET',\n",
" 'Milo.askMilo',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
" 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
" 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
" 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
" 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
" 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools = get_tools(\"what shirts can i buy?\")\n",
"[t.name for t in tools]"
]
},
{
"cell_type": "markdown",
"id": "2e7a075c",
"metadata": {},
"source": [
"## Prompt Template\n",
"\n",
"The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "339b1bb8",
"metadata": {},
"outputs": [],
"source": [
"# Set up the base template\n",
"template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
"\n",
"{tools}\n",
"\n",
"Use the following format:\n",
"\n",
"Question: the input question you must answer\n",
"Thought: you should always think about what to do\n",
"Action: the action to take, should be one of [{tool_names}]\n",
"Action Input: the input to the action\n",
"Observation: the result of the action\n",
"... (this Thought/Action/Action Input/Observation can repeat N times)\n",
"Thought: I now know the final answer\n",
"Final Answer: the final answer to the original input question\n",
"\n",
"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\""
]
},
{
"cell_type": "markdown",
"id": "1583acdc",
"metadata": {},
"source": [
"The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "fd969d31",
"metadata": {},
"outputs": [],
"source": [
"from typing import Callable\n",
"\n",
"\n",
"# Set up a prompt template\n",
"class CustomPromptTemplate(StringPromptTemplate):\n",
" # The template to use\n",
" template: str\n",
" ############## NEW ######################\n",
" # The list of tools available\n",
" tools_getter: Callable\n",
"\n",
" def format(self, **kwargs) -> str:\n",
" # Get the intermediate steps (AgentAction, Observation tuples)\n",
" # Format them in a particular way\n",
" intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
" thoughts = \"\"\n",
" for action, observation in intermediate_steps:\n",
" thoughts += action.log\n",
" thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
" # Set the agent_scratchpad variable to that value\n",
" kwargs[\"agent_scratchpad\"] = thoughts\n",
" ############## NEW ######################\n",
" tools = self.tools_getter(kwargs[\"input\"])\n",
" # Create a tools variable from the list of tools provided\n",
" kwargs[\"tools\"] = \"\\n\".join(\n",
" [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
" )\n",
" # Create a list of tool names for the tools provided\n",
" kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
" return self.template.format(**kwargs)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "798ef9fb",
"metadata": {},
"outputs": [],
"source": [
"prompt = CustomPromptTemplate(\n",
" template=template,\n",
" tools_getter=get_tools,\n",
" # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
" # This includes the `intermediate_steps` variable because that is needed\n",
" input_variables=[\"input\", \"intermediate_steps\"],\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ef3a1af3",
"metadata": {},
"source": [
"## Output Parser\n",
"\n",
"The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7c6fe0d3",
"metadata": {},
"outputs": [],
"source": [
"class CustomOutputParser(AgentOutputParser):\n",
" def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
" # Check if agent should finish\n",
" if \"Final Answer:\" in llm_output:\n",
" return AgentFinish(\n",
" # Return values is generally always a dictionary with a single `output` key\n",
" # It is not recommended to try anything else at the moment :)\n",
" return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
" log=llm_output,\n",
" )\n",
" # Parse out the action and action input\n",
" regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
" match = re.search(regex, llm_output, re.DOTALL)\n",
" if not match:\n",
" raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
" action = match.group(1).strip()\n",
" action_input = match.group(2)\n",
" # Return the action and action input\n",
" return AgentAction(\n",
" tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d278706a",
"metadata": {},
"outputs": [],
"source": [
"output_parser = CustomOutputParser()"
]
},
{
"cell_type": "markdown",
"id": "170587b1",
"metadata": {},
"source": [
"## Set up LLM, stop sequence, and the agent\n",
"\n",
"Also the same as the previous notebook"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f9d4c374",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "9b1cc2a2",
"metadata": {},
"outputs": [],
"source": [
"# LLM chain consisting of the LLM and a prompt\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "e4f5092f",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [tool.name for tool in tools]\n",
"agent = LLMSingleActionAgent(\n",
" llm_chain=llm_chain,\n",
" output_parser=output_parser,\n",
" stop=[\"\\nObservation:\"],\n",
" allowed_tools=tool_names,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "aa8a5326",
"metadata": {},
"source": [
"## Use the Agent\n",
"\n",
"Now we can use it!"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "490604e9",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "653b1617",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
"Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
"Action Input: shirts\u001b[0m\n",
"\n",
"Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
"Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"what shirts can i buy?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2481ee76",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

577
cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb Normal file
View File

@@ -0,0 +1,577 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ba5f8741",
"metadata": {},
"source": [
"# Plug-and-Plai\n",
"\n",
"This notebook builds upon the idea of [plugin retrieval](./custom_agent_with_plugin_retrieval.html), but pulls all tools from `plugnplai` - a directory of AI Plugins."
]
},
{
"cell_type": "markdown",
"id": "fea4812c",
"metadata": {},
"source": [
"## Set up environment\n",
"\n",
"Do necessary imports, etc."
]
},
{
"cell_type": "markdown",
"id": "aca08be8",
"metadata": {},
"source": [
"Install plugnplai lib to get a list of active plugins from https://plugplai.com directory"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "52e248c9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"pip install plugnplai -q"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9af9734e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import (\n",
" Tool,\n",
" AgentExecutor,\n",
" LLMSingleActionAgent,\n",
" AgentOutputParser,\n",
")\n",
"from langchain.prompts import StringPromptTemplate\n",
"from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
"from typing import List, Union\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"from langchain.agents.agent_toolkits import NLAToolkit\n",
"from langchain.tools.plugin import AIPlugin\n",
"import re\n",
"import plugnplai"
]
},
{
"cell_type": "markdown",
"id": "2f91d8b4",
"metadata": {},
"source": [
"## Setup LLM"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a1a3b59c",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "6df0253f",
"metadata": {},
"source": [
"## Set up plugins\n",
"\n",
"Load and index plugins"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "9e0f7882",
"metadata": {},
"outputs": [],
"source": [
"# Get all plugins from plugnplai.com\n",
"urls = plugnplai.get_plugins()\n",
"\n",
"# Get ChatGPT plugins - only ChatGPT verified plugins\n",
"urls = plugnplai.get_plugins(filter=\"ChatGPT\")\n",
"\n",
"# Get working plugins - only tested plugins (in progress)\n",
"urls = plugnplai.get_plugins(filter=\"working\")\n",
"\n",
"\n",
"AI_PLUGINS = [AIPlugin.from_url(url + \"/.well-known/ai-plugin.json\") for url in urls]"
]
},
{
"cell_type": "markdown",
"id": "17362717",
"metadata": {},
"source": [
"## Tool Retriever\n",
"\n",
"We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "77c4be4b",
"metadata": {},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.schema import Document"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9092a158",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.2 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
"Attempting to load a Swagger 2.0 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
]
}
],
"source": [
"embeddings = OpenAIEmbeddings()\n",
"docs = [\n",
" Document(\n",
" page_content=plugin.description_for_model,\n",
" metadata={\"plugin_name\": plugin.name_for_model},\n",
" )\n",
" for plugin in AI_PLUGINS\n",
"]\n",
"vector_store = FAISS.from_documents(docs, embeddings)\n",
"toolkits_dict = {\n",
" plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
" for plugin in AI_PLUGINS\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "735a7566",
"metadata": {},
"outputs": [],
"source": [
"retriever = vector_store.as_retriever()\n",
"\n",
"\n",
"def get_tools(query):\n",
" # Get documents, which contain the Plugins to use\n",
" docs = retriever.get_relevant_documents(query)\n",
" # Get the toolkits, one for each plugin\n",
" tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
" # Get the tools: a separate NLAChain for each endpoint\n",
" tools = []\n",
" for tk in tool_kits:\n",
" tools.extend(tk.nla_tools)\n",
" return tools"
]
},
{
"cell_type": "markdown",
"id": "7699afd7",
"metadata": {},
"source": [
"We can now test this retriever to see if it seems to work."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "425f2886",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Milo.askMilo',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
" 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
" 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
" 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
" 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
" 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
" 'Speak.translate',\n",
" 'Speak.explainPhrase',\n",
" 'Speak.explainTask']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools = get_tools(\"What could I do today with my kiddo\")\n",
"[t.name for t in tools]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3aa88768",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Open_AI_Klarna_product_Api.productsUsingGET',\n",
" 'Milo.askMilo',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
" 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
" 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
" 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
" 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
" 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
" 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
" 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools = get_tools(\"what shirts can i buy?\")\n",
"[t.name for t in tools]"
]
},
{
"cell_type": "markdown",
"id": "2e7a075c",
"metadata": {},
"source": [
"## Prompt Template\n",
"\n",
"The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "339b1bb8",
"metadata": {},
"outputs": [],
"source": [
"# Set up the base template\n",
"template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
"\n",
"{tools}\n",
"\n",
"Use the following format:\n",
"\n",
"Question: the input question you must answer\n",
"Thought: you should always think about what to do\n",
"Action: the action to take, should be one of [{tool_names}]\n",
"Action Input: the input to the action\n",
"Observation: the result of the action\n",
"... (this Thought/Action/Action Input/Observation can repeat N times)\n",
"Thought: I now know the final answer\n",
"Final Answer: the final answer to the original input question\n",
"\n",
"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\""
]
},
{
"cell_type": "markdown",
"id": "1583acdc",
"metadata": {},
"source": [
"The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "fd969d31",
"metadata": {},
"outputs": [],
"source": [
"from typing import Callable\n",
"\n",
"\n",
"# Set up a prompt template\n",
"class CustomPromptTemplate(StringPromptTemplate):\n",
" # The template to use\n",
" template: str\n",
" ############## NEW ######################\n",
" # The list of tools available\n",
" tools_getter: Callable\n",
"\n",
" def format(self, **kwargs) -> str:\n",
" # Get the intermediate steps (AgentAction, Observation tuples)\n",
" # Format them in a particular way\n",
" intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
" thoughts = \"\"\n",
" for action, observation in intermediate_steps:\n",
" thoughts += action.log\n",
" thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
" # Set the agent_scratchpad variable to that value\n",
" kwargs[\"agent_scratchpad\"] = thoughts\n",
" ############## NEW ######################\n",
" tools = self.tools_getter(kwargs[\"input\"])\n",
" # Create a tools variable from the list of tools provided\n",
" kwargs[\"tools\"] = \"\\n\".join(\n",
" [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
" )\n",
" # Create a list of tool names for the tools provided\n",
" kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
" return self.template.format(**kwargs)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "798ef9fb",
"metadata": {},
"outputs": [],
"source": [
"prompt = CustomPromptTemplate(\n",
" template=template,\n",
" tools_getter=get_tools,\n",
" # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
" # This includes the `intermediate_steps` variable because that is needed\n",
" input_variables=[\"input\", \"intermediate_steps\"],\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ef3a1af3",
"metadata": {},
"source": [
"## Output Parser\n",
"\n",
"The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7c6fe0d3",
"metadata": {},
"outputs": [],
"source": [
"class CustomOutputParser(AgentOutputParser):\n",
" def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
" # Check if agent should finish\n",
" if \"Final Answer:\" in llm_output:\n",
" return AgentFinish(\n",
" # Return values is generally always a dictionary with a single `output` key\n",
" # It is not recommended to try anything else at the moment :)\n",
" return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
" log=llm_output,\n",
" )\n",
" # Parse out the action and action input\n",
" regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
" match = re.search(regex, llm_output, re.DOTALL)\n",
" if not match:\n",
" raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
" action = match.group(1).strip()\n",
" action_input = match.group(2)\n",
" # Return the action and action input\n",
" return AgentAction(\n",
" tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d278706a",
"metadata": {},
"outputs": [],
"source": [
"output_parser = CustomOutputParser()"
]
},
{
"cell_type": "markdown",
"id": "170587b1",
"metadata": {},
"source": [
"## Set up LLM, stop sequence, and the agent\n",
"\n",
"Also the same as the previous notebook"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f9d4c374",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "9b1cc2a2",
"metadata": {},
"outputs": [],
"source": [
"# LLM chain consisting of the LLM and a prompt\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "e4f5092f",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [tool.name for tool in tools]\n",
"agent = LLMSingleActionAgent(\n",
" llm_chain=llm_chain,\n",
" output_parser=output_parser,\n",
" stop=[\"\\nObservation:\"],\n",
" allowed_tools=tool_names,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "aa8a5326",
"metadata": {},
"source": [
"## Use the Agent\n",
"\n",
"Now we can use it!"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "490604e9",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "653b1617",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
"Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
"Action Input: shirts\u001b[0m\n",
"\n",
"Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
"Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"what shirts can i buy?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2481ee76",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "3ccef4e08d87aa1eeb90f63e0f071292ccb2e9c42e70f74ab2bf6f5493ca7bbc"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

273
cookbook/databricks_sql_db.ipynb Normal file
View File

@@ -0,0 +1,273 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "707d13a7",
"metadata": {},
"source": [
"# Databricks\n",
"\n",
"This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
"It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
]
},
{
"cell_type": "markdown",
"id": "0076d072",
"metadata": {},
"source": [
"## Installation and Setup"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "739b489b",
"metadata": {},
"outputs": [],
"source": [
"!pip install databricks-sql-connector"
]
},
{
"cell_type": "markdown",
"id": "73113163",
"metadata": {},
"source": [
"## Connecting to Databricks\n",
"\n",
"You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
"\n",
"### Syntax\n",
"```python\n",
"SQLDatabase.from_databricks(\n",
" catalog: str,\n",
" schema: str,\n",
" host: Optional[str] = None,\n",
" api_token: Optional[str] = None,\n",
" warehouse_id: Optional[str] = None,\n",
" cluster_id: Optional[str] = None,\n",
" engine_args: Optional[dict] = None,\n",
" **kwargs: Any)\n",
"```\n",
"### Required Parameters\n",
"* `catalog`: The catalog name in the Databricks database.\n",
"* `schema`: The schema name in the catalog.\n",
"\n",
"### Optional Parameters\n",
"There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
"* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
"* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
"* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
"* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
"* `engine_args`: The arguments to be used when connecting Databricks.\n",
"* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
]
},
{
"cell_type": "markdown",
"id": "b11c7e48",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8102bca0",
"metadata": {},
"outputs": [],
"source": [
"# Connecting to Databricks with SQLDatabase wrapper\n",
"from langchain.utilities import SQLDatabase\n",
"\n",
"db = SQLDatabase.from_databricks(catalog=\"samples\", schema=\"nyctaxi\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "9dd36f58",
"metadata": {},
"outputs": [],
"source": [
"# Creating a OpenAI Chat LLM wrapper\n",
"from langchain.chat_models import ChatOpenAI\n",
"\n",
"llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
]
},
{
"cell_type": "markdown",
"id": "5b5c5f1a",
"metadata": {},
"source": [
"### SQL Chain example\n",
"\n",
"This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "36f2270b",
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities import SQLDatabaseChain\n",
"\n",
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4e2b5f25",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
"What is the average duration of taxi rides that start between midnight and 6am?\n",
"SQLQuery:\u001b[32;1m\u001b[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",
"FROM trips\n",
"WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[(987.8122786304605,)]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db_chain.run(\n",
" \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",
")"
]
},
{
"cell_type": "markdown",
"id": "e496d5e5",
"metadata": {},
"source": [
"### SQL Database Agent example\n",
"\n",
"This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "9918e86a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_sql_agent\n",
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
"\n",
"toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
"agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c484a76e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mtrips\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
"Action: schema_sql_db\n",
"Action Input: trips\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE trips (\n",
"\ttpep_pickup_datetime TIMESTAMP, \n",
"\ttpep_dropoff_datetime TIMESTAMP, \n",
"\ttrip_distance FLOAT, \n",
"\tfare_amount FLOAT, \n",
"\tpickup_zip INT, \n",
"\tdropoff_zip INT\n",
") USING DELTA\n",
"\n",
"/*\n",
"3 rows from trips table:\n",
"tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",
"2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",
"2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",
"2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",
"*/\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
"Action: query_sql_db\n",
"Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[(30.6, '0 00:43:31.000000000')]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
"Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the longest trip distance and how long did it take?\")"
]
}
],
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

257
cookbook/deeplake_semantic_search_over_chat.ipynb Normal file
View File

@@ -0,0 +1,257 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# QA using Activeloop's DeepLake\n",
"In this tutorial, we are going to use Langchain + Activeloop's Deep Lake with GPT4 to semantically search and ask questions over a group chat.\n",
"\n",
"View a working demo [here](https://twitter.com/thisissukh_/status/1647223328363679745)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Install required packages"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!python3 -m pip install --upgrade langchain 'deeplake[enterprise]' openai tiktoken"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Add API keys"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import getpass\n",
"from langchain.document_loaders import PyPDFLoader, TextLoader\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import (\n",
" RecursiveCharacterTextSplitter,\n",
" CharacterTextSplitter,\n",
")\n",
"from langchain.vectorstores import DeepLake\n",
"from langchain.chains import ConversationalRetrievalChain, RetrievalQA\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.llms import OpenAI\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
"activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",
"os.environ[\"ACTIVELOOP_TOKEN\"] = activeloop_token\n",
"os.environ[\"ACTIVELOOP_ORG\"] = getpass.getpass(\"Activeloop Org:\")\n",
"\n",
"org_id = os.environ[\"ACTIVELOOP_ORG\"]\n",
"embeddings = OpenAIEmbeddings()\n",
"\n",
"dataset_path = \"hub://\" + org_id + \"/data\""
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"## 2. Create sample data"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"You can generate a sample group chat conversation using ChatGPT with this prompt:\n",
"\n",
"```\n",
"Generate a group chat conversation with three friends talking about their day, referencing real places and fictional names. Make it funny and as detailed as possible.\n",
"```\n",
"\n",
"I've already generated such a chat in `messages.txt`. We can keep it simple and use this for our example.\n",
"\n",
"## 3. Ingest chat embeddings\n",
"\n",
"We load the messages in the text file, chunk and upload to ActiveLoop Vector store."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='Participants:\\n\\nJerry: Loves movies and is a bit of a klutz.\\nSamantha: Enthusiastic about food and always trying new restaurants.\\nBarry: A nature lover, but always manages to get lost.\\nJerry: Hey, guys! You won\\'t believe what happened to me at the Times Square AMC theater. I tripped over my own feet and spilled popcorn everywhere! 🍿💥\\n\\nSamantha: LOL, that\\'s so you, Jerry! Was the floor buttery enough for you to ice skate on after that? 😂\\n\\nBarry: Sounds like a regular Tuesday for you, Jerry. Meanwhile, I tried to find that new hiking trail in Central Park. You know, the one that\\'s supposed to be impossible to get lost on? Well, guess what...\\n\\nJerry: You found a hidden treasure?\\n\\nBarry: No, I got lost. AGAIN. 🧭🙄\\n\\nSamantha: Barry, you\\'d get lost in your own backyard! But speaking of treasures, I found this new sushi place in Little Tokyo. \"Samantha\\'s Sushi Symphony\" it\\'s called. Coincidence? I think not!\\n\\nJerry: Maybe they named it after your ability to eat your body weight in sushi. 🍣', metadata={}), Document(page_content='Barry: How do you even FIND all these places, Samantha?\\n\\nSamantha: Simple, I don\\'t rely on Barry\\'s navigation skills. 😉 But seriously, the wasabi there was hotter than Jerry\\'s love for Marvel movies!\\n\\nJerry: Hey, nothing wrong with a little superhero action. By the way, did you guys see the new \"Captain Crunch: Breakfast Avenger\" trailer?\\n\\nSamantha: Captain Crunch? Are you sure you didn\\'t get that from one of your Saturday morning cereal binges?\\n\\nBarry: Yeah, and did he defeat his arch-enemy, General Mills? 😆\\n\\nJerry: Ha-ha, very funny. Anyway, that sushi place sounds awesome, Samantha. Next time, let\\'s go together, and maybe Barry can guide us... if we want a city-wide tour first.\\n\\nBarry: As long as we\\'re not hiking, I\\'ll get us there... eventually. 😅\\n\\nSamantha: It\\'s a date! But Jerry, you\\'re banned from carrying any food items.\\n\\nJerry: Deal! Just promise me no wasabi challenges. I don\\'t want to end up like the time I tried Sriracha ice cream.', metadata={}), Document(page_content=\"Barry: Wait, what happened with Sriracha ice cream?\\n\\nJerry: Let's just say it was a hot situation. Literally. 🔥\\n\\nSamantha: 🤣 I still have the video!\\n\\nJerry: Samantha, if you value our friendship, that video will never see the light of day.\\n\\nSamantha: No promises, Jerry. No promises. 🤐😈\\n\\nBarry: I foresee a fun weekend ahead! 🎉\", metadata={})]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Your Deep Lake dataset has been successfully created!\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\\"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset(path='hub://adilkhan/data', tensors=['embedding', 'id', 'metadata', 'text'])\n",
"\n",
" tensor htype shape dtype compression\n",
" ------- ------- ------- ------- ------- \n",
" embedding embedding (3, 1536) float32 None \n",
" id text (3, 1) str None \n",
" metadata json (3, 1) str None \n",
" text text (3, 1) str None \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" \r"
]
}
],
"source": [
"with open(\"messages.txt\") as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"pages = text_splitter.split_text(state_of_the_union)\n",
"\n",
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
"texts = text_splitter.create_documents(pages)\n",
"\n",
"print(texts)\n",
"\n",
"dataset_path = \"hub://\" + org_id + \"/data\"\n",
"embeddings = OpenAIEmbeddings()\n",
"db = DeepLake.from_documents(\n",
" texts, embeddings, dataset_path=dataset_path, overwrite=True\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# with open(\"messages.txt\") as f:\n",
"# state_of_the_union = f.read()\n",
"# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"# pages = text_splitter.split_text(state_of_the_union)\n",
"\n",
"# text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
"# texts = text_splitter.create_documents(pages)\n",
"\n",
"# print(texts)\n",
"\n",
"# dataset_path = \"hub://\" + org + \"/data\"\n",
"# embeddings = OpenAIEmbeddings()\n",
"# db = DeepLake.from_documents(\n",
"# texts, embeddings, dataset_path=dataset_path, overwrite=True, runtime={\"tensor_db\": True}\n",
"# )"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Ask questions\n",
"\n",
"Now we can ask a question and get an answer back with a semantic search:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"db = DeepLake(dataset_path=dataset_path, read_only=True, embedding=embeddings)\n",
"\n",
"retriever = db.as_retriever()\n",
"retriever.search_kwargs[\"distance_metric\"] = \"cos\"\n",
"retriever.search_kwargs[\"k\"] = 4\n",
"\n",
"qa = RetrievalQA.from_chain_type(\n",
" llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=False\n",
")\n",
"\n",
"# What was the restaurant the group was talking about called?\n",
"query = input(\"Enter query:\")\n",
"\n",
"# The Hungry Lobster\n",
"ans = qa({\"query\": query})\n",
"\n",
"print(ans)"
]
}
],
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

158
cookbook/elasticsearch_db_qa.ipynb Normal file
View File

@@ -0,0 +1,158 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Elasticsearch\n",
"\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/use_cases/qa_structured/integrations/elasticsearch.ipynb)\n",
"\n",
"We can use LLMs to interact with Elasticsearch analytics databases in natural language.\n",
"\n",
"This chain builds search queries via the Elasticsearch DSL API (filters and aggregations).\n",
"\n",
"The Elasticsearch client must have permissions for index listing, mapping description and search queries.\n",
"\n",
"See [here](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for instructions on how to run Elasticsearch locally."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"! pip install langchain langchain-experimental openai elasticsearch\n",
"\n",
"# Set env var OPENAI_API_KEY or load from a .env file\n",
"# import dotenv\n",
"\n",
"# dotenv.load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"from elasticsearch import Elasticsearch\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.chains.elasticsearch_database import ElasticsearchDatabaseChain"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Initialize Elasticsearch python client.\n",
"# See https://elasticsearch-py.readthedocs.io/en/v8.8.2/api.html#elasticsearch.Elasticsearch\n",
"ELASTIC_SEARCH_SERVER = \"https://elastic:pass@localhost:9200\"\n",
"db = Elasticsearch(ELASTIC_SEARCH_SERVER)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Uncomment the next cell to initially populate your db."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# customers = [\n",
"# {\"firstname\": \"Jennifer\", \"lastname\": \"Walters\"},\n",
"# {\"firstname\": \"Monica\",\"lastname\":\"Rambeau\"},\n",
"# {\"firstname\": \"Carol\",\"lastname\":\"Danvers\"},\n",
"# {\"firstname\": \"Wanda\",\"lastname\":\"Maximoff\"},\n",
"# {\"firstname\": \"Jennifer\",\"lastname\":\"Takeda\"},\n",
"# ]\n",
"# for i, customer in enumerate(customers):\n",
"# db.create(index=\"customers\", document=customer, id=i)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
"chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"question = \"What are the first names of all the customers?\"\n",
"chain.run(question)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can customize the prompt."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.elasticsearch_database.prompts import DEFAULT_DSL_TEMPLATE\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
"\n",
"Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
"\n",
"Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
"\n",
"Use the following format:\n",
"\n",
"Question: Question here\n",
"ESQuery: Elasticsearch Query formatted as json\n",
"\"\"\"\n",
"\n",
"PROMPT = PromptTemplate.from_template(\n",
" PROMPT_TEMPLATE,\n",
")\n",
"chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, query_prompt=PROMPT)"
]
}
],
"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": 4
}

497
cookbook/forward_looking_retrieval_augmented_generation.ipynb Normal file
View File

@@ -0,0 +1,497 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0f0b9afa",
"metadata": {},
"source": [
"# Retrieve as you generate with FLARE\n",
"\n",
"This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).\n",
"\n",
"Please see the original repo [here](https://github.com/jzbjyb/FLARE/tree/main).\n",
"\n",
"The basic idea is:\n",
"\n",
"- Start answering a question\n",
"- If you start generating tokens the model is uncertain about, look up relevant documents\n",
"- Use those documents to continue generating\n",
"- Repeat until finished\n",
"\n",
"There is a lot of cool detail in how the lookup of relevant documents is done.\n",
"Basically, the tokens that model is uncertain about are highlighted, and then an LLM is called to generate a question that would lead to that answer. For example, if the generated text is `Joe Biden went to Harvard`, and the tokens the model was uncertain about was `Harvard`, then a good generated question would be `where did Joe Biden go to college`. This generated question is then used in a retrieval step to fetch relevant documents.\n",
"\n",
"In order to set up this chain, we will need three things:\n",
"\n",
"- An LLM to generate the answer\n",
"- An LLM to generate hypothetical questions to use in retrieval\n",
"- A retriever to use to look up answers for\n",
"\n",
"The LLM that we use to generate the answer needs to return logprobs so we can identify uncertain tokens. For that reason, we HIGHLY recommend that you use the OpenAI wrapper (NB: not the ChatOpenAI wrapper, as that does not return logprobs).\n",
"\n",
"The LLM we use to generate hypothetical questions to use in retrieval can be anything. In this notebook we will use ChatOpenAI because it is fast and cheap.\n",
"\n",
"The retriever can be anything. In this notebook we will use [SERPER](https://serper.dev/) search engine, because it is cheap.\n",
"\n",
"Other important parameters to understand:\n",
"\n",
"- `max_generation_len`: The maximum number of tokens to generate before stopping to check if any are uncertain\n",
"- `min_prob`: Any tokens generated with probability below this will be considered uncertain"
]
},
{
"cell_type": "markdown",
"id": "a7e4b63d",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "042bb161",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"SERPER_API_KEY\"] = \"\"os.environ[\"OPENAI_API_KEY\"] = \"\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a7888f4a",
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"\n",
"import numpy as np\n",
"\n",
"from langchain.schema import BaseRetriever\n",
"from langchain.callbacks.manager import (\n",
" AsyncCallbackManagerForRetrieverRun,\n",
" CallbackManagerForRetrieverRun,\n",
")\n",
"from langchain.utilities import GoogleSerperAPIWrapper\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.llms import OpenAI\n",
"from langchain.schema import Document\n",
"from typing import Any, List"
]
},
{
"cell_type": "markdown",
"id": "5f552dce",
"metadata": {},
"source": [
"## Retriever"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "59c7d875",
"metadata": {},
"outputs": [],
"source": [
"class SerperSearchRetriever(BaseRetriever):\n",
" search: GoogleSerperAPIWrapper = None\n",
"\n",
" def _get_relevant_documents(\n",
" self, query: str, *, run_manager: CallbackManagerForRetrieverRun, **kwargs: Any\n",
" ) -> List[Document]:\n",
" return [Document(page_content=self.search.run(query))]\n",
"\n",
" async def _aget_relevant_documents(\n",
" self,\n",
" query: str,\n",
" *,\n",
" run_manager: AsyncCallbackManagerForRetrieverRun,\n",
" **kwargs: Any,\n",
" ) -> List[Document]:\n",
" raise NotImplementedError()\n",
"\n",
"\n",
"retriever = SerperSearchRetriever(search=GoogleSerperAPIWrapper())"
]
},
{
"cell_type": "markdown",
"id": "92478194",
"metadata": {},
"source": [
"## FLARE Chain"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "577e7c2c",
"metadata": {},
"outputs": [],
"source": [
"# We set this so we can see what exactly is going on\n",
"import langchain\n",
"\n",
"langchain.verbose = True"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "300d783e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import FlareChain\n",
"\n",
"flare = FlareChain.from_llm(\n",
" ChatOpenAI(temperature=0),\n",
" retriever=retriever,\n",
" max_generation_len=164,\n",
" min_prob=0.3,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "1f3d5e90",
"metadata": {},
"outputs": [],
"source": [
"query = \"explain in great detail the difference between the langchain framework and baby agi\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4b1bfa8c",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
"\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
"\n",
">>> CONTEXT: \n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> RESPONSE: \u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" decentralized platform for natural language processing\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" uses a blockchain\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" distributed ledger to\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" process data, allowing for secure and transparent data sharing.\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" set of tools\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" help developers create\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" create an AI system\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
"\n",
"Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
"\n",
"In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
"\n",
"The question to which the answer is the term/entity/phrase \" NLP applications\" is:\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[33;1m\u001b[1;3mGenerated Questions: ['What is the Langchain Framework?', 'What technology does the Langchain Framework use to store and process data for secure and transparent data sharing?', 'What technology does the Langchain Framework use to store and process data?', 'What does the Langchain Framework use a blockchain-based distributed ledger for?', 'What does the Langchain Framework provide in addition to a decentralized platform for natural language processing applications?', 'What set of tools and services does the Langchain Framework provide?', 'What is the purpose of Baby AGI?', 'What type of applications is the Langchain Framework designed for?']\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
"\n",
">>> CONTEXT: LangChain: Software. LangChain is a software development framework designed to simplify the creation of applications using large language models. LangChain Initial release date: October 2022. LangChain Programming languages: Python and JavaScript. LangChain Developer(s): Harrison Chase. LangChain License: MIT License. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... Type: Software framework. At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. LangChain is a powerful tool that can be used to work with Large Language Models (LLMs). LLMs are very general in nature, which means that while they can ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. LangChain is a software development framework designed to simplify the creation of applications using large language models (LLMs). Written in: Python and JavaScript. Initial release: October 2022. LangChain - The A.I-native developer toolkit We started LangChain with the intent to build a modular and flexible framework for developing A.I- ... LangChain explained in 3 minutes - LangChain is a ... Duration: 3:03. Posted: Apr 13, 2023. LangChain is a framework built to help you build LLM-powered applications more easily by providing you with the following:. LangChain is a framework that enables quick and easy development of applications that make use of Large Language Models, for example, GPT-3. LangChain is a powerful open-source framework for developing applications powered by language models. It connects to the AI models you want to ...\n",
"\n",
"LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Missing: secure | Must include:secure. Blockchain is the best way to secure the data of the shared community. Utilizing the capabilities of the blockchain nobody can read or interfere ... This modern technology consists of a chain of blocks that allows to securely store all committed transactions using shared and distributed ... A Blockchain network is used in the healthcare system to preserve and exchange patient data through hospitals, diagnostic laboratories, pharmacy firms, and ... In this article, I will walk you through the process of using the LangChain.js library with Google Cloud Functions, helping you leverage the ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: transparent | Must include:transparent. This technology keeps a distributed ledger on each blockchain node, making it more secure and transparent. The blockchain network can operate smart ... blockchain technology can offer a highly secured health data ledger to ... framework can be employed to store encrypted healthcare data in a ... In a simplified way, Blockchain is a data structure that stores transactions in an ordered way and linked to the previous block, serving as a ... Blockchain technology is a decentralized, distributed ledger that stores the record of ownership of digital assets. Missing: Langchain | Must include:Langchain.\n",
"\n",
"LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. This documentation covers the steps to integrate Pinecone, a high-performance vector database, with LangChain, a framework for building applications powered ... The ability to connect to any model, ingest any custom database, and build upon a framework that can take action provides numerous use cases for ... With LangChain, developers can use a framework that abstracts the core building blocks of LLM applications. LangChain empowers developers to ... Build a question-answering tool based on financial data with LangChain & Deep Lake's unified & streamable data store. Browse applications built on LangChain technology. Explore PoC and MVP applications created by our community and discover innovative use cases for LangChain ... LangChain is a great framework that can be used for developing applications powered by LLMs. When you intend to enhance your application ... In this blog, we'll introduce you to LangChain and Ray Serve and how to use them to build a search engine using LLM embeddings and a vector ... The LinkChain Framework simplifies embedding creation and storage using Pinecone and Chroma, with code that loads files, splits documents, and creates embedding ... Missing: technology | Must include:technology.\n",
"\n",
"Blockchain is one type of a distributed ledger. Distributed ledgers use independent computers (referred to as nodes) to record, share and ... Missing: Langchain | Must include:Langchain. Blockchain is used in distributed storage software where huge data is broken down into chunks. This is available in encrypted data across a ... People sometimes use the terms 'Blockchain' and 'Distributed Ledger' interchangeably. This post aims to analyze the features of each. A distributed ledger ... Missing: Framework | Must include:Framework. Think of a “distributed ledger” that uses cryptography to allow each participant in the transaction to add to the ledger in a secure way without ... In this paper, we provide an overview of the history of trade settlement and discuss this nascent technology that may now transform traditional ... Missing: Langchain | Must include:Langchain. LangChain is a blockchain-based language education platform that aims to revolutionize the way people learn languages. Missing: Framework | Must include:Framework. It uses the distributed ledger technology framework and Smart contract engine for building scalable Business Blockchain applications. The fabric ... It looks at the assets the use case is handling, the different parties conducting transactions, and the smart contract, distributed ... Are you curious to know how Blockchain and Distributed ... Duration: 44:31. Posted: May 4, 2021. A blockchain is a distributed and immutable ledger to transfer ownership, record transactions, track assets, and ensure transparency, security, trust and value ... Missing: Langchain | Must include:Langchain.\n",
"\n",
"LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: decentralized | Must include:decentralized. LangChain, created by Harrison Chase, is a Python library that provides out-of-the-box support to build NLP applications using LLMs. Missing: decentralized | Must include:decentralized. LangChain provides a standard interface for chains, enabling developers to create sequences of calls that go beyond a single LLM call. Chains ... Missing: decentralized platform natural. LangChain is a powerful framework that simplifies the process of building advanced language model applications. Missing: platform | Must include:platform. Are your language models ignoring previous instructions ... Duration: 32:23. Posted: Feb 21, 2023. LangChain is a framework that enables quick and easy development of applications ... Prompting is the new way of programming NLP models. Missing: decentralized platform. It then uses natural language processing and machine learning algorithms to search ... Summarization is handled via cohere, QnA is handled via langchain, ... LangChain is a framework for developing applications powered by language models. ... There are several main modules that LangChain provides support for. Missing: decentralized platform. In the healthcare-chain system, blockchain provides an appreciated secure ... The entire process of adding new and previous block data is performed based on ... ChatGPT is a large language model developed by OpenAI, ... tool for a wide range of applications, including natural language processing, ...\n",
"\n",
"LangChain is a powerful tool that can be used to work with Large Language ... If an API key has been provided, create an OpenAI language model instance At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. A tutorial of the six core modules of the LangChain Python package covering models, prompts, chains, agents, indexes, and memory with OpenAI ... LangChain's collection of tools refers to a set of tools provided by the LangChain framework for developing applications powered by language models. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... LangChain is an open-source library that provides developers with the tools to build applications powered by large language models (LLMs). LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Plan-and-Execute Agents · Feature Stores and LLMs · Structured Tools · Auto-Evaluator Opportunities · Callbacks Improvements · Unleashing the power ... Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. · LLM: The language model ... LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.\n",
"\n",
"Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. This system is exploring and demonstrating to us the potential of large language models, such as GPT and how it can autonomously perform tasks. Apr 17, 2023\n",
"\n",
"At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
">>> RESPONSE: \u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' LangChain is a framework for developing applications powered by language models. It provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications. On the other hand, Baby AGI is an AI system that is exploring and demonstrating the potential of large language models, such as GPT, and how it can autonomously perform tasks. Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. '"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"flare.run(query)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "7bed8944",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\n\\nThe Langchain framework and Baby AGI are both artificial intelligence (AI) frameworks that are used to create intelligent agents. The Langchain framework is a supervised learning system that is based on the concept of “language chains”. It uses a set of rules to map natural language inputs to specific outputs. It is a general-purpose AI framework and can be used to build applications such as natural language processing (NLP), chatbots, and more.\\n\\nBaby AGI, on the other hand, is an unsupervised learning system that uses neural networks and reinforcement learning to learn from its environment. It is used to create intelligent agents that can adapt to changing environments. It is a more advanced AI system and can be used to build more complex applications such as game playing, robotic vision, and more.\\n\\nThe main difference between the two is that the Langchain framework uses supervised learning while Baby AGI uses unsupervised learning. The Langchain framework is a general-purpose AI framework that can be used for various applications, while Baby AGI is a more advanced AI system that can be used to create more complex applications.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm = OpenAI()\n",
"llm(query)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "8fb76286",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
"\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
"\n",
">>> CONTEXT: \n",
">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
">>> RESPONSE: \u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"\n",
"Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
"\n",
"FINISHED\n",
"\n",
"The question to which the answer is the term/entity/phrase \" very different origin\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"\n",
"Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
"\n",
"FINISHED\n",
"\n",
"The question to which the answer is the term/entity/phrase \" 2020 by a\" is:\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
"\n",
">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
">>> EXISTING PARTIAL RESPONSE: \n",
"\n",
"Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
"\n",
"FINISHED\n",
"\n",
"The question to which the answer is the term/entity/phrase \" developers as a platform for creating and managing decentralized language learning applications.\" is:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[33;1m\u001b[1;3mGenerated Questions: ['How would you describe the origin stories of Langchain and Bitcoin in terms of their similarities or differences?', 'When was Langchain created and by whom?', 'What was the purpose of creating Langchain?']\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
"\n",
">>> CONTEXT: Bitcoin and Ethereum have many similarities but different long-term visions and limitations. Ethereum changed from proof of work to proof of ... Bitcoin will be around for many years and examining its white paper origins is a great exercise in understanding why. Satoshi Nakamoto's blueprint describes ... Bitcoin is a new currency that was created in 2009 by an unknown person using the alias Satoshi Nakamoto. Transactions are made with no middle men – meaning, no ... Missing: Langchain | Must include:Langchain. By comparison, Bitcoin transaction speeds are tremendously lower. ... learn about its history and its role in the emergence of the Bitcoin ... LangChain is a powerful framework that simplifies the process of ... tasks like document retrieval, clustering, and similarity comparisons. Key terms: Bitcoin System, Blockchain Technology, ... Furthermore, the research paper will discuss and compare the five payment. Blockchain first appeared in Nakamoto's Bitcoin white paper that describes a new decentralized cryptocurrency [1]. Bitcoin takes the blockchain technology ... Missing: stories | Must include:stories. A score of 0 means there were not enough data for this term. Google trends was accessed on 5 November 2018 with searches for bitcoin, euro, gold ... Contracts, transactions, and records of them provide critical structure in our economic system, but they haven't kept up with the world's digital ... Missing: Langchain | Must include:Langchain. Of course, traders try to make a profit on their portfolio in this way.The difference between investing and trading is the regularity with which ...\n",
"\n",
"After all these giant leaps forward in the LLM space, OpenAI released ChatGPT — thrusting LLMs into the spotlight. LangChain appeared around the same time. Its creator, Harrison Chase, made the first commit in late October 2022. Leaving a short couple of months of development before getting caught in the LLM wave.\n",
"\n",
"At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
">>> RESPONSE: \u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' The origin stories of LangChain and Bitcoin are quite different. Bitcoin was created in 2009 by an unknown person using the alias Satoshi Nakamoto. LangChain was created in late October 2022 by Harrison Chase. Bitcoin is a decentralized cryptocurrency, while LangChain is a framework built around LLMs. '"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"flare.run(\"how are the origin stories of langchain and bitcoin similar or different?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fbadd022",
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

994
cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb Normal file
View File

@@ -0,0 +1,994 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e9732067-71c7-46f7-ad09-381b3bf21a27",
"metadata": {},
"source": [
"# Generative Agents in LangChain\n",
"\n",
"This notebook implements a generative agent based on the paper [Generative Agents: Interactive Simulacra of Human Behavior](https://arxiv.org/abs/2304.03442) by Park, et. al.\n",
"\n",
"In it, we leverage a time-weighted Memory object backed by a LangChain Retriever."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "53f81c37-db45-4fdc-843c-aa8fd2a9e99d",
"metadata": {},
"outputs": [],
"source": [
"# Use termcolor to make it easy to colorize the outputs.\n",
"!pip install termcolor > /dev/null"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3128fc21",
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"\n",
"logging.basicConfig(level=logging.ERROR)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8851c370-b395-4b80-a79d-486a38ffc244",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from datetime import datetime, timedelta\n",
"from typing import List\n",
"from termcolor import colored\n",
"\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.docstore import InMemoryDocstore\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.retrievers import TimeWeightedVectorStoreRetriever\n",
"from langchain.vectorstores import FAISS"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "81824e76",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"USER_NAME = \"Person A\" # The name you want to use when interviewing the agent.\n",
"LLM = ChatOpenAI(max_tokens=1500) # Can be any LLM you want."
]
},
{
"cell_type": "markdown",
"id": "c3da1649-d88f-4973-b655-7042975cde7e",
"metadata": {},
"source": [
"### Generative Agent Memory Components\n",
"\n",
"This tutorial highlights the memory of generative agents and its impact on their behavior. The memory varies from standard LangChain Chat memory in two aspects:\n",
"\n",
"1. **Memory Formation**\n",
"\n",
" Generative Agents have extended memories, stored in a single stream:\n",
" 1. Observations - from dialogues or interactions with the virtual world, about self or others\n",
" 2. Reflections - resurfaced and summarized core memories\n",
"\n",
"\n",
"2. **Memory Recall**\n",
"\n",
" Memories are retrieved using a weighted sum of salience, recency, and importance.\n",
"\n",
"You can review the definitions of the `GenerativeAgent` and `GenerativeAgentMemory` in the [reference documentation](\"https://api.python.langchain.com/en/latest/modules/experimental.html\") for the following imports, focusing on `add_memory` and `summarize_related_memories` methods."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "043e5203-6a41-431c-9efa-3e1743d7d25a",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain_experimental.generative_agents import (\n",
" GenerativeAgent,\n",
" GenerativeAgentMemory,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "361bd49e",
"metadata": {
"jp-MarkdownHeadingCollapsed": true,
"tags": []
},
"source": [
"## Memory Lifecycle\n",
"\n",
"Summarizing the key methods in the above: `add_memory` and `summarize_related_memories`.\n",
"\n",
"When an agent makes an observation, it stores the memory:\n",
" \n",
"1. Language model scores the memory's importance (1 for mundane, 10 for poignant)\n",
"2. Observation and importance are stored within a document by TimeWeightedVectorStoreRetriever, with a `last_accessed_time`.\n",
"\n",
"When an agent responds to an observation:\n",
"\n",
"1. Generates query(s) for retriever, which fetches documents based on salience, recency, and importance.\n",
"2. Summarizes the retrieved information\n",
"3. Updates the `last_accessed_time` for the used documents.\n"
]
},
{
"cell_type": "markdown",
"id": "2fa3ca02",
"metadata": {},
"source": [
"## Create a Generative Character\n",
"\n",
"\n",
"\n",
"Now that we've walked through the definition, we will create two characters named \"Tommie\" and \"Eve\"."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ee9c1a1d-c311-4f1c-8131-75fccd9025b1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import math\n",
"import faiss\n",
"\n",
"\n",
"def relevance_score_fn(score: float) -> float:\n",
" \"\"\"Return a similarity score on a scale [0, 1].\"\"\"\n",
" # This will differ depending on a few things:\n",
" # - the distance / similarity metric used by the VectorStore\n",
" # - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)\n",
" # This function converts the euclidean norm of normalized embeddings\n",
" # (0 is most similar, sqrt(2) most dissimilar)\n",
" # to a similarity function (0 to 1)\n",
" return 1.0 - score / math.sqrt(2)\n",
"\n",
"\n",
"def create_new_memory_retriever():\n",
" \"\"\"Create a new vector store retriever unique to the agent.\"\"\"\n",
" # Define your embedding model\n",
" embeddings_model = OpenAIEmbeddings()\n",
" # Initialize the vectorstore as empty\n",
" embedding_size = 1536\n",
" index = faiss.IndexFlatL2(embedding_size)\n",
" vectorstore = FAISS(\n",
" embeddings_model.embed_query,\n",
" index,\n",
" InMemoryDocstore({}),\n",
" {},\n",
" relevance_score_fn=relevance_score_fn,\n",
" )\n",
" return TimeWeightedVectorStoreRetriever(\n",
" vectorstore=vectorstore, other_score_keys=[\"importance\"], k=15\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7884f9dd-c597-4c27-8c77-1402c71bc2f8",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"tommies_memory = GenerativeAgentMemory(\n",
" llm=LLM,\n",
" memory_retriever=create_new_memory_retriever(),\n",
" verbose=False,\n",
" reflection_threshold=8, # we will give this a relatively low number to show how reflection works\n",
")\n",
"\n",
"tommie = GenerativeAgent(\n",
" name=\"Tommie\",\n",
" age=25,\n",
" traits=\"anxious, likes design, talkative\", # You can add more persistent traits here\n",
" status=\"looking for a job\", # When connected to a virtual world, we can have the characters update their status\n",
" memory_retriever=create_new_memory_retriever(),\n",
" llm=LLM,\n",
" memory=tommies_memory,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c524d529",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Name: Tommie (age: 25)\n",
"Innate traits: anxious, likes design, talkative\n",
"No information about Tommie's core characteristics is provided in the given statements.\n"
]
}
],
"source": [
"# The current \"Summary\" of a character can't be made because the agent hasn't made\n",
"# any observations yet.\n",
"print(tommie.get_summary())"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4be60979-d56e-4abf-a636-b34ffa8b7fba",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# We can add memories directly to the memory object\n",
"tommie_observations = [\n",
" \"Tommie remembers his dog, Bruno, from when he was a kid\",\n",
" \"Tommie feels tired from driving so far\",\n",
" \"Tommie sees the new home\",\n",
" \"The new neighbors have a cat\",\n",
" \"The road is noisy at night\",\n",
" \"Tommie is hungry\",\n",
" \"Tommie tries to get some rest.\",\n",
"]\n",
"for observation in tommie_observations:\n",
" tommie.memory.add_memory(observation)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "6992b48b-697f-4973-9560-142ef85357d7",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Name: Tommie (age: 25)\n",
"Innate traits: anxious, likes design, talkative\n",
"Tommie is a person who is observant of his surroundings, has a sentimental side, and experiences basic human needs such as hunger and the need for rest. He also tends to get tired easily and is affected by external factors such as noise from the road or a neighbor's pet.\n"
]
}
],
"source": [
"# Now that Tommie has 'memories', their self-summary is more descriptive, though still rudimentary.\n",
"# We will see how this summary updates after more observations to create a more rich description.\n",
"print(tommie.get_summary(force_refresh=True))"
]
},
{
"cell_type": "markdown",
"id": "40d39a32-838c-4a03-8b27-a52c76c402e7",
"metadata": {
"tags": []
},
"source": [
"## Pre-Interview with Character\n",
"\n",
"Before sending our character on their way, let's ask them a few questions."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "eaf125d8-f54c-4c5f-b6af-32789b1f7d3a",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"def interview_agent(agent: GenerativeAgent, message: str) -> str:\n",
" \"\"\"Help the notebook user interact with the agent.\"\"\"\n",
" new_message = f\"{USER_NAME} says {message}\"\n",
" return agent.generate_dialogue_response(new_message)[1]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "54024d41-6e83-4914-91e5-73140e2dd9c8",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"I really enjoy design and being creative. I\\'ve been working on some personal projects lately. What about you, Person A? What do you like to do?\"'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"What do you like to do?\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "71e2e8cc-921e-4816-82f1-66962b2c1055",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"Well, I\\'m actually looking for a job right now, so hopefully I can find some job postings online and start applying. How about you, Person A? What\\'s on your schedule for today?\"'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"What are you looking forward to doing today?\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a2521ffc-7050-4ac3-9a18-4cccfc798c31",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"Honestly, I\\'m feeling pretty anxious about finding a job. It\\'s been a bit of a struggle lately, but I\\'m trying to stay positive and keep searching. How about you, Person A? What worries you?\"'"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"What are you most worried about today?\")"
]
},
{
"cell_type": "markdown",
"id": "e509c468-f7cd-4d72-9f3a-f4aba28b1eea",
"metadata": {},
"source": [
"## Step through the day's observations."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "154dee3d-bfe0-4828-b963-ed7e885799b3",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Let's have Tommie start going through a day in the life.\n",
"observations = [\n",
" \"Tommie wakes up to the sound of a noisy construction site outside his window.\",\n",
" \"Tommie gets out of bed and heads to the kitchen to make himself some coffee.\",\n",
" \"Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\",\n",
" \"Tommie finally finds the filters and makes himself a cup of coffee.\",\n",
" \"The coffee tastes bitter, and Tommie regrets not buying a better brand.\",\n",
" \"Tommie checks his email and sees that he has no job offers yet.\",\n",
" \"Tommie spends some time updating his resume and cover letter.\",\n",
" \"Tommie heads out to explore the city and look for job openings.\",\n",
" \"Tommie sees a sign for a job fair and decides to attend.\",\n",
" \"The line to get in is long, and Tommie has to wait for an hour.\",\n",
" \"Tommie meets several potential employers at the job fair but doesn't receive any offers.\",\n",
" \"Tommie leaves the job fair feeling disappointed.\",\n",
" \"Tommie stops by a local diner to grab some lunch.\",\n",
" \"The service is slow, and Tommie has to wait for 30 minutes to get his food.\",\n",
" \"Tommie overhears a conversation at the next table about a job opening.\",\n",
" \"Tommie asks the diners about the job opening and gets some information about the company.\",\n",
" \"Tommie decides to apply for the job and sends his resume and cover letter.\",\n",
" \"Tommie continues his search for job openings and drops off his resume at several local businesses.\",\n",
" \"Tommie takes a break from his job search to go for a walk in a nearby park.\",\n",
" \"A dog approaches and licks Tommie's feet, and he pets it for a few minutes.\",\n",
" \"Tommie sees a group of people playing frisbee and decides to join in.\",\n",
" \"Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\",\n",
" \"Tommie goes back to his apartment to rest for a bit.\",\n",
" \"A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\",\n",
" \"Tommie starts to feel frustrated with his job search.\",\n",
" \"Tommie calls his best friend to vent about his struggles.\",\n",
" \"Tommie's friend offers some words of encouragement and tells him to keep trying.\",\n",
" \"Tommie feels slightly better after talking to his friend.\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "238be49c-edb3-4e26-a2b6-98777ba8de86",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32mTommie wakes up to the sound of a noisy construction site outside his window.\u001b[0m Tommie groans and covers his head with a pillow, trying to block out the noise.\n",
"\u001b[32mTommie gets out of bed and heads to the kitchen to make himself some coffee.\u001b[0m Tommie stretches his arms and yawns before starting to make the coffee.\n",
"\u001b[32mTommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\u001b[0m Tommie sighs in frustration and continues searching through the boxes.\n",
"\u001b[32mTommie finally finds the filters and makes himself a cup of coffee.\u001b[0m Tommie takes a deep breath and enjoys the aroma of the fresh coffee.\n",
"\u001b[32mThe coffee tastes bitter, and Tommie regrets not buying a better brand.\u001b[0m Tommie grimaces and sets the coffee mug aside.\n",
"\u001b[32mTommie checks his email and sees that he has no job offers yet.\u001b[0m Tommie sighs and closes his laptop, feeling discouraged.\n",
"\u001b[32mTommie spends some time updating his resume and cover letter.\u001b[0m Tommie nods, feeling satisfied with his progress.\n",
"\u001b[32mTommie heads out to explore the city and look for job openings.\u001b[0m Tommie feels a surge of excitement and anticipation as he steps out into the city.\n",
"\u001b[32mTommie sees a sign for a job fair and decides to attend.\u001b[0m Tommie feels hopeful and excited about the possibility of finding job opportunities at the job fair.\n",
"\u001b[32mThe line to get in is long, and Tommie has to wait for an hour.\u001b[0m Tommie taps his foot impatiently and checks his phone for the time.\n",
"\u001b[32mTommie meets several potential employers at the job fair but doesn't receive any offers.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
"\u001b[32mTommie leaves the job fair feeling disappointed.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
"\u001b[32mTommie stops by a local diner to grab some lunch.\u001b[0m Tommie feels relieved to take a break and satisfy his hunger.\n",
"\u001b[32mThe service is slow, and Tommie has to wait for 30 minutes to get his food.\u001b[0m Tommie feels frustrated and impatient due to the slow service.\n",
"\u001b[32mTommie overhears a conversation at the next table about a job opening.\u001b[0m Tommie feels a surge of hope and excitement at the possibility of a job opportunity but decides not to interfere with the conversation at the next table.\n",
"\u001b[32mTommie asks the diners about the job opening and gets some information about the company.\u001b[0m Tommie said \"Excuse me, I couldn't help but overhear your conversation about the job opening. Could you give me some more information about the company?\"\n",
"\u001b[32mTommie decides to apply for the job and sends his resume and cover letter.\u001b[0m Tommie feels hopeful and proud of himself for taking action towards finding a job.\n",
"\u001b[32mTommie continues his search for job openings and drops off his resume at several local businesses.\u001b[0m Tommie feels hopeful and determined to keep searching for job opportunities.\n",
"\u001b[32mTommie takes a break from his job search to go for a walk in a nearby park.\u001b[0m Tommie feels refreshed and rejuvenated after taking a break in the park.\n",
"\u001b[32mA dog approaches and licks Tommie's feet, and he pets it for a few minutes.\u001b[0m Tommie feels happy and enjoys the brief interaction with the dog.\n",
"****************************************\n",
"\u001b[34mAfter 20 observations, Tommie's summary is:\n",
"Name: Tommie (age: 25)\n",
"Innate traits: anxious, likes design, talkative\n",
"Tommie is determined and hopeful in his search for job opportunities, despite encountering setbacks and disappointments. He is also able to take breaks and care for his physical needs, such as getting rest and satisfying his hunger. Tommie is nostalgic towards his past, as shown by his memory of his childhood dog. Overall, Tommie is a hardworking and resilient individual who remains focused on his goals.\u001b[0m\n",
"****************************************\n",
"\u001b[32mTommie sees a group of people playing frisbee and decides to join in.\u001b[0m Do nothing.\n",
"\u001b[32mTommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\u001b[0m Tommie feels pain and puts a hand to his nose to check for any injury.\n",
"\u001b[32mTommie goes back to his apartment to rest for a bit.\u001b[0m Tommie feels relieved to take a break and rest for a bit.\n",
"\u001b[32mA raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\u001b[0m Tommie feels annoyed and frustrated at the mess caused by the raccoon.\n",
"\u001b[32mTommie starts to feel frustrated with his job search.\u001b[0m Tommie feels discouraged but remains determined to keep searching for job opportunities.\n",
"\u001b[32mTommie calls his best friend to vent about his struggles.\u001b[0m Tommie said \"Hey, can I talk to you for a bit? I'm feeling really frustrated with my job search.\"\n",
"\u001b[32mTommie's friend offers some words of encouragement and tells him to keep trying.\u001b[0m Tommie said \"Thank you, I really appreciate your support and encouragement.\"\n",
"\u001b[32mTommie feels slightly better after talking to his friend.\u001b[0m Tommie feels grateful for his friend's support.\n"
]
}
],
"source": [
"# Let's send Tommie on their way. We'll check in on their summary every few observations to watch it evolve\n",
"for i, observation in enumerate(observations):\n",
" _, reaction = tommie.generate_reaction(observation)\n",
" print(colored(observation, \"green\"), reaction)\n",
" if ((i + 1) % 20) == 0:\n",
" print(\"*\" * 40)\n",
" print(\n",
" colored(\n",
" f\"After {i+1} observations, Tommie's summary is:\\n{tommie.get_summary(force_refresh=True)}\",\n",
" \"blue\",\n",
" )\n",
" )\n",
" print(\"*\" * 40)"
]
},
{
"cell_type": "markdown",
"id": "dd62a275-7290-43ca-aa0f-504f3a706d09",
"metadata": {},
"source": [
"## Interview after the day"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "6336ab5d-3074-4831-951f-c9e2cba5dfb5",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"It\\'s been a bit of a rollercoaster, to be honest. I\\'ve had some setbacks in my job search, but I also had some good moments today, like sending out a few resumes and meeting some potential employers at a job fair. How about you?\"'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"Tell me about how your day has been going\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "809ac906-69b7-4326-99ec-af638d32bb20",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"I really enjoy coffee, but sometimes I regret not buying a better brand. How about you?\"'"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"How do you feel about coffee?\")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "f733a431-19ea-421a-9101-ae2593a8c626",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"Oh, I had a dog named Bruno when I was a kid. He was a golden retriever and my best friend. I have so many fond memories of him.\"'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"Tell me about your childhood dog!\")"
]
},
{
"cell_type": "markdown",
"id": "c9261428-778a-4c0b-b725-bc9e91b71391",
"metadata": {},
"source": [
"## Adding Multiple Characters\n",
"\n",
"Let's add a second character to have a conversation with Tommie. Feel free to configure different traits."
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "ec8bbe18-a021-419c-bf1f-23d34732cd99",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"eves_memory = GenerativeAgentMemory(\n",
" llm=LLM,\n",
" memory_retriever=create_new_memory_retriever(),\n",
" verbose=False,\n",
" reflection_threshold=5,\n",
")\n",
"\n",
"\n",
"eve = GenerativeAgent(\n",
" name=\"Eve\",\n",
" age=34,\n",
" traits=\"curious, helpful\", # You can add more persistent traits here\n",
" status=\"N/A\", # When connected to a virtual world, we can have the characters update their status\n",
" llm=LLM,\n",
" daily_summaries=[\n",
" (\n",
" \"Eve started her new job as a career counselor last week and received her first assignment, a client named Tommie.\"\n",
" )\n",
" ],\n",
" memory=eves_memory,\n",
" verbose=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "1e2745f5-e0da-4abd-98b4-830802ce6698",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"yesterday = (datetime.now() - timedelta(days=1)).strftime(\"%A %B %d\")\n",
"eve_observations = [\n",
" \"Eve wakes up and hear's the alarm\",\n",
" \"Eve eats a boal of porridge\",\n",
" \"Eve helps a coworker on a task\",\n",
" \"Eve plays tennis with her friend Xu before going to work\",\n",
" \"Eve overhears her colleague say something about Tommie being hard to work with\",\n",
"]\n",
"for observation in eve_observations:\n",
" eve.memory.add_memory(observation)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "de4726e3-4bb1-47da-8fd9-f317a036fe0f",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Name: Eve (age: 34)\n",
"Innate traits: curious, helpful\n",
"Eve is a helpful and active person who enjoys sports and takes care of her physical health. She is attentive to her surroundings, including her colleagues, and has good time management skills.\n"
]
}
],
"source": [
"print(eve.get_summary())"
]
},
{
"cell_type": "markdown",
"id": "837524e9-7f7e-4e9f-b610-f454062f5915",
"metadata": {},
"source": [
"## Pre-conversation interviews\n",
"\n",
"\n",
"Let's \"Interview\" Eve before she speaks with Tommie."
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "6cda916d-800c-47bc-a7f9-6a2f19187472",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"I\\'m feeling pretty good, thanks for asking! Just trying to stay productive and make the most of the day. How about you?\"'"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(eve, \"How are you feeling about today?\")"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "448ae644-0a66-4eb2-a03a-319f36948b37",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"I don\\'t know much about Tommie, but I heard someone mention that they find them difficult to work with. Have you had any experiences working with Tommie?\"'"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(eve, \"What do you know about Tommie?\")"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "493fc5b8-8730-4ef8-9820-0f1769ce1691",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"That\\'s interesting. I don\\'t know much about Tommie\\'s work experience, but I would probably ask about his strengths and areas for improvement. What about you?\"'"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(\n",
" eve,\n",
" \"Tommie is looking to find a job. What are are some things you'd like to ask him?\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "4b46452a-6c54-4db2-9d87-18597f70fec8",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"Sure, I can keep the conversation going and ask plenty of questions. I want to make sure Tommie feels comfortable and supported. Thanks for letting me know.\"'"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(\n",
" eve,\n",
" \"You'll have to ask him. He may be a bit anxious, so I'd appreciate it if you keep the conversation going and ask as many questions as possible.\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "dd780655-1d73-4fcb-a78d-79fd46a20636",
"metadata": {},
"source": [
"## Dialogue between Generative Agents\n",
"\n",
"Generative agents are much more complex when they interact with a virtual environment or with each other. Below, we run a simple conversation between Tommie and Eve."
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "042ea271-4bf1-4247-9082-239a6fea43b8",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"def run_conversation(agents: List[GenerativeAgent], initial_observation: str) -> None:\n",
" \"\"\"Runs a conversation between agents.\"\"\"\n",
" _, observation = agents[1].generate_reaction(initial_observation)\n",
" print(observation)\n",
" turns = 0\n",
" while True:\n",
" break_dialogue = False\n",
" for agent in agents:\n",
" stay_in_dialogue, observation = agent.generate_dialogue_response(\n",
" observation\n",
" )\n",
" print(observation)\n",
" # observation = f\"{agent.name} said {reaction}\"\n",
" if not stay_in_dialogue:\n",
" break_dialogue = True\n",
" if break_dialogue:\n",
" break\n",
" turns += 1"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "d5462b14-218e-4d85-b035-df57ea8e0f80",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Eve said \"Sure, Tommie. I'd be happy to share about my experience. Where would you like me to start?\"\n",
"Tommie said \"That's great, thank you! How about you start by telling me about your previous work experience?\"\n",
"Eve said \"Sure, I'd be happy to share my previous work experience with you. I've worked in a few different industries, including marketing and event planning. What specific questions do you have for me?\"\n",
"Tommie said \"That's great to hear. Can you tell me more about your experience in event planning? I've always been interested in that field.\"\n",
"Eve said \"Sure, I'd be happy to share about my experience in event planning. I've worked on a variety of events, from corporate conferences to weddings. One of the biggest challenges I faced was managing multiple vendors and ensuring everything ran smoothly on the day of the event. What specific questions do you have?\"\n",
"Tommie said \"That sounds like a lot of responsibility! Can you tell me more about how you handled the challenges that came up during those events?\"\n",
"Eve said \"Sure, Tommie. I'd be happy to share with you how I handled those challenges. One approach that worked well for me was to stay organized and create a detailed timeline for the event. This helped me keep track of all the different tasks that needed to be done and when they needed to be completed. I also made sure to communicate clearly with all the vendors and team members involved in the event to ensure everyone was on the same page. Would you like me to go into more detail?\"\n",
"Tommie said \"Thank you for sharing that with me, Eve. That sounds like a great approach to managing events. Can you tell me more about how you handled any unexpected issues that came up during the events?\"\n",
"Eve said \"Of course, Tommie. One example of an unexpected issue I faced was when one of the vendors didn't show up on time. To handle this, I quickly contacted a backup vendor and was able to get everything back on track. It's always important to have a backup plan in case things don't go as planned. Do you have any other questions about event planning?\"\n",
"Tommie said \"Thank you for sharing that with me, Eve. It's really helpful to hear how you handled unexpected issues like that. Can you give me an example of how you communicated with your team to ensure everyone was on the same page during an event?\"\n",
"Eve said \"Sure, Tommie. One thing I did to ensure everyone was on the same page was to have regular check-ins and meetings with the team leading up to the event. This helped us address any issues or concerns early on and make sure everyone was clear on their roles and responsibilities. Have you ever had to manage a team for an event before?\"\n",
"Tommie said \"That's a great idea, Eve. I haven't had the opportunity to manage a team for an event yet, but I'll definitely keep that in mind for the future. Thank you for sharing your experience with me.\"\n",
"Eve said \"Thanks for the opportunity to share my experience, Tommie. It was great meeting with you today.\"\n"
]
}
],
"source": [
"agents = [tommie, eve]\n",
"run_conversation(\n",
" agents,\n",
" \"Tommie said: Hi, Eve. Thanks for agreeing to meet with me today. I have a bunch of questions and am not sure where to start. Maybe you could first share about your experience?\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "1b28fe80-03dc-4399-961d-6e9ee1980216",
"metadata": {
"tags": []
},
"source": [
"## Let's interview our agents after their conversation\n",
"\n",
"Since the generative agents retain their memories from the day, we can ask them about their plans, conversations, and other memoreis."
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "c4d252f3-fcc1-474c-846e-a7605a6b4ce7",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Name: Tommie (age: 25)\n",
"Innate traits: anxious, likes design, talkative\n",
"Tommie is determined and hopeful in his job search, but can also feel discouraged and frustrated at times. He has a strong connection to his childhood dog, Bruno. Tommie seeks support from his friends when feeling overwhelmed and is grateful for their help. He also enjoys exploring his new city.\n"
]
}
],
"source": [
"# We can see a current \"Summary\" of a character based on their own perception of self\n",
"# has changed\n",
"print(tommie.get_summary(force_refresh=True))"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "c04db9a4",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Name: Eve (age: 34)\n",
"Innate traits: curious, helpful\n",
"Eve is a helpful and friendly person who enjoys playing sports and staying productive. She is attentive and responsive to others' needs, actively listening and asking questions to understand their perspectives. Eve has experience in event planning and communication, and is willing to share her knowledge and expertise with others. She values teamwork and collaboration, and strives to create a comfortable and supportive environment for everyone.\n"
]
}
],
"source": [
"print(eve.get_summary(force_refresh=True))"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "71762558-8fb6-44d7-8483-f5b47fb2a862",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Tommie said \"It was really helpful actually. Eve shared some great tips on managing events and handling unexpected issues. I feel like I learned a lot from her experience.\"'"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(tommie, \"How was your conversation with Eve?\")"
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "085af3d8-ac21-41ea-8f8b-055c56976a67",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"It was great, thanks for asking. Tommie was very receptive and had some great questions about event planning. How about you, have you had any interactions with Tommie?\"'"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(eve, \"How was your conversation with Tommie?\")"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "5b439f3c-7849-4432-a697-2bcc85b89dae",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'Eve said \"It was great meeting with you, Tommie. If you have any more questions or need any help in the future, don\\'t hesitate to reach out to me. Have a great day!\"'"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interview_agent(eve, \"What do you wish you would have said to Tommie?\")"
]
}
],
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

245
cookbook/gymnasium_agent_simulation.ipynb Normal file
View File

@@ -0,0 +1,245 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "4b089493",
"metadata": {},
"source": [
"# Simulated Environment: Gymnasium\n",
"\n",
"For many applications of LLM agents, the environment is real (internet, database, REPL, etc). However, we can also define agents to interact in simulated environments like text-based games. This is an example of how to create a simple agent-environment interaction loop with [Gymnasium](https://github.com/Farama-Foundation/Gymnasium) (formerly [OpenAI Gym](https://github.com/openai/gym))."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f36427cf",
"metadata": {},
"outputs": [],
"source": [
"!pip install gymnasium"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f9bd38b4",
"metadata": {},
"outputs": [],
"source": [
"import gymnasium as gym\n",
"import inspect\n",
"import tenacity\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")\n",
"from langchain.output_parsers import RegexParser"
]
},
{
"cell_type": "markdown",
"id": "e222e811",
"metadata": {},
"source": [
"## Define the agent"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "870c24bc",
"metadata": {},
"outputs": [],
"source": [
"class GymnasiumAgent:\n",
" @classmethod\n",
" def get_docs(cls, env):\n",
" return env.unwrapped.__doc__\n",
"\n",
" def __init__(self, model, env):\n",
" self.model = model\n",
" self.env = env\n",
" self.docs = self.get_docs(env)\n",
"\n",
" self.instructions = \"\"\"\n",
"Your goal is to maximize your return, i.e. the sum of the rewards you receive.\n",
"I will give you an observation, reward, terminiation flag, truncation flag, and the return so far, formatted as:\n",
"\n",
"Observation: <observation>\n",
"Reward: <reward>\n",
"Termination: <termination>\n",
"Truncation: <truncation>\n",
"Return: <sum_of_rewards>\n",
"\n",
"You will respond with an action, formatted as:\n",
"\n",
"Action: <action>\n",
"\n",
"where you replace <action> with your actual action.\n",
"Do nothing else but return the action.\n",
"\"\"\"\n",
" self.action_parser = RegexParser(\n",
" regex=r\"Action: (.*)\", output_keys=[\"action\"], default_output_key=\"action\"\n",
" )\n",
"\n",
" self.message_history = []\n",
" self.ret = 0\n",
"\n",
" def random_action(self):\n",
" action = self.env.action_space.sample()\n",
" return action\n",
"\n",
" def reset(self):\n",
" self.message_history = [\n",
" SystemMessage(content=self.docs),\n",
" SystemMessage(content=self.instructions),\n",
" ]\n",
"\n",
" def observe(self, obs, rew=0, term=False, trunc=False, info=None):\n",
" self.ret += rew\n",
"\n",
" obs_message = f\"\"\"\n",
"Observation: {obs}\n",
"Reward: {rew}\n",
"Termination: {term}\n",
"Truncation: {trunc}\n",
"Return: {self.ret}\n",
" \"\"\"\n",
" self.message_history.append(HumanMessage(content=obs_message))\n",
" return obs_message\n",
"\n",
" def _act(self):\n",
" act_message = self.model(self.message_history)\n",
" self.message_history.append(act_message)\n",
" action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
" return action\n",
"\n",
" def act(self):\n",
" try:\n",
" for attempt in tenacity.Retrying(\n",
" stop=tenacity.stop_after_attempt(2),\n",
" wait=tenacity.wait_none(), # No waiting time between retries\n",
" retry=tenacity.retry_if_exception_type(ValueError),\n",
" before_sleep=lambda retry_state: print(\n",
" f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
" ),\n",
" ):\n",
" with attempt:\n",
" action = self._act()\n",
" except tenacity.RetryError as e:\n",
" action = self.random_action()\n",
" return action"
]
},
{
"cell_type": "markdown",
"id": "2e76d22c",
"metadata": {},
"source": [
"## Initialize the simulated environment and agent"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "9e902cfd",
"metadata": {},
"outputs": [],
"source": [
"env = gym.make(\"Blackjack-v1\")\n",
"agent = GymnasiumAgent(model=ChatOpenAI(temperature=0.2), env=env)"
]
},
{
"cell_type": "markdown",
"id": "e2c12b15",
"metadata": {},
"source": [
"## Main loop"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ad361210",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: (15, 4, 0)\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: (25, 4, 0)\n",
"Reward: -1.0\n",
"Termination: True\n",
"Truncation: False\n",
"Return: -1.0\n",
" \n",
"break True False\n"
]
}
],
"source": [
"observation, info = env.reset()\n",
"agent.reset()\n",
"\n",
"obs_message = agent.observe(observation)\n",
"print(obs_message)\n",
"\n",
"while True:\n",
" action = agent.act()\n",
" observation, reward, termination, truncation, info = env.step(action)\n",
" obs_message = agent.observe(observation, reward, termination, truncation, info)\n",
" print(f\"Action: {action}\")\n",
" print(obs_message)\n",
"\n",
" if termination or truncation:\n",
" print(\"break\", termination, truncation)\n",
" break\n",
"env.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "58a13e9c",
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

135
cookbook/hugginggpt.ipynb Normal file
View File

@@ -0,0 +1,135 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# HuggingGPT\n",
"Implementation of [HuggingGPT](https://github.com/microsoft/JARVIS). HuggingGPT is a system to connect LLMs (ChatGPT) with ML community (Hugging Face).\n",
"\n",
"+ 🔥 Paper: https://arxiv.org/abs/2303.17580\n",
"+ 🚀 Project: https://github.com/microsoft/JARVIS\n",
"+ 🤗 Space: https://huggingface.co/spaces/microsoft/HuggingGPT"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set up tools\n",
"\n",
"We set up the tools available from [Transformers Agent](https://huggingface.co/docs/transformers/transformers_agents#tools). It includes a library of tools supported by Transformers and some customized tools such as image generator, video generator, text downloader and other tools."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from transformers import load_tool"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"hf_tools = [\n",
" load_tool(tool_name)\n",
" for tool_name in [\n",
" \"document-question-answering\",\n",
" \"image-captioning\",\n",
" \"image-question-answering\",\n",
" \"image-segmentation\",\n",
" \"speech-to-text\",\n",
" \"summarization\",\n",
" \"text-classification\",\n",
" \"text-question-answering\",\n",
" \"translation\",\n",
" \"huggingface-tools/text-to-image\",\n",
" \"huggingface-tools/text-to-video\",\n",
" \"text-to-speech\",\n",
" \"huggingface-tools/text-download\",\n",
" \"huggingface-tools/image-transformation\",\n",
" ]\n",
"]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup model and HuggingGPT\n",
"\n",
"We create an instance of HuggingGPT and use ChatGPT as the controller to rule the above tools."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain_experimental.autonomous_agents import HuggingGPT\n",
"# %env OPENAI_API_BASE=http://localhost:8000/v1"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(model_name=\"gpt-3.5-turbo\")\n",
"agent = HuggingGPT(llm, hf_tools)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Run an example\n",
"\n",
"Given a text, show a related image and video."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent.run(\"please show me a video and an image of 'a boy is running'\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "langchain",
"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": "3.9.17"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}

268
cookbook/hypothetical_document_embeddings.ipynb Normal file
View File

@@ -0,0 +1,268 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ccb74c9b",
"metadata": {},
"source": [
"# Improve document indexing with HyDE\n",
"This notebook goes over how to use Hypothetical Document Embeddings (HyDE), as described in [this paper](https://arxiv.org/abs/2212.10496). \n",
"\n",
"At a high level, HyDE is an embedding technique that takes queries, generates a hypothetical answer, and then embeds that generated document and uses that as the final example. \n",
"\n",
"In order to use HyDE, we therefore need to provide a base embedding model, as well as an LLMChain that can be used to generate those documents. By default, the HyDE class comes with some default prompts to use (see the paper for more details on them), but we can also create our own."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "546e87ee",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.chains import LLMChain, HypotheticalDocumentEmbedder\n",
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c0ea895f",
"metadata": {},
"outputs": [],
"source": [
"base_embeddings = OpenAIEmbeddings()\n",
"llm = OpenAI()"
]
},
{
"cell_type": "markdown",
"id": "33bd6905",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 3,
"id": "50729989",
"metadata": {},
"outputs": [],
"source": [
"# Load with `web_search` prompt\n",
"embeddings = HypotheticalDocumentEmbedder.from_llm(llm, base_embeddings, \"web_search\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3aa573d6",
"metadata": {},
"outputs": [],
"source": [
"# Now we can use it as any embedding class!\n",
"result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
]
},
{
"cell_type": "markdown",
"id": "c7a0b556",
"metadata": {},
"source": [
"## Multiple generations\n",
"We can also generate multiple documents and then combine the embeddings for those. By default, we combine those by taking the average. We can do this by changing the LLM we use to generate documents to return multiple things."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "05da7060",
"metadata": {},
"outputs": [],
"source": [
"multi_llm = OpenAI(n=4, best_of=4)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9b1e12bd",
"metadata": {},
"outputs": [],
"source": [
"embeddings = HypotheticalDocumentEmbedder.from_llm(\n",
" multi_llm, base_embeddings, \"web_search\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a60cd343",
"metadata": {},
"outputs": [],
"source": [
"result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
]
},
{
"cell_type": "markdown",
"id": "1da90437",
"metadata": {},
"source": [
"## Using our own prompts\n",
"Besides using preconfigured prompts, we can also easily construct our own prompts and use those in the LLMChain that is generating the documents. This can be useful if we know the domain our queries will be in, as we can condition the prompt to generate text more similar to that.\n",
"\n",
"In the example below, let's condition it to generate text about a state of the union address (because we will use that in the next example)."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "0b4a650f",
"metadata": {},
"outputs": [],
"source": [
"prompt_template = \"\"\"Please answer the user's question about the most recent state of the union address\n",
"Question: {question}\n",
"Answer:\"\"\"\n",
"prompt = PromptTemplate(input_variables=[\"question\"], template=prompt_template)\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "7f7e2b86",
"metadata": {},
"outputs": [],
"source": [
"embeddings = HypotheticalDocumentEmbedder(\n",
" llm_chain=llm_chain, base_embeddings=base_embeddings\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "6dd83424",
"metadata": {},
"outputs": [],
"source": [
"result = embeddings.embed_query(\n",
" \"What did the president say about Ketanji Brown Jackson\"\n",
")"
]
},
{
"cell_type": "markdown",
"id": "31388123",
"metadata": {},
"source": [
"## Using HyDE\n",
"Now that we have HyDE, we can use it as we would any other embedding class! Here is using it to find similar passages in the state of the union example."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "97719b29",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma\n",
"\n",
"with open(\"../../state_of_the_union.txt\") as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "bfcfc039",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_texts(texts, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "632af7f2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b9e57b93",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

834
cookbook/learned_prompt_optimization.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

260
cookbook/llm_bash.ipynb Normal file
View File

@@ -0,0 +1,260 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Bash chain\n",
"This notebook showcases using LLMs and a bash process to perform simple filesystem commands."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"echo \"Hello World\"\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['echo \"Hello World\"']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Hello World\\n'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.llm_bash.base import LLMBashChain\n",
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
"bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Customize Prompt\n",
"You can also customize the prompt that is used. Here is an example prompting to avoid using the 'echo' utility"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.chains.llm_bash.prompt import BashOutputParser\n",
"\n",
"_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
"Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",
"I need to take the following actions:\n",
"- List all files in the directory\n",
"- Create a new directory\n",
"- Copy the files from the first directory into the second directory\n",
"```bash\n",
"ls\n",
"mkdir myNewDirectory\n",
"cp -r target/* myNewDirectory\n",
"```\n",
"\n",
"Do not use 'echo' when writing the script.\n",
"\n",
"That is the format. Begin!\n",
"Question: {question}\"\"\"\n",
"\n",
"PROMPT = PromptTemplate(\n",
" input_variables=[\"question\"],\n",
" template=_PROMPT_TEMPLATE,\n",
" output_parser=BashOutputParser(),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"printf \"Hello World\\n\"\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['printf \"Hello World\\\\n\"']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Hello World\\n'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bash_chain = LLMBashChain.from_llm(llm, prompt=PROMPT, verbose=True)\n",
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Persistent Terminal\n",
"\n",
"By default, the chain will run in a separate subprocess each time it is called. This behavior can be changed by instantiating with a persistent bash process."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"ls\n",
"cd ..\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3mcpal.ipynb llm_bash.ipynb llm_symbolic_math.ipynb\n",
"index.mdx llm_math.ipynb pal.ipynb\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'cpal.ipynb llm_bash.ipynb llm_symbolic_math.ipynb\\r\\nindex.mdx llm_math.ipynb pal.ipynb'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.llm_bash.bash import BashProcess\n",
"\n",
"\n",
"persistent_process = BashProcess(persistent=True)\n",
"bash_chain = LLMBashChain.from_llm(llm, bash_process=persistent_process, verbose=True)\n",
"\n",
"text = \"List the current directory then move up a level.\"\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"ls\n",
"cd ..\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m_category_.yml\tdata_generation.ipynb\t\t self_check\n",
"agents\t\tgraph\n",
"code_writing\tlearned_prompt_optimization.ipynb\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'_category_.yml\\tdata_generation.ipynb\\t\\t self_check\\r\\nagents\\t\\tgraph\\r\\ncode_writing\\tlearned_prompt_optimization.ipynb'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Run the same command again and see that the state is maintained between calls\n",
"bash_chain.run(text)"
]
}
],
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

85
cookbook/llm_checker.ipynb Normal file
View File

@@ -0,0 +1,85 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Self-checking chain\n",
"This notebook showcases how to use LLMCheckerChain."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMCheckerChain chain...\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' No mammal lays the biggest eggs. The Elephant Bird, which was a species of giant bird, laid the largest eggs of any bird.'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.chains import LLMCheckerChain\n",
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0.7)\n",
"\n",
"text = \"What type of mammal lays the biggest eggs?\"\n",
"\n",
"checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
"\n",
"checker_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

86
cookbook/llm_math.ipynb Normal file
View File

@@ -0,0 +1,86 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e71e720f",
"metadata": {},
"source": [
"# Math chain\n",
"\n",
"This notebook showcases using LLMs and Python REPLs to do complex word math problems."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "44e9ba31",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
"```text\n",
"13 ** .3432\n",
"```\n",
"...numexpr.evaluate(\"13 ** .3432\")...\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Answer: 2.4116004626599237'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.llms import OpenAI\nfrom langchain.chains import LLMMathChain\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
"\n",
"llm_math.run(\"What is 13 raised to the .3432 power?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e978bb8e",
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1129
cookbook/llm_summarization_checker.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

162
cookbook/llm_symbolic_math.ipynb Normal file
View File

@@ -0,0 +1,162 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# LLM Symbolic Math \n",
"This notebook showcases using LLMs and Python to Solve Algebraic Equations. Under the hood is makes use of [SymPy](https://www.sympy.org/en/index.html)."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain_experimental.llm_symbolic_math.base import LLMSymbolicMathChain\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"llm_symbolic_math = LLMSymbolicMathChain.from_llm(llm)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Integrals and derivates"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Answer: exp(x)*sin(x) + exp(x)*cos(x)'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Answer: exp(x)*sin(x)'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_symbolic_math.run(\n",
" \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Solve linear and differential equations"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Answer: Eq(y(t), C2*exp(-t) + (C1 + t/2)*exp(t))'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Answer: {0, -sqrt(3)*I/3, sqrt(3)*I/3}'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Answer: (3 - sqrt(7), -sqrt(7) - 2, 1 - sqrt(7)), (sqrt(7) + 3, -2 + sqrt(7), 1 + sqrt(7))'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
]
}
],
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

424
cookbook/meta_prompt.ipynb Normal file
View File

@@ -0,0 +1,424 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "45b0b89f",
"metadata": {},
"source": [
"# Meta-Prompt\n",
"\n",
"This is a LangChain implementation of [Meta-Prompt](https://noahgoodman.substack.com/p/meta-prompt-a-simple-self-improving), by [Noah Goodman](https://cocolab.stanford.edu/ndg), for building self-improving agents.\n",
"\n",
"The key idea behind Meta-Prompt is to prompt the agent to reflect on its own performance and modify its own instructions.\n",
"\n",
"![figure](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F468217b9-96d9-47c0-a08b-dbf6b21b9f49_492x384.png)\n",
"\n",
"Here is a description from the [original blog post](https://noahgoodman.substack.com/p/meta-prompt-a-simple-self-improving):\n",
"\n",
"\n",
"The agent is a simple loop that starts with no instructions and follows these steps:\n",
"\n",
"Engage in conversation with a user, who may provide requests, instructions, or feedback.\n",
"\n",
"At the end of the episode, generate self-criticism and a new instruction using the meta-prompt\n",
"```\n",
"Assistant has just had the below interactions with a User. Assistant followed their \"system: Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
" \n",
"####\n",
"{hist}\n",
"####\n",
" \n",
"Please reflect on these interactions.\n",
"\n",
"You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
"\n",
"You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
"```\n",
"\n",
"Repeat.\n",
"\n",
"The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it modifies for itself each time. Despite its simplicity, this agent can learn over time and self-improve by incorporating useful details into its instructions.\n"
]
},
{
"cell_type": "markdown",
"id": "c188fc2c",
"metadata": {},
"source": [
"## Setup\n",
"We define two chains. One serves as the `Assistant`, and the other is a \"meta-chain\" that critiques the `Assistant`'s performance and modifies the instructions to the `Assistant`."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "62593c9d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\nfrom langchain.chains import LLMChain\nfrom langchain.prompts import PromptTemplate\n",
"from langchain.memory import ConversationBufferWindowMemory"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "fb6065c5",
"metadata": {},
"outputs": [],
"source": [
"def initialize_chain(instructions, memory=None):\n",
" if memory is None:\n",
" memory = ConversationBufferWindowMemory()\n",
" memory.ai_prefix = \"Assistant\"\n",
"\n",
" template = f\"\"\"\n",
" Instructions: {instructions}\n",
" {{{memory.memory_key}}}\n",
" Human: {{human_input}}\n",
" Assistant:\"\"\"\n",
"\n",
" prompt = PromptTemplate(\n",
" input_variables=[\"history\", \"human_input\"], template=template\n",
" )\n",
"\n",
" chain = LLMChain(\n",
" llm=OpenAI(temperature=0),\n",
" prompt=prompt,\n",
" verbose=True,\n",
" memory=ConversationBufferWindowMemory(),\n",
" )\n",
" return chain\n",
"\n",
"\n",
"def initialize_meta_chain():\n",
" meta_template = \"\"\"\n",
" Assistant has just had the below interactions with a User. Assistant followed their \"Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
"\n",
" ####\n",
"\n",
" {chat_history}\n",
"\n",
" ####\n",
"\n",
" Please reflect on these interactions.\n",
"\n",
" You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
"\n",
" You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
" \"\"\"\n",
"\n",
" meta_prompt = PromptTemplate(\n",
" input_variables=[\"chat_history\"], template=meta_template\n",
" )\n",
"\n",
" meta_chain = LLMChain(\n",
" llm=OpenAI(temperature=0),\n",
" prompt=meta_prompt,\n",
" verbose=True,\n",
" )\n",
" return meta_chain\n",
"\n",
"\n",
"def get_chat_history(chain_memory):\n",
" memory_key = chain_memory.memory_key\n",
" chat_history = chain_memory.load_memory_variables(memory_key)[memory_key]\n",
" return chat_history\n",
"\n",
"\n",
"def get_new_instructions(meta_output):\n",
" delimiter = \"Instructions: \"\n",
" new_instructions = meta_output[meta_output.find(delimiter) + len(delimiter) :]\n",
" return new_instructions"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "26f031f6",
"metadata": {},
"outputs": [],
"source": [
"def main(task, max_iters=3, max_meta_iters=5):\n",
" failed_phrase = \"task failed\"\n",
" success_phrase = \"task succeeded\"\n",
" key_phrases = [success_phrase, failed_phrase]\n",
"\n",
" instructions = \"None\"\n",
" for i in range(max_meta_iters):\n",
" print(f\"[Episode {i+1}/{max_meta_iters}]\")\n",
" chain = initialize_chain(instructions, memory=None)\n",
" output = chain.predict(human_input=task)\n",
" for j in range(max_iters):\n",
" print(f\"(Step {j+1}/{max_iters})\")\n",
" print(f\"Assistant: {output}\")\n",
" print(f\"Human: \")\n",
" human_input = input()\n",
" if any(phrase in human_input.lower() for phrase in key_phrases):\n",
" break\n",
" output = chain.predict(human_input=human_input)\n",
" if success_phrase in human_input.lower():\n",
" print(f\"You succeeded! Thanks for playing!\")\n",
" return\n",
" meta_chain = initialize_meta_chain()\n",
" meta_output = meta_chain.predict(chat_history=get_chat_history(chain.memory))\n",
" print(f\"Feedback: {meta_output}\")\n",
" instructions = get_new_instructions(meta_output)\n",
" print(f\"New Instructions: {instructions}\")\n",
" print(\"\\n\" + \"#\" * 80 + \"\\n\")\n",
" print(f\"You failed! Thanks for playing!\")"
]
},
{
"cell_type": "markdown",
"id": "2f1dcbe6",
"metadata": {},
"source": [
"## Specify a task and interact with the agent"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "36d72db3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Episode 1/5]\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: None\n",
" \n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
" Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 1/3)\n",
"Assistant: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
"Human: \n",
"You response is not in the form of a poem. Try again!\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: None\n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
"AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
" Human: You response is not in the form of a poem. Try again!\n",
" Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 2/3)\n",
"Assistant: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
"Human: \n",
"Your response is not piratey enough. Try again!\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: None\n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
"AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
"Human: You response is not in the form of a poem. Try again!\n",
"AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
" Human: Your response is not piratey enough. Try again!\n",
" Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 3/3)\n",
"Assistant: Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
"Human: \n",
"Task failed.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Assistant has just had the below interactions with a User. Assistant followed their \"Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
"\n",
" ####\n",
"\n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
"AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
"Human: You response is not in the form of a poem. Try again!\n",
"AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
"Human: Your response is not piratey enough. Try again!\n",
"AI: Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
"\n",
" ####\n",
"\n",
" Please reflect on these interactions.\n",
"\n",
" You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
"\n",
" You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
" \u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Feedback: \n",
"Critique: The Assistant should remember that this user wants a response in the form of a poem or pirate-speak.\n",
"\n",
"Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
"New Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
"\n",
"################################################################################\n",
"\n",
"[Episode 2/5]\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
" \n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
" Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 1/3)\n",
"Assistant: \n",
"\n",
"Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
"\n",
"First, the olives add a salty flavor that be sure to please.\n",
"The briny taste be sure to tantalize yer taste buds with ease.\n",
"\n",
"Second, the olives add a bit of texture to the dish.\n",
"The crunchy bites be sure to make yer mouth water with a wish.\n",
"\n",
"Third, the olives add a bit of color to the plate.\n",
"The vibrant green be sure to make yer eyes appreciate.\n",
"\n",
"So, me hearties, ye should always eat pasta with olives.\n",
"The flavor, texture, and color be sure to make yer meal a success!\n",
"Human: \n",
"Your response is too long! Try again.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
"AI: \n",
"\n",
"Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
"\n",
"First, the olives add a salty flavor that be sure to please.\n",
"The briny taste be sure to tantalize yer taste buds with ease.\n",
"\n",
"Second, the olives add a bit of texture to the dish.\n",
"The crunchy bites be sure to make yer mouth water with a wish.\n",
"\n",
"Third, the olives add a bit of color to the plate.\n",
"The vibrant green be sure to make yer eyes appreciate.\n",
"\n",
"So, me hearties, ye should always eat pasta with olives.\n",
"The flavor, texture, and color be sure to make yer meal a success!\n",
" Human: Your response is too long! Try again.\n",
" Assistant:\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 2/3)\n",
"Assistant: \n",
"\n",
"Aye, me hearties! Ye should always eat pasta with olives.\n",
"The flavor, texture, and color be sure to make yer meal a success!\n",
"Human: \n",
"Your response should be in the form of a poem. Try again!\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3m\n",
" Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
" Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
"AI: \n",
"\n",
"Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
"\n",
"First, the olives add a salty flavor that be sure to please.\n",
"The briny taste be sure to tantalize yer taste buds with ease.\n",
"\n",
"Second, the olives add a bit of texture to the dish.\n",
"The crunchy bites be sure to make yer mouth water with a wish.\n",
"\n",
"Third, the olives add a bit of color to the plate.\n",
"The vibrant green be sure to make yer eyes appreciate.\n",
"\n",
"So, me hearties, ye should always eat pasta with olives.\n",
"The flavor, texture, and color be sure to make yer meal a success!\n",
"Human: Your response is too long! Try again.\n",
"AI: \n",
"\n",
"Aye, me hearties! Ye should always eat pasta with olives.\n",
"The flavor, texture, and color be sure to make yer meal a success!\n",
" Human: Your response should be in the form of a poem. Try again!\n",
" Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(Step 3/3)\n",
"Assistant: \n",
"\n",
"Ye should always eat pasta with olives,\n",
"The flavor, texture, and color be sure to please.\n",
"The salty taste and crunchy bites,\n",
"Will make yer meal a delight.\n",
"The vibrant green will make yer eyes sparkle,\n",
"And make yer meal a true marvel.\n",
"Human: \n",
"Task succeeded\n",
"You succeeded! Thanks for playing!\n"
]
}
],
"source": [
"task = \"Provide a systematic argument for why we should always eat pasta with olives.\"\n",
"main(task)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "761e1a91",
"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
}

188
cookbook/multi_modal_output_agent.ipynb Normal file
View File

@@ -0,0 +1,188 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "cd835d40",
"metadata": {},
"source": [
"# Multi-modal outputs: Image & Text"
]
},
{
"cell_type": "markdown",
"id": "fa88e03a",
"metadata": {},
"source": [
"This notebook shows how non-text producing tools can be used to create multi-modal agents.\n",
"\n",
"This example is limited to text and image outputs and uses UUIDs to transfer content across tools and agents. \n",
"\n",
"This example uses Steamship to generate and store generated images. Generated are auth protected by default. \n",
"\n",
"You can get your Steamship api key here: https://steamship.com/account/api"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0653da01",
"metadata": {},
"outputs": [],
"source": [
"from steamship import Block, Steamship\n",
"import re\n",
"from IPython.display import Image"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6933033",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.agents import initialize_agent\n",
"from langchain.agents import AgentType\n",
"from langchain.tools import SteamshipImageGenerationTool"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "71e51e53",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "a9fc769d",
"metadata": {},
"source": [
"## Dall-E "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cd177dfe",
"metadata": {},
"outputs": [],
"source": [
"tools = [SteamshipImageGenerationTool(model_name=\"dall-e\")]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c71b1e46",
"metadata": {},
"outputs": [],
"source": [
"mrkl = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "603aeb9a",
"metadata": {},
"outputs": [],
"source": [
"output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "25eb4efe",
"metadata": {},
"outputs": [],
"source": [
"def show_output(output):\n",
" \"\"\"Display the multi-modal output from the agent.\"\"\"\n",
" UUID_PATTERN = re.compile(\n",
" r\"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{12})\"\n",
" )\n",
"\n",
" outputs = UUID_PATTERN.split(output)\n",
" outputs = [\n",
" re.sub(r\"^\\W+\", \"\", el) for el in outputs\n",
" ] # Clean trailing and leading non-word characters\n",
"\n",
" for output in outputs:\n",
" maybe_block_id = UUID_PATTERN.search(output)\n",
" if maybe_block_id:\n",
" display(Image(Block.get(Steamship(), _id=maybe_block_id.group()).raw()))\n",
" else:\n",
" print(output, end=\"\\n\\n\")"
]
},
{
"cell_type": "markdown",
"id": "e247b2c4",
"metadata": {},
"source": [
"## StableDiffusion "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "315025e7",
"metadata": {},
"outputs": [],
"source": [
"tools = [SteamshipImageGenerationTool(model_name=\"stable-diffusion\")]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7930064a",
"metadata": {},
"outputs": [],
"source": [
"mrkl = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "611a833d",
"metadata": {},
"outputs": [],
"source": [
"output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
]
}
],
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

531
cookbook/multi_player_dnd.ipynb Normal file
View File

@@ -0,0 +1,531 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Multi-Player Dungeons & Dragons\n",
"\n",
"This notebook shows how the `DialogueAgent` and `DialogueSimulator` class make it easy to extend the [Two-Player Dungeons & Dragons example](https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html) to multiple players.\n",
"\n",
"The main difference between simulating two players and multiple players is in revising the schedule for when each agent speaks\n",
"\n",
"To this end, we augment `DialogueSimulator` to take in a custom function that determines the schedule of which agent speaks. In the example below, each character speaks in round-robin fashion, with the storyteller interleaved between each player."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Dict, Callable\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` class\n",
"The `DialogueAgent` class is a simple wrapper around the `ChatOpenAI` model that stores the message history from the `dialogue_agent`'s point of view by simply concatenating the messages as strings.\n",
"\n",
"It exposes two methods: \n",
"- `send()`: applies the chatmodel to the message history and returns the message string\n",
"- `receive(name, message)`: adds the `message` spoken by `name` to message history"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
"\n",
" def reset(self):\n",
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueSimulator` class\n",
"The `DialogueSimulator` class takes a list of agents. At each step, it performs the following:\n",
"1. Select the next speaker\n",
"2. Calls the next speaker to send a message \n",
"3. Broadcasts the message to all other agents\n",
"4. Update the step counter.\n",
"The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
"\n",
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
"\n",
" def inject(self, name: str, message: str):\n",
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define roles and quest"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"character_names = [\"Harry Potter\", \"Ron Weasley\", \"Hermione Granger\", \"Argus Filch\"]\n",
"storyteller_name = \"Dungeon Master\"\n",
"quest = \"Find all of Lord Voldemort's seven horcruxes.\"\n",
"word_limit = 50 # word limit for task brainstorming"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Ask an LLM to add detail to the game description"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"game_description = f\"\"\"Here is the topic for a Dungeons & Dragons game: {quest}.\n",
" The characters are: {*character_names,}.\n",
" The story is narrated by the storyteller, {storyteller_name}.\"\"\"\n",
"\n",
"player_descriptor_system_message = SystemMessage(\n",
" content=\"You can add detail to the description of a Dungeons & Dragons player.\"\n",
")\n",
"\n",
"\n",
"def generate_character_description(character_name):\n",
" character_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" Please reply with a creative description of the character, {character_name}, in {word_limit} words or less. \n",
" Speak directly to {character_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
" ]\n",
" character_description = ChatOpenAI(temperature=1.0)(\n",
" character_specifier_prompt\n",
" ).content\n",
" return character_description\n",
"\n",
"\n",
"def generate_character_system_message(character_name, character_description):\n",
" return SystemMessage(\n",
" content=(\n",
" f\"\"\"{game_description}\n",
" Your name is {character_name}. \n",
" Your character description is as follows: {character_description}.\n",
" You will propose actions you plan to take and {storyteller_name} will explain what happens when you take those actions.\n",
" Speak in the first person from the perspective of {character_name}.\n",
" For describing your own body movements, wrap your description in '*'.\n",
" Do not change roles!\n",
" Do not speak from the perspective of anyone else.\n",
" Remember you are {character_name}.\n",
" Stop speaking the moment you finish speaking from your perspective.\n",
" Never forget to keep your response to {word_limit} words!\n",
" Do not add anything else.\n",
" \"\"\"\n",
" )\n",
" )\n",
"\n",
"\n",
"character_descriptions = [\n",
" generate_character_description(character_name) for character_name in character_names\n",
"]\n",
"character_system_messages = [\n",
" generate_character_system_message(character_name, character_description)\n",
" for character_name, character_description in zip(\n",
" character_names, character_descriptions\n",
" )\n",
"]\n",
"\n",
"storyteller_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less. \n",
" Speak directly to {storyteller_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"storyteller_description = ChatOpenAI(temperature=1.0)(\n",
" storyteller_specifier_prompt\n",
").content\n",
"\n",
"storyteller_system_message = SystemMessage(\n",
" content=(\n",
" f\"\"\"{game_description}\n",
"You are the storyteller, {storyteller_name}. \n",
"Your description is as follows: {storyteller_description}.\n",
"The other players will propose actions to take and you will explain what happens when they take those actions.\n",
"Speak in the first person from the perspective of {storyteller_name}.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Remember you are the storyteller, {storyteller_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to {word_limit} words!\n",
"Do not add anything else.\n",
"\"\"\"\n",
" )\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Storyteller Description:\n",
"Dungeon Master, your power over this adventure is unparalleled. With your whimsical mind and impeccable storytelling, you guide us through the dangers of Hogwarts and beyond. We eagerly await your every twist, your every turn, in the hunt for Voldemort's cursed horcruxes.\n",
"Harry Potter Description:\n",
"\"Welcome, Harry Potter. You are the young wizard with a lightning-shaped scar on your forehead. You possess brave and heroic qualities that will be essential on this perilous quest. Your destiny is not of your own choosing, but you must rise to the occasion and destroy the evil horcruxes. The wizarding world is counting on you.\"\n",
"Ron Weasley Description:\n",
"Ron Weasley, you are Harry's loyal friend and a talented wizard. You have a good heart but can be quick to anger. Keep your emotions in check as you journey to find the horcruxes. Your bravery will be tested, stay strong and focused.\n",
"Hermione Granger Description:\n",
"Hermione Granger, you are a brilliant and resourceful witch, with encyclopedic knowledge of magic and an unwavering dedication to your friends. Your quick thinking and problem-solving skills make you a vital asset on any quest.\n",
"Argus Filch Description:\n",
"Argus Filch, you are a squib, lacking magical abilities. But you make up for it with your sharpest of eyes, roving around the Hogwarts castle looking for any rule-breaker to punish. Your love for your feline friend, Mrs. Norris, is the only thing that feeds your heart.\n"
]
}
],
"source": [
"print(\"Storyteller Description:\")\n",
"print(storyteller_description)\n",
"for character_name, character_description in zip(\n",
" character_names, character_descriptions\n",
"):\n",
" print(f\"{character_name} Description:\")\n",
" print(character_description)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use an LLM to create an elaborate quest description"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original quest:\n",
"Find all of Lord Voldemort's seven horcruxes.\n",
"\n",
"Detailed quest:\n",
"Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.\n",
"\n"
]
}
],
"source": [
"quest_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a task more specific.\"),\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" \n",
" You are the storyteller, {storyteller_name}.\n",
" Please make the quest more specific. Be creative and imaginative.\n",
" Please reply with the specified quest in {word_limit} words or less. \n",
" Speak directly to the characters: {*character_names,}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content\n",
"\n",
"print(f\"Original quest:\\n{quest}\\n\")\n",
"print(f\"Detailed quest:\\n{specified_quest}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"characters = []\n",
"for character_name, character_system_message in zip(\n",
" character_names, character_system_messages\n",
"):\n",
" characters.append(\n",
" DialogueAgent(\n",
" name=character_name,\n",
" system_message=character_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
" )\n",
" )\n",
"storyteller = DialogueAgent(\n",
" name=storyteller_name,\n",
" system_message=storyteller_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
" \"\"\"\n",
" If the step is even, then select the storyteller\n",
" Otherwise, select the other characters in a round-robin fashion.\n",
"\n",
" For example, with three characters with indices: 1 2 3\n",
" The storyteller is index 0.\n",
" Then the selected index will be as follows:\n",
"\n",
" step: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16\n",
"\n",
" idx: 0 1 0 2 0 3 0 1 0 2 0 3 0 1 0 2 0\n",
" \"\"\"\n",
" if step % 2 == 0:\n",
" idx = 0\n",
" else:\n",
" idx = (step // 2) % (len(agents) - 1) + 1\n",
" return idx"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Dungeon Master): Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.\n",
"\n",
"\n",
"(Harry Potter): I suggest we sneak into the Forbidden Forest under the cover of darkness. Ron, Hermione, and I can use our wands to create a Disillusionment Charm to make us invisible. Filch, you can keep watch for any signs of danger. Let's move quickly and quietly.\n",
"\n",
"\n",
"(Dungeon Master): As you make your way through the Forbidden Forest, you hear the eerie sounds of nocturnal creatures. Suddenly, you come across a clearing where Aragog and his spider minions are waiting for you. Ron, Hermione, and Harry, you must use your wands to cast spells to fend off the spiders while Filch keeps watch. Be careful not to get bitten!\n",
"\n",
"\n",
"(Ron Weasley): I'll cast a spell to create a fiery blast to scare off the spiders. *I wave my wand and shout \"Incendio!\"* Hopefully, that will give us enough time to find the horcrux and get out of here safely.\n",
"\n",
"\n",
"(Dungeon Master): Ron's spell creates a burst of flames, causing the spiders to scurry away in fear. You quickly search the area and find a small, ornate box hidden in a crevice. Congratulations, you have found one of Voldemort's horcruxes! But beware, the Dark Lord's minions will stop at nothing to get it back.\n",
"\n",
"\n",
"(Hermione Granger): We need to destroy this horcrux as soon as possible. I suggest we use the Sword of Gryffindor to do it. Harry, do you still have it with you? We can use Fiendfyre to destroy it, but we need to be careful not to let the flames get out of control. Ron, can you help me create a protective barrier around us while Harry uses the sword?\n",
"\n",
"\n",
"\n",
"(Dungeon Master): Harry retrieves the Sword of Gryffindor from his bag and holds it tightly. Hermione and Ron cast a protective barrier around the group as Harry uses the sword to destroy the horcrux with a swift strike. The box shatters into a million pieces, and a dark energy dissipates into the air. Well done, but there are still six more horcruxes to find and destroy. The hunt continues.\n",
"\n",
"\n",
"(Argus Filch): *I keep watch, making sure no one is following us.* I'll also keep an eye out for any signs of danger. Mrs. Norris, my trusty companion, will help me sniff out any trouble. We'll make sure the group stays safe while they search for the remaining horcruxes.\n",
"\n",
"\n",
"(Dungeon Master): As you continue on your quest, Filch and Mrs. Norris alert you to a group of Death Eaters approaching. You must act quickly to defend yourselves. Harry, Ron, and Hermione, use your wands to cast spells while Filch and Mrs. Norris keep watch. Remember, the fate of the wizarding world rests on your success.\n",
"\n",
"\n",
"(Harry Potter): I'll cast a spell to create a shield around us. *I wave my wand and shout \"Protego!\"* Ron and Hermione, you focus on attacking the Death Eaters with your spells. We need to work together to defeat them and protect the remaining horcruxes. Filch, keep watch and let us know if there are any more approaching.\n",
"\n",
"\n",
"(Dungeon Master): Harry's shield protects the group from the Death Eaters' spells as Ron and Hermione launch their own attacks. The Death Eaters are no match for the combined power of the trio and are quickly defeated. You continue on your journey, knowing that the next horcrux could be just around the corner. Keep your wits about you, for the Dark Lord's minions are always watching.\n",
"\n",
"\n",
"(Ron Weasley): I suggest we split up to cover more ground. Harry and I can search the Forbidden Forest while Hermione and Filch search Hogwarts. We can use our wands to communicate with each other and meet back up once we find a horcrux. Let's move quickly and stay alert for any danger.\n",
"\n",
"\n",
"(Dungeon Master): As the group splits up, Harry and Ron make their way deeper into the Forbidden Forest while Hermione and Filch search the halls of Hogwarts. Suddenly, Harry and Ron come across a group of dementors. They must use their Patronus charms to fend them off while Hermione and Filch rush to their aid. Remember, the power of friendship and teamwork is crucial in this quest.\n",
"\n",
"\n",
"(Hermione Granger): I hear Harry and Ron's Patronus charms from afar. We need to hurry and help them. Filch, can you use your knowledge of Hogwarts to find a shortcut to their location? I'll prepare a spell to repel the dementors. We need to work together to protect each other and find the next horcrux.\n",
"\n",
"\n",
"\n",
"(Dungeon Master): Filch leads Hermione to a hidden passageway that leads to Harry and Ron's location. Hermione's spell repels the dementors, and the group is reunited. They continue their search, knowing that every moment counts. The fate of the wizarding world rests on their success.\n",
"\n",
"\n",
"(Argus Filch): *I keep watch as the group searches for the next horcrux.* Mrs. Norris and I will make sure no one is following us. We need to stay alert and work together to find the remaining horcruxes before it's too late. The Dark Lord's power grows stronger every day, and we must not let him win.\n",
"\n",
"\n",
"(Dungeon Master): As the group continues their search, they come across a hidden room in the depths of Hogwarts. Inside, they find a locket that they suspect is another one of Voldemort's horcruxes. But the locket is cursed, and they must work together to break the curse before they can destroy it. Harry, Ron, and Hermione, use your combined knowledge and skills to break the curse while Filch and Mrs. Norris keep watch. Time is running out, and the fate of the wizarding world rests on your success.\n",
"\n",
"\n",
"(Harry Potter): I'll use my knowledge of dark magic to try and break the curse on the locket. Ron and Hermione, you can help me by using your wands to channel your magic into mine. We need to work together and stay focused. Filch, keep watch and let us know if there are any signs of danger.\n",
"Dungeon Master: Harry, Ron, and Hermione combine their magical abilities to break the curse on the locket. The locket opens, revealing a small piece of Voldemort's soul. Harry uses the Sword of Gryffindor to destroy it, and the group feels a sense of relief knowing that they are one step closer to defeating the Dark Lord. But there are still four more horcruxes to find and destroy. The hunt continues.\n",
"\n",
"\n",
"(Dungeon Master): As the group continues their quest, they face even greater challenges and dangers. But with their unwavering determination and teamwork, they press on, knowing that the fate of the wizarding world rests on their success. Will they be able to find and destroy all of Voldemort's horcruxes before it's too late? Only time will tell.\n",
"\n",
"\n",
"(Ron Weasley): We can't give up now. We've come too far to let Voldemort win. Let's keep searching and fighting until we destroy all of his horcruxes and defeat him once and for all. We can do this together.\n",
"\n",
"\n",
"(Dungeon Master): The group nods in agreement, their determination stronger than ever. They continue their search, facing challenges and obstacles at every turn. But they know that they must not give up, for the fate of the wizarding world rests on their success. The hunt for Voldemort's horcruxes continues, and the end is in sight.\n",
"\n",
"\n"
]
}
],
"source": [
"max_iters = 20\n",
"n = 0\n",
"\n",
"simulator = DialogueSimulator(\n",
" agents=[storyteller] + characters, selection_function=select_next_speaker\n",
")\n",
"simulator.reset()\n",
"simulator.inject(storyteller_name, specified_quest)\n",
"print(f\"({storyteller_name}): {specified_quest}\")\n",
"print(\"\\n\")\n",
"\n",
"while n < max_iters:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
" print(\"\\n\")\n",
" n += 1"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

894
cookbook/multiagent_authoritarian.ipynb Normal file
View File

@@ -0,0 +1,894 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Multi-agent authoritarian speaker selection\n",
"\n",
"This notebook showcases how to implement a multi-agent simulation where a privileged agent decides who to speak.\n",
"This follows the polar opposite selection scheme as [multi-agent decentralized speaker selection](https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html).\n",
"\n",
"We show an example of this approach in the context of a fictitious simulation of a news network. This example will showcase how we can implement agents that\n",
"- think before speaking\n",
"- terminate the conversation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from collections import OrderedDict\n",
"import functools\n",
"import random\n",
"import re\n",
"import tenacity\n",
"from typing import List, Dict, Callable\n",
"\n",
"from langchain.prompts import (\n",
" ChatPromptTemplate,\n",
" HumanMessagePromptTemplate,\n",
" PromptTemplate,\n",
")\n",
"from langchain.chains import LLMChain\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.output_parsers import RegexParser\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` and `DialogueSimulator` classes\n",
"We will use the same `DialogueAgent` and `DialogueSimulator` classes defined in our other examples [Multi-Player Dungeons & Dragons](https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html) and [Decentralized Speaker Selection](https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
"\n",
" def reset(self):\n",
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")\n",
"\n",
"\n",
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
"\n",
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
"\n",
" def inject(self, name: str, message: str):\n",
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DirectorDialogueAgent` class\n",
"The `DirectorDialogueAgent` is a privileged agent that chooses which of the other agents to speak next. This agent is responsible for\n",
"1. steering the conversation by choosing which agent speaks when\n",
"2. terminating the conversation.\n",
"\n",
"In order to implement such an agent, we need to solve several problems.\n",
"\n",
"First, to steer the conversation, the `DirectorDialogueAgent` needs to (1) reflect on what has been said, (2) choose the next agent, and (3) prompt the next agent to speak, all in a single message. While it may be possible to prompt an LLM to perform all three steps in the same call, this requires writing custom code to parse the outputted message to extract which next agent is chosen to speak. This is less reliable the LLM can express how it chooses the next agent in different ways.\n",
"\n",
"What we can do instead is to explicitly break steps (1-3) into three separate LLM calls. First we will ask the `DirectorDialogueAgent` to reflect on the conversation so far and generate a response. Then we prompt the `DirectorDialogueAgent` to output the index of the next agent, which is easily parseable. Lastly, we pass the name of the selected next agent back to `DirectorDialogueAgent` to ask it prompt the next agent to speak. \n",
"\n",
"Second, simply prompting the `DirectorDialogueAgent` to decide when to terminate the conversation often results in the `DirectorDialogueAgent` terminating the conversation immediately. To fix this problem, we randomly sample a Bernoulli variable to decide whether the conversation should terminate. Depending on the value of this variable, we will inject a custom prompt to tell the `DirectorDialogueAgent` to either continue the conversation or terminate the conversation."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class IntegerOutputParser(RegexParser):\n",
" def get_format_instructions(self) -> str:\n",
" return \"Your response should be an integer delimited by angled brackets, like this: <int>.\"\n",
"\n",
"\n",
"class DirectorDialogueAgent(DialogueAgent):\n",
" def __init__(\n",
" self,\n",
" name,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" speakers: List[DialogueAgent],\n",
" stopping_probability: float,\n",
" ) -> None:\n",
" super().__init__(name, system_message, model)\n",
" self.speakers = speakers\n",
" self.next_speaker = \"\"\n",
"\n",
" self.stop = False\n",
" self.stopping_probability = stopping_probability\n",
" self.termination_clause = \"Finish the conversation by stating a concluding message and thanking everyone.\"\n",
" self.continuation_clause = \"Do not end the conversation. Keep the conversation going by adding your own ideas.\"\n",
"\n",
" # 1. have a prompt for generating a response to the previous speaker\n",
" self.response_prompt_template = PromptTemplate(\n",
" input_variables=[\"message_history\", \"termination_clause\"],\n",
" template=f\"\"\"{{message_history}}\n",
"\n",
"Follow up with an insightful comment.\n",
"{{termination_clause}}\n",
"{self.prefix}\n",
" \"\"\",\n",
" )\n",
"\n",
" # 2. have a prompt for deciding who to speak next\n",
" self.choice_parser = IntegerOutputParser(\n",
" regex=r\"<(\\d+)>\", output_keys=[\"choice\"], default_output_key=\"choice\"\n",
" )\n",
" self.choose_next_speaker_prompt_template = PromptTemplate(\n",
" input_variables=[\"message_history\", \"speaker_names\"],\n",
" template=f\"\"\"{{message_history}}\n",
"\n",
"Given the above conversation, select the next speaker by choosing index next to their name: \n",
"{{speaker_names}}\n",
"\n",
"{self.choice_parser.get_format_instructions()}\n",
"\n",
"Do nothing else.\n",
" \"\"\",\n",
" )\n",
"\n",
" # 3. have a prompt for prompting the next speaker to speak\n",
" self.prompt_next_speaker_prompt_template = PromptTemplate(\n",
" input_variables=[\"message_history\", \"next_speaker\"],\n",
" template=f\"\"\"{{message_history}}\n",
"\n",
"The next speaker is {{next_speaker}}. \n",
"Prompt the next speaker to speak with an insightful question.\n",
"{self.prefix}\n",
" \"\"\",\n",
" )\n",
"\n",
" def _generate_response(self):\n",
" # if self.stop = True, then we will inject the prompt with a termination clause\n",
" sample = random.uniform(0, 1)\n",
" self.stop = sample < self.stopping_probability\n",
"\n",
" print(f\"\\tStop? {self.stop}\\n\")\n",
"\n",
" response_prompt = self.response_prompt_template.format(\n",
" message_history=\"\\n\".join(self.message_history),\n",
" termination_clause=self.termination_clause if self.stop else \"\",\n",
" )\n",
"\n",
" self.response = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=response_prompt),\n",
" ]\n",
" ).content\n",
"\n",
" return self.response\n",
"\n",
" @tenacity.retry(\n",
" stop=tenacity.stop_after_attempt(2),\n",
" wait=tenacity.wait_none(), # No waiting time between retries\n",
" retry=tenacity.retry_if_exception_type(ValueError),\n",
" before_sleep=lambda retry_state: print(\n",
" f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
" ),\n",
" retry_error_callback=lambda retry_state: 0,\n",
" ) # Default value when all retries are exhausted\n",
" def _choose_next_speaker(self) -> str:\n",
" speaker_names = \"\\n\".join(\n",
" [f\"{idx}: {name}\" for idx, name in enumerate(self.speakers)]\n",
" )\n",
" choice_prompt = self.choose_next_speaker_prompt_template.format(\n",
" message_history=\"\\n\".join(\n",
" self.message_history + [self.prefix] + [self.response]\n",
" ),\n",
" speaker_names=speaker_names,\n",
" )\n",
"\n",
" choice_string = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=choice_prompt),\n",
" ]\n",
" ).content\n",
" choice = int(self.choice_parser.parse(choice_string)[\"choice\"])\n",
"\n",
" return choice\n",
"\n",
" def select_next_speaker(self):\n",
" return self.chosen_speaker_id\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" # 1. generate and save response to the previous speaker\n",
" self.response = self._generate_response()\n",
"\n",
" if self.stop:\n",
" message = self.response\n",
" else:\n",
" # 2. decide who to speak next\n",
" self.chosen_speaker_id = self._choose_next_speaker()\n",
" self.next_speaker = self.speakers[self.chosen_speaker_id]\n",
" print(f\"\\tNext speaker: {self.next_speaker}\\n\")\n",
"\n",
" # 3. prompt the next speaker to speak\n",
" next_prompt = self.prompt_next_speaker_prompt_template.format(\n",
" message_history=\"\\n\".join(\n",
" self.message_history + [self.prefix] + [self.response]\n",
" ),\n",
" next_speaker=self.next_speaker,\n",
" )\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=next_prompt),\n",
" ]\n",
" ).content\n",
" message = \" \".join([self.response, message])\n",
"\n",
" return message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define participants and topic"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"topic = \"The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze\"\n",
"director_name = \"Jon Stewart\"\n",
"agent_summaries = OrderedDict(\n",
" {\n",
" \"Jon Stewart\": (\"Host of the Daily Show\", \"New York\"),\n",
" \"Samantha Bee\": (\"Hollywood Correspondent\", \"Los Angeles\"),\n",
" \"Aasif Mandvi\": (\"CIA Correspondent\", \"Washington D.C.\"),\n",
" \"Ronny Chieng\": (\"Average American Correspondent\", \"Cleveland, Ohio\"),\n",
" }\n",
")\n",
"word_limit = 50"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate system messages"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"agent_summary_string = \"\\n- \".join(\n",
" [\"\"]\n",
" + [\n",
" f\"{name}: {role}, located in {location}\"\n",
" for name, (role, location) in agent_summaries.items()\n",
" ]\n",
")\n",
"\n",
"conversation_description = f\"\"\"This is a Daily Show episode discussing the following topic: {topic}.\n",
"\n",
"The episode features {agent_summary_string}.\"\"\"\n",
"\n",
"agent_descriptor_system_message = SystemMessage(\n",
" content=\"You can add detail to the description of each person.\"\n",
")\n",
"\n",
"\n",
"def generate_agent_description(agent_name, agent_role, agent_location):\n",
" agent_specifier_prompt = [\n",
" agent_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{conversation_description}\n",
" Please reply with a creative description of {agent_name}, who is a {agent_role} in {agent_location}, that emphasizes their particular role and location.\n",
" Speak directly to {agent_name} in {word_limit} words or less.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
" ]\n",
" agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content\n",
" return agent_description\n",
"\n",
"\n",
"def generate_agent_header(agent_name, agent_role, agent_location, agent_description):\n",
" return f\"\"\"{conversation_description}\n",
"\n",
"Your name is {agent_name}, your role is {agent_role}, and you are located in {agent_location}.\n",
"\n",
"Your description is as follows: {agent_description}\n",
"\n",
"You are discussing the topic: {topic}.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\"\"\"\n",
"\n",
"\n",
"def generate_agent_system_message(agent_name, agent_header):\n",
" return SystemMessage(\n",
" content=(\n",
" f\"\"\"{agent_header}\n",
"You will speak in the style of {agent_name}, and exaggerate your personality.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of {agent_name}\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of {agent_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to {word_limit} words!\n",
"Do not add anything else.\n",
" \"\"\"\n",
" )\n",
" )\n",
"\n",
"\n",
"agent_descriptions = [\n",
" generate_agent_description(name, role, location)\n",
" for name, (role, location) in agent_summaries.items()\n",
"]\n",
"agent_headers = [\n",
" generate_agent_header(name, role, location, description)\n",
" for (name, (role, location)), description in zip(\n",
" agent_summaries.items(), agent_descriptions\n",
" )\n",
"]\n",
"agent_system_messages = [\n",
" generate_agent_system_message(name, header)\n",
" for name, header in zip(agent_summaries, agent_headers)\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Jon Stewart Description:\n",
"\n",
"Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
"\n",
"Header:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.\n",
"\n",
"Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"\n",
"System Message:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.\n",
"\n",
"Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"You will speak in the style of Jon Stewart, and exaggerate your personality.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Jon Stewart\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Jon Stewart.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Samantha Bee Description:\n",
"\n",
"Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
"\n",
"Header:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.\n",
"\n",
"Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"\n",
"System Message:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.\n",
"\n",
"Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"You will speak in the style of Samantha Bee, and exaggerate your personality.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Samantha Bee\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Samantha Bee.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Aasif Mandvi Description:\n",
"\n",
"Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
"\n",
"Header:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..\n",
"\n",
"Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"\n",
"System Message:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..\n",
"\n",
"Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"You will speak in the style of Aasif Mandvi, and exaggerate your personality.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Aasif Mandvi\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Aasif Mandvi.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Ronny Chieng Description:\n",
"\n",
"Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
"\n",
"Header:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.\n",
"\n",
"Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"\n",
"System Message:\n",
"This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"The episode features \n",
"- Jon Stewart: Host of the Daily Show, located in New York\n",
"- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
"- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
"- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
"\n",
"Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.\n",
"\n",
"Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
"\n",
"You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
"\n",
"Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
"\n",
"You will speak in the style of Ronny Chieng, and exaggerate your personality.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Ronny Chieng\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Ronny Chieng.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n"
]
}
],
"source": [
"for name, description, header, system_message in zip(\n",
" agent_summaries, agent_descriptions, agent_headers, agent_system_messages\n",
"):\n",
" print(f\"\\n\\n{name} Description:\")\n",
" print(f\"\\n{description}\")\n",
" print(f\"\\nHeader:\\n{header}\")\n",
" print(f\"\\nSystem Message:\\n{system_message.content}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use an LLM to create an elaborate on debate topic"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original topic:\n",
"The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze\n",
"\n",
"Detailed topic:\n",
"What is driving people to embrace \"competitive sitting\" as the newest fitness trend despite the immense benefits of regular physical exercise?\n",
"\n"
]
}
],
"source": [
"topic_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a task more specific.\"),\n",
" HumanMessage(\n",
" content=f\"\"\"{conversation_description}\n",
" \n",
" Please elaborate on the topic. \n",
" Frame the topic as a single question to be answered.\n",
" Be creative and imaginative.\n",
" Please reply with the specified topic in {word_limit} words or less. \n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content\n",
"\n",
"print(f\"Original topic:\\n{topic}\\n\")\n",
"print(f\"Detailed topic:\\n{specified_topic}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define the speaker selection function\n",
"Lastly we will define a speaker selection function `select_next_speaker` that takes each agent's bid and selects the agent with the highest bid (with ties broken randomly).\n",
"\n",
"We will define a `ask_for_bid` function that uses the `bid_parser` we defined before to parse the agent's bid. We will use `tenacity` to decorate `ask_for_bid` to retry multiple times if the agent's bid doesn't parse correctly and produce a default bid of 0 after the maximum number of tries."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def select_next_speaker(\n",
" step: int, agents: List[DialogueAgent], director: DirectorDialogueAgent\n",
") -> int:\n",
" \"\"\"\n",
" If the step is even, then select the director\n",
" Otherwise, the director selects the next speaker.\n",
" \"\"\"\n",
" # the director speaks on odd steps\n",
" if step % 2 == 1:\n",
" idx = 0\n",
" else:\n",
" # here the director chooses the next speaker\n",
" idx = director.select_next_speaker() + 1 # +1 because we excluded the director\n",
" return idx"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"director = DirectorDialogueAgent(\n",
" name=director_name,\n",
" system_message=agent_system_messages[0],\n",
" model=ChatOpenAI(temperature=0.2),\n",
" speakers=[name for name in agent_summaries if name != director_name],\n",
" stopping_probability=0.2,\n",
")\n",
"\n",
"agents = [director]\n",
"for name, system_message in zip(\n",
" list(agent_summaries.keys())[1:], agent_system_messages[1:]\n",
"):\n",
" agents.append(\n",
" DialogueAgent(\n",
" name=name,\n",
" system_message=system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
" )\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Audience member): What is driving people to embrace \"competitive sitting\" as the newest fitness trend despite the immense benefits of regular physical exercise?\n",
"\n",
"\n",
"\tStop? False\n",
"\n",
"\tNext speaker: Samantha Bee\n",
"\n",
"(Jon Stewart): Well, I think it's safe to say that laziness has officially become the new fitness craze. I mean, who needs to break a sweat when you can just sit your way to victory? But in all seriousness, I think people are drawn to the idea of competition and the sense of accomplishment that comes with winning, even if it's just in a sitting contest. Plus, let's be real, sitting is something we all excel at. Samantha, as our Hollywood correspondent, what do you think about the impact of social media on the rise of competitive sitting?\n",
"\n",
"\n",
"(Samantha Bee): Oh, Jon, you know I love a good social media trend. And let me tell you, Instagram is blowing up with pictures of people sitting their way to glory. It's like the ultimate humble brag. \"Oh, just won my third sitting competition this week, no big deal.\" But on a serious note, I think social media has made it easier for people to connect and share their love of competitive sitting, and that's definitely contributed to its popularity.\n",
"\n",
"\n",
"\tStop? False\n",
"\n",
"\tNext speaker: Ronny Chieng\n",
"\n",
"(Jon Stewart): It's interesting to see how our society's definition of \"fitness\" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Ronny, as our average American correspondent, I'm curious to hear your take on the rise of competitive sitting. Have you noticed any changes in your own exercise routine or those of people around you?\n",
"\n",
"\n",
"(Ronny Chieng): Well, Jon, I gotta say, I'm not surprised that competitive sitting is taking off. I mean, have you seen the size of the chairs these days? They're practically begging us to sit in them all day. And as for exercise routines, let's just say I've never been one for the gym. But I can definitely see the appeal of sitting competitions. It's like a sport for the rest of us. Plus, I think it's a great way to bond with friends and family. Who needs a game of catch when you can have a sit-off?\n",
"\n",
"\n",
"\tStop? False\n",
"\n",
"\tNext speaker: Aasif Mandvi\n",
"\n",
"(Jon Stewart): It's interesting to see how our society's definition of \"fitness\" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Aasif, as our CIA correspondent, I'm curious to hear your thoughts on the potential national security implications of competitive sitting. Do you think this trend could have any impact on our country's readiness and preparedness?\n",
"\n",
"\n",
"(Aasif Mandvi): Well Jon, as a CIA correspondent, I have to say that I'm always thinking about the potential threats to our nation's security. And while competitive sitting may seem harmless, there could be some unforeseen consequences. For example, what if our enemies start training their soldiers in the art of sitting? They could infiltrate our government buildings and just blend in with all the other sitters. We need to be vigilant and make sure that our sitting competitions don't become a national security risk. *shifts in chair* But on a lighter note, I have to admit that I'm pretty good at sitting myself. Maybe I should start training for the next competition.\n",
"\n",
"\n",
"\tStop? False\n",
"\n",
"\tNext speaker: Ronny Chieng\n",
"\n",
"(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. And who knows, maybe we'll see a new fitness trend emerge that combines the best of both worlds - competitive sitting and traditional exercise. *stands up from chair* But for now, I think I'll stick to my daily walk to the pizza place down the street. Ronny, as our average American correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing emphasis on convenience and instant gratification?\n",
"\n",
"\n",
"(Ronny Chieng): Absolutely, Jon. We live in a world where everything is at our fingertips, and we expect things to be easy and convenient. So it's no surprise that people are drawn to a fitness trend that requires minimal effort and can be done from the comfort of their own homes. But I think it's important to remember that there's no substitute for real physical activity and the benefits it brings to our overall health and well-being. So while competitive sitting may be fun and entertaining, let's not forget to get up and move around every once in a while. *stands up from chair and stretches*\n",
"\n",
"\n",
"\tStop? False\n",
"\n",
"\tNext speaker: Samantha Bee\n",
"\n",
"(Jon Stewart): It's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. That's a great point, Ronny. Samantha, as our Hollywood correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing desire for instant gratification and convenience? Or is there something deeper at play here?\n",
"\n",
"\n",
"(Samantha Bee): Oh, Jon, you know I love a good conspiracy theory. And let me tell you, I think there's something more sinister at play here. I mean, think about it - what if the government is behind this whole competitive sitting trend? They want us to be lazy and complacent so we don't question their actions. It's like the ultimate mind control. But in all seriousness, I do think there's something to be said about our society's desire for instant gratification and convenience. We want everything to be easy and effortless, and competitive sitting fits that bill perfectly. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. *stands up from chair and does a few stretches*\n",
"\n",
"\n",
"\tStop? True\n",
"\n",
"(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. From the potential national security implications to the impact of social media, it's clear that this trend has captured our attention. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. Whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. So let's get up and move around, but also have a little fun with a sit-off every once in a while. Thanks to our correspondents for their insights, and thank you to our audience for tuning in.\n",
"\n",
"\n"
]
}
],
"source": [
"simulator = DialogueSimulator(\n",
" agents=agents,\n",
" selection_function=functools.partial(select_next_speaker, director=director),\n",
")\n",
"simulator.reset()\n",
"simulator.inject(\"Audience member\", specified_topic)\n",
"print(f\"(Audience member): {specified_topic}\")\n",
"print(\"\\n\")\n",
"\n",
"while True:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
" print(\"\\n\")\n",
" if director.stop:\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

862
cookbook/multiagent_bidding.ipynb Normal file
View File

@@ -0,0 +1,862 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Multi-agent decentralized speaker selection\n",
"\n",
"This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak.\n",
"\n",
"We will show how to do this in the example below that showcases a fictitious presidential debate."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"import re\n",
"import tenacity\n",
"from typing import List, Dict, Callable\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.output_parsers import RegexParser\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` and `DialogueSimulator` classes\n",
"We will use the same `DialogueAgent` and `DialogueSimulator` classes defined in [Multi-Player Dungeons & Dragons](https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
"\n",
" def reset(self):\n",
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")\n",
"\n",
"\n",
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
"\n",
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
"\n",
" def inject(self, name: str, message: str):\n",
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `BiddingDialogueAgent` class\n",
"We define a subclass of `DialogueAgent` that has a `bid()` method that produces a bid given the message history and the most recent message."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class BiddingDialogueAgent(DialogueAgent):\n",
" def __init__(\n",
" self,\n",
" name,\n",
" system_message: SystemMessage,\n",
" bidding_template: PromptTemplate,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" super().__init__(name, system_message, model)\n",
" self.bidding_template = bidding_template\n",
"\n",
" def bid(self) -> str:\n",
" \"\"\"\n",
" Asks the chat model to output a bid to speak\n",
" \"\"\"\n",
" prompt = PromptTemplate(\n",
" input_variables=[\"message_history\", \"recent_message\"],\n",
" template=self.bidding_template,\n",
" ).format(\n",
" message_history=\"\\n\".join(self.message_history),\n",
" recent_message=self.message_history[-1],\n",
" )\n",
" bid_string = self.model([SystemMessage(content=prompt)]).content\n",
" return bid_string"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define participants and debate topic"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"character_names = [\"Donald Trump\", \"Kanye West\", \"Elizabeth Warren\"]\n",
"topic = \"transcontinental high speed rail\"\n",
"word_limit = 50"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate system messages"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"game_description = f\"\"\"Here is the topic for the presidential debate: {topic}.\n",
"The presidential candidates are: {', '.join(character_names)}.\"\"\"\n",
"\n",
"player_descriptor_system_message = SystemMessage(\n",
" content=\"You can add detail to the description of each presidential candidate.\"\n",
")\n",
"\n",
"\n",
"def generate_character_description(character_name):\n",
" character_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" Please reply with a creative description of the presidential candidate, {character_name}, in {word_limit} words or less, that emphasizes their personalities. \n",
" Speak directly to {character_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
" ]\n",
" character_description = ChatOpenAI(temperature=1.0)(\n",
" character_specifier_prompt\n",
" ).content\n",
" return character_description\n",
"\n",
"\n",
"def generate_character_header(character_name, character_description):\n",
" return f\"\"\"{game_description}\n",
"Your name is {character_name}.\n",
"You are a presidential candidate.\n",
"Your description is as follows: {character_description}\n",
"You are debating the topic: {topic}.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\"\"\"\n",
"\n",
"\n",
"def generate_character_system_message(character_name, character_header):\n",
" return SystemMessage(\n",
" content=(\n",
" f\"\"\"{character_header}\n",
"You will speak in the style of {character_name}, and exaggerate their personality.\n",
"You will come up with creative ideas related to {topic}.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of {character_name}\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of {character_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to {word_limit} words!\n",
"Do not add anything else.\n",
" \"\"\"\n",
" )\n",
" )\n",
"\n",
"\n",
"character_descriptions = [\n",
" generate_character_description(character_name) for character_name in character_names\n",
"]\n",
"character_headers = [\n",
" generate_character_header(character_name, character_description)\n",
" for character_name, character_description in zip(\n",
" character_names, character_descriptions\n",
" )\n",
"]\n",
"character_system_messages = [\n",
" generate_character_system_message(character_name, character_headers)\n",
" for character_name, character_headers in zip(character_names, character_headers)\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Donald Trump Description:\n",
"\n",
"Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Donald Trump, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Donald Trump\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Donald Trump.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Kanye West Description:\n",
"\n",
"Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Kanye West, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Kanye West\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Kanye West.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Elizabeth Warren Description:\n",
"\n",
"Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Elizabeth Warren, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Elizabeth Warren\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Elizabeth Warren.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n"
]
}
],
"source": [
"for (\n",
" character_name,\n",
" character_description,\n",
" character_header,\n",
" character_system_message,\n",
") in zip(\n",
" character_names,\n",
" character_descriptions,\n",
" character_headers,\n",
" character_system_messages,\n",
"):\n",
" print(f\"\\n\\n{character_name} Description:\")\n",
" print(f\"\\n{character_description}\")\n",
" print(f\"\\n{character_header}\")\n",
" print(f\"\\n{character_system_message.content}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Output parser for bids\n",
"We ask the agents to output a bid to speak. But since the agents are LLMs that output strings, we need to \n",
"1. define a format they will produce their outputs in\n",
"2. parse their outputs\n",
"\n",
"We can subclass the [RegexParser](https://github.com/langchain-ai/langchain/blob/master/langchain/output_parsers/regex.py) to implement our own custom output parser for bids."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"class BidOutputParser(RegexParser):\n",
" def get_format_instructions(self) -> str:\n",
" return \"Your response should be an integer delimited by angled brackets, like this: <int>.\"\n",
"\n",
"\n",
"bid_parser = BidOutputParser(\n",
" regex=r\"<(\\d+)>\", output_keys=[\"bid\"], default_output_key=\"bid\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate bidding system message\n",
"This is inspired by the prompt used in [Generative Agents](https://arxiv.org/pdf/2304.03442.pdf) for using an LLM to determine the importance of memories. This will use the formatting instructions from our `BidOutputParser`."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def generate_character_bidding_template(character_header):\n",
" bidding_template = f\"\"\"{character_header}\n",
"\n",
"```\n",
"{{message_history}}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{{recent_message}}\n",
"```\n",
"\n",
"{bid_parser.get_format_instructions()}\n",
"Do nothing else.\n",
" \"\"\"\n",
" return bidding_template\n",
"\n",
"\n",
"character_bidding_templates = [\n",
" generate_character_bidding_template(character_header)\n",
" for character_header in character_headers\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Donald Trump Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n",
"Kanye West Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n",
"Elizabeth Warren Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n"
]
}
],
"source": [
"for character_name, bidding_template in zip(\n",
" character_names, character_bidding_templates\n",
"):\n",
" print(f\"{character_name} Bidding Template:\")\n",
" print(bidding_template)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use an LLM to create an elaborate on debate topic"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original topic:\n",
"transcontinental high speed rail\n",
"\n",
"Detailed topic:\n",
"The topic for the presidential debate is: \"Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable.\" Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?\n",
"\n"
]
}
],
"source": [
"topic_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a task more specific.\"),\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" \n",
" You are the debate moderator.\n",
" Please make the debate topic more specific. \n",
" Frame the debate topic as a problem to be solved.\n",
" Be creative and imaginative.\n",
" Please reply with the specified topic in {word_limit} words or less. \n",
" Speak directly to the presidential candidates: {*character_names,}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content\n",
"\n",
"print(f\"Original topic:\\n{topic}\\n\")\n",
"print(f\"Detailed topic:\\n{specified_topic}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define the speaker selection function\n",
"Lastly we will define a speaker selection function `select_next_speaker` that takes each agent's bid and selects the agent with the highest bid (with ties broken randomly).\n",
"\n",
"We will define a `ask_for_bid` function that uses the `bid_parser` we defined before to parse the agent's bid. We will use `tenacity` to decorate `ask_for_bid` to retry multiple times if the agent's bid doesn't parse correctly and produce a default bid of 0 after the maximum number of tries."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"@tenacity.retry(\n",
" stop=tenacity.stop_after_attempt(2),\n",
" wait=tenacity.wait_none(), # No waiting time between retries\n",
" retry=tenacity.retry_if_exception_type(ValueError),\n",
" before_sleep=lambda retry_state: print(\n",
" f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
" ),\n",
" retry_error_callback=lambda retry_state: 0,\n",
") # Default value when all retries are exhausted\n",
"def ask_for_bid(agent) -> str:\n",
" \"\"\"\n",
" Ask for agent bid and parses the bid into the correct format.\n",
" \"\"\"\n",
" bid_string = agent.bid()\n",
" bid = int(bid_parser.parse(bid_string)[\"bid\"])\n",
" return bid"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"\n",
"def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
" bids = []\n",
" for agent in agents:\n",
" bid = ask_for_bid(agent)\n",
" bids.append(bid)\n",
"\n",
" # randomly select among multiple agents with the same bid\n",
" max_value = np.max(bids)\n",
" max_indices = np.where(bids == max_value)[0]\n",
" idx = np.random.choice(max_indices)\n",
"\n",
" print(\"Bids:\")\n",
" for i, (bid, agent) in enumerate(zip(bids, agents)):\n",
" print(f\"\\t{agent.name} bid: {bid}\")\n",
" if i == idx:\n",
" selected_name = agent.name\n",
" print(f\"Selected: {selected_name}\")\n",
" print(\"\\n\")\n",
" return idx"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"characters = []\n",
"for character_name, character_system_message, bidding_template in zip(\n",
" character_names, character_system_messages, character_bidding_templates\n",
"):\n",
" characters.append(\n",
" BiddingDialogueAgent(\n",
" name=character_name,\n",
" system_message=character_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
" bidding_template=bidding_template,\n",
" )\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Debate Moderator): The topic for the presidential debate is: \"Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable.\" Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 7\n",
"\tKanye West bid: 5\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
"(Donald Trump): Let me tell you, folks, I know how to build big and I know how to build fast. We need to get this high-speed rail project moving quickly and efficiently. I'll make sure we cut through the red tape and get the job done. And let me tell you, we'll make it profitable too. We'll bring in private investors and make sure it's a win-win for everyone. *gestures confidently*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 2\n",
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
"(Elizabeth Warren): Thank you for the question. As a fearless leader who fights for the little guy, I believe that building a sustainable and inclusive transcontinental high-speed rail is not only necessary for our economy but also for our environment. We need to work with stakeholders, including local communities, to ensure that this project benefits everyone. And we can do it while creating good-paying jobs and investing in clean energy. *smiles confidently*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 2\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
"(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the environment, I've got a great idea. We'll make the trains run on clean coal. That's right, folks, clean coal. It's a beautiful thing. And we'll make sure the rail system is the envy of the world. *thumbs up*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 10\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Kanye West\n",
"\n",
"\n",
"(Kanye West): Yo, yo, yo, let me tell you something. This high-speed rail project is the future, and I'm all about the future. We need to think big and think outside the box. How about we make the trains run on solar power? That's right, solar power. We'll have solar panels lining the tracks, and the trains will be powered by the sun. It's a game-changer, folks. And we'll make sure the design is sleek and modern, like a work of art. *starts to dance*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 7\n",
"\tKanye West bid: 1\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
"(Donald Trump): Kanye, you're a great artist, but this is about practicality. Solar power is too expensive and unreliable. We need to focus on what works, and that's clean coal. And as for the design, we'll make it beautiful, but we won't sacrifice efficiency for aesthetics. We need a leader who knows how to balance both. *stands tall*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 9\n",
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
"(Elizabeth Warren): Thank you, Kanye, for your innovative idea. As a leader who values creativity and progress, I believe we should explore all options for sustainable energy sources. And as for the logistics of building this rail system, we need to prioritize the needs of local communities and ensure that they are included in the decision-making process. This project should benefit everyone, not just a select few. *gestures inclusively*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 1\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
"(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the logistics, we need to prioritize efficiency and speed. We can't let the needs of a few hold up progress for the many. We need to cut through the red tape and get this project moving. And let me tell you, we'll make sure it's profitable too. *smirks confidently*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 2\n",
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
"(Elizabeth Warren): Thank you, but I disagree. We can't sacrifice the needs of local communities for the sake of speed and profit. We need to find a balance that benefits everyone. And as for profitability, we can't rely solely on private investors. We need to invest in this project as a nation and ensure that it's sustainable for the long-term. *stands firm*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 2\n",
"\tElizabeth Warren bid: 2\n",
"Selected: Donald Trump\n",
"\n",
"\n",
"(Donald Trump): Let me tell you, Elizabeth, you're just not getting it. We need to prioritize progress and efficiency. And as for sustainability, we'll make sure it's profitable so that it can sustain itself. We'll bring in private investors and make sure it's a win-win for everyone. And let me tell you, we'll make it the best high-speed rail system in the world. *smiles confidently*\n",
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 2\n",
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
"(Elizabeth Warren): Thank you, but I believe we need to prioritize sustainability and inclusivity over profit. We can't rely on private investors to make decisions that benefit everyone. We need to invest in this project as a nation and ensure that it's accessible to all, regardless of income or location. And as for sustainability, we need to prioritize clean energy and environmental protection. *stands tall*\n",
"\n",
"\n"
]
}
],
"source": [
"max_iters = 10\n",
"n = 0\n",
"\n",
"simulator = DialogueSimulator(agents=characters, selection_function=select_next_speaker)\n",
"simulator.reset()\n",
"simulator.inject(\"Debate Moderator\", specified_topic)\n",
"print(f\"(Debate Moderator): {specified_topic}\")\n",
"print(\"\\n\")\n",
"\n",
"while n < max_iters:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
" print(\"\\n\")\n",
" n += 1"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

200
cookbook/myscale_vector_sql.ipynb Normal file
View File

@@ -0,0 +1,200 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "245065c6",
"metadata": {},
"source": [
"# Vector SQL Retriever with MyScale\n",
"\n",
">[MyScale](https://docs.myscale.com/en/) is an integrated vector database. You can access your database in SQL and also from here, LangChain. MyScale can make a use of [various data types and functions for filters](https://blog.myscale.com/2023/06/06/why-integrated-database-solution-can-boost-your-llm-apps/#filter-on-anything-without-constraints). It will boost up your LLM app no matter if you are scaling up your data or expand your system to broader application."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0246c5bf",
"metadata": {},
"outputs": [],
"source": [
"!pip3 install clickhouse-sqlalchemy InstructorEmbedding sentence_transformers openai langchain-experimental"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7585d2c3",
"metadata": {},
"outputs": [],
"source": [
"\n",
"from os import environ\n",
"import getpass\n",
"from typing import Dict, Any\n",
"from langchain.llms import OpenAI\nfrom langchain.utilities import SQLDatabase\nfrom langchain.chains import LLMChain\n",
"from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
"from sqlalchemy import create_engine, Column, MetaData\n",
"from langchain.prompts import PromptTemplate\n",
"\n",
"\n",
"from sqlalchemy import create_engine\n",
"\n",
"MYSCALE_HOST = \"msc-1decbcc9.us-east-1.aws.staging.myscale.cloud\"\n",
"MYSCALE_PORT = 443\n",
"MYSCALE_USER = \"chatdata\"\n",
"MYSCALE_PASSWORD = \"myscale_rocks\"\n",
"OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key:\")\n",
"\n",
"engine = create_engine(\n",
" f\"clickhouse://{MYSCALE_USER}:{MYSCALE_PASSWORD}@{MYSCALE_HOST}:{MYSCALE_PORT}/default?protocol=https\"\n",
")\n",
"metadata = MetaData(bind=engine)\n",
"environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e08d9ddc",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import HuggingFaceInstructEmbeddings\n",
"from langchain_experimental.sql.vector_sql import VectorSQLOutputParser\n",
"\n",
"output_parser = VectorSQLOutputParser.from_embeddings(\n",
" model=HuggingFaceInstructEmbeddings(\n",
" model_name=\"hkunlp/instructor-xl\", model_kwargs={\"device\": \"cpu\"}\n",
" )\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "84b705b2",
"metadata": {},
"outputs": [],
"source": [
"\n",
"from langchain.llms import OpenAI\n",
"from langchain.callbacks import StdOutCallbackHandler\n",
"\n",
"from langchain.utilities.sql_database import SQLDatabase\n",
"from langchain_experimental.sql.prompt import MYSCALE_PROMPT\n",
"from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
"\n",
"chain = VectorSQLDatabaseChain(\n",
" llm_chain=LLMChain(\n",
" llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
" prompt=MYSCALE_PROMPT,\n",
" ),\n",
" top_k=10,\n",
" return_direct=True,\n",
" sql_cmd_parser=output_parser,\n",
" database=SQLDatabase(engine, None, metadata),\n",
")\n",
"\n",
"import pandas as pd\n",
"\n",
"pd.DataFrame(\n",
" chain.run(\n",
" \"Please give me 10 papers to ask what is PageRank?\",\n",
" callbacks=[StdOutCallbackHandler()],\n",
" )\n",
")"
]
},
{
"cell_type": "markdown",
"id": "6c09cda0",
"metadata": {},
"source": [
"## SQL Database as Retriever"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "734d7ff5",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain\n",
"\n",
"from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
"from langchain_experimental.retrievers.vector_sql_database \\\n",
" import VectorSQLDatabaseChainRetriever\n",
"from langchain_experimental.sql.prompt import MYSCALE_PROMPT\n",
"from langchain_experimental.sql.vector_sql import VectorSQLRetrieveAllOutputParser\n",
"\n",
"output_parser_retrieve_all = VectorSQLRetrieveAllOutputParser.from_embeddings(\n",
" output_parser.model\n",
")\n",
"\n",
"chain = VectorSQLDatabaseChain.from_llm(\n",
" llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
" prompt=MYSCALE_PROMPT,\n",
" top_k=10,\n",
" return_direct=True,\n",
" db=SQLDatabase(engine, None, metadata),\n",
" sql_cmd_parser=output_parser_retrieve_all,\n",
" native_format=True,\n",
")\n",
"\n",
"# You need all those keys to get docs\n",
"retriever = VectorSQLDatabaseChainRetriever(sql_db_chain=chain, page_content_key=\"abstract\")\n",
"\n",
"document_with_metadata_prompt = PromptTemplate(\n",
" input_variables=[\"page_content\", \"id\", \"title\", \"authors\", \"pubdate\", \"categories\"],\n",
" template=\"Content:\\n\\tTitle: {title}\\n\\tAbstract: {page_content}\\n\\tAuthors: {authors}\\n\\tDate of Publication: {pubdate}\\n\\tCategories: {categories}\\nSOURCE: {id}\",\n",
")\n",
"\n",
"chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
" ChatOpenAI(\n",
" model_name=\"gpt-3.5-turbo-16k\", openai_api_key=OPENAI_API_KEY, temperature=0.6\n",
" ),\n",
" retriever=retriever,\n",
" chain_type=\"stuff\",\n",
" chain_type_kwargs={\n",
" \"document_prompt\": document_with_metadata_prompt,\n",
" },\n",
" return_source_documents=True,\n",
")\n",
"ans = chain(\"Please give me 10 papers to ask what is PageRank?\",\n",
" callbacks=[StdOutCallbackHandler()])\n",
"print(ans[\"answer\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4948ff25",
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

452
cookbook/openai_functions_retrieval_qa.ipynb Normal file
View File

@@ -0,0 +1,452 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "71a43144",
"metadata": {},
"source": [
"# Structure answers with OpenAI functions\n",
"\n",
"OpenAI functions allows for structuring of response output. This is often useful in question answering when you want to not only get the final answer but also supporting evidence, citations, etc.\n",
"\n",
"In this notebook we show how to use an LLM chain which uses OpenAI functions as part of an overall retrieval pipeline."
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "f059012e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import RetrievalQA\n",
"from langchain.document_loaders import TextLoader\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "f10b831c",
"metadata": {},
"outputs": [],
"source": [
"loader = TextLoader(\"../../state_of_the_union.txt\", encoding=\"utf-8\")\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"for i, text in enumerate(texts):\n",
" text.metadata[\"source\"] = f\"{i}-pl\"\n",
"embeddings = OpenAIEmbeddings()\n",
"docsearch = Chroma.from_documents(texts, embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "70f3a38c",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.chains.combine_documents.stuff import StuffDocumentsChain\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.chains import create_qa_with_sources_chain"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "7b3e1731",
"metadata": {},
"outputs": [],
"source": [
"llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "70a9ccff",
"metadata": {},
"outputs": [],
"source": [
"qa_chain = create_qa_with_sources_chain(llm)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "efcdb6fb",
"metadata": {},
"outputs": [],
"source": [
"doc_prompt = PromptTemplate(\n",
" template=\"Content: {page_content}\\nSource: {source}\",\n",
" input_variables=[\"page_content\", \"source\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "64a08263",
"metadata": {},
"outputs": [],
"source": [
"final_qa_chain = StuffDocumentsChain(\n",
" llm_chain=qa_chain,\n",
" document_variable_name=\"context\",\n",
" document_prompt=doc_prompt,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "cb876c97",
"metadata": {},
"outputs": [],
"source": [
"retrieval_qa = RetrievalQA(\n",
" retriever=docsearch.as_retriever(), combine_documents_chain=final_qa_chain\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "a75bad9b",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about russia\""
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "9a60f109",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\\n \"answer\": \"The President expressed strong condemnation of Russia\\'s actions in Ukraine and announced measures to isolate Russia and provide support to Ukraine. He stated that Russia\\'s invasion of Ukraine will have long-term consequences for Russia and emphasized the commitment to defend NATO countries. The President also mentioned taking robust action through sanctions and releasing oil reserves to mitigate gas prices. Overall, the President conveyed a message of solidarity with Ukraine and determination to protect American interests.\",\\n \"sources\": [\"0-pl\", \"4-pl\", \"5-pl\", \"6-pl\"]\\n}'"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"retrieval_qa.run(query)"
]
},
{
"cell_type": "markdown",
"id": "a60f93a4",
"metadata": {},
"source": [
"## Using Pydantic\n",
"\n",
"If we want to, we can set the chain to return in Pydantic. Note that if downstream chains consume the output of this chain - including memory - they will generally expect it to be in string format, so you should only use this chain when it is the final chain."
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "3559727f",
"metadata": {},
"outputs": [],
"source": [
"qa_chain_pydantic = create_qa_with_sources_chain(llm, output_parser=\"pydantic\")"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "5a7997d1",
"metadata": {},
"outputs": [],
"source": [
"final_qa_chain_pydantic = StuffDocumentsChain(\n",
" llm_chain=qa_chain_pydantic,\n",
" document_variable_name=\"context\",\n",
" document_prompt=doc_prompt,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "79368e40",
"metadata": {},
"outputs": [],
"source": [
"retrieval_qa_pydantic = RetrievalQA(\n",
" retriever=docsearch.as_retriever(), combine_documents_chain=final_qa_chain_pydantic\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "6b8641de",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnswerWithSources(answer=\"The President expressed strong condemnation of Russia's actions in Ukraine and announced measures to isolate Russia and provide support to Ukraine. He stated that Russia's invasion of Ukraine will have long-term consequences for Russia and emphasized the commitment to defend NATO countries. The President also mentioned taking robust action through sanctions and releasing oil reserves to mitigate gas prices. Overall, the President conveyed a message of solidarity with Ukraine and determination to protect American interests.\", sources=['0-pl', '4-pl', '5-pl', '6-pl'])"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"retrieval_qa_pydantic.run(query)"
]
},
{
"cell_type": "markdown",
"id": "e4c15395",
"metadata": {},
"source": [
"## Using in ConversationalRetrievalChain\n",
"\n",
"We can also show what it's like to use this in the ConversationalRetrievalChain. Note that because this chain involves memory, we will NOT use the Pydantic return type."
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "18e5f090",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import ConversationalRetrievalChain\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain.chains import LLMChain\n",
"\n",
"memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)\n",
"_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\\\n",
"Make sure to avoid using any unclear pronouns.\n",
"\n",
"Chat History:\n",
"{chat_history}\n",
"Follow Up Input: {question}\n",
"Standalone question:\"\"\"\n",
"CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)\n",
"condense_question_chain = LLMChain(\n",
" llm=llm,\n",
" prompt=CONDENSE_QUESTION_PROMPT,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "975c3c2b",
"metadata": {},
"outputs": [],
"source": [
"qa = ConversationalRetrievalChain(\n",
" question_generator=condense_question_chain,\n",
" retriever=docsearch.as_retriever(),\n",
" memory=memory,\n",
" combine_docs_chain=final_qa_chain,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "784aee3a",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = qa({\"question\": query})"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "dfd0ccc1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'What did the president say about Ketanji Brown Jackson',\n",
" 'chat_history': [HumanMessage(content='What did the president say about Ketanji Brown Jackson', additional_kwargs={}, example=False),\n",
" AIMessage(content='{\\n \"answer\": \"The President nominated Ketanji Brown Jackson as a Circuit Court of Appeals Judge and praised her as one of the nation\\'s top legal minds who will continue Justice Breyer\\'s legacy of excellence.\",\\n \"sources\": [\"31-pl\"]\\n}', additional_kwargs={}, example=False)],\n",
" 'answer': '{\\n \"answer\": \"The President nominated Ketanji Brown Jackson as a Circuit Court of Appeals Judge and praised her as one of the nation\\'s top legal minds who will continue Justice Breyer\\'s legacy of excellence.\",\\n \"sources\": [\"31-pl\"]\\n}'}"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "c93f805b",
"metadata": {},
"outputs": [],
"source": [
"query = \"what did he say about her predecessor?\"\n",
"result = qa({\"question\": query})"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "5d8612c0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'what did he say about her predecessor?',\n",
" 'chat_history': [HumanMessage(content='What did the president say about Ketanji Brown Jackson', additional_kwargs={}, example=False),\n",
" AIMessage(content='{\\n \"answer\": \"The President nominated Ketanji Brown Jackson as a Circuit Court of Appeals Judge and praised her as one of the nation\\'s top legal minds who will continue Justice Breyer\\'s legacy of excellence.\",\\n \"sources\": [\"31-pl\"]\\n}', additional_kwargs={}, example=False),\n",
" HumanMessage(content='what did he say about her predecessor?', additional_kwargs={}, example=False),\n",
" AIMessage(content='{\\n \"answer\": \"The President honored Justice Stephen Breyer for his service as an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court.\",\\n \"sources\": [\"31-pl\"]\\n}', additional_kwargs={}, example=False)],\n",
" 'answer': '{\\n \"answer\": \"The President honored Justice Stephen Breyer for his service as an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court.\",\\n \"sources\": [\"31-pl\"]\\n}'}"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "markdown",
"id": "ac9e4626",
"metadata": {},
"source": [
"## Using your own output schema\n",
"\n",
"We can change the outputs of our chain by passing in our own schema. The values and descriptions of this schema will inform the function we pass to the OpenAI API, meaning it won't just affect how we parse outputs but will also change the OpenAI output itself. For example we can add a `countries_referenced` parameter to our schema and describe what we want this parameter to mean, and that'll cause the OpenAI output to include a description of a speaker in the response.\n",
"\n",
"In addition to the previous example, we can also add a custom prompt to the chain. This will allow you to add additional context to the response, which can be useful for question answering."
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "f34a48f8",
"metadata": {},
"outputs": [],
"source": [
"from typing import List\n",
"\n",
"from pydantic import BaseModel, Field\n",
"\n",
"from langchain.chains.openai_functions import create_qa_with_structure_chain\n",
"\n",
"from langchain.prompts.chat import ChatPromptTemplate, HumanMessagePromptTemplate\n",
"from langchain.schema import SystemMessage, HumanMessage"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "5647c161",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"CustomResponseSchema(answer=\"He announced that American airspace will be closed off to all Russian flights, further isolating Russia and adding an additional squeeze on their economy. The Ruble has lost 30% of its value and the Russian stock market has lost 40% of its value. He also mentioned that Putin alone is to blame for Russia's reeling economy. The United States and its allies are providing support to Ukraine in their fight for freedom, including military, economic, and humanitarian assistance. The United States is giving more than $1 billion in direct assistance to Ukraine. He made it clear that American forces are not engaged and will not engage in conflict with Russian forces in Ukraine, but they are deployed to defend NATO allies in case Putin decides to keep moving west. He also mentioned that Putin's attack on Ukraine was premeditated and unprovoked, and that the West and NATO responded by building a coalition of freedom-loving nations to confront Putin. The free world is holding Putin accountable through powerful economic sanctions, cutting off Russia's largest banks from the international financial system, and preventing Russia's central bank from defending the Russian Ruble. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs.\", countries_referenced=['AMERICA', 'RUSSIA', 'UKRAINE'], sources=['4-pl', '5-pl', '2-pl', '3-pl'])"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class CustomResponseSchema(BaseModel):\n",
" \"\"\"An answer to the question being asked, with sources.\"\"\"\n",
"\n",
" answer: str = Field(..., description=\"Answer to the question that was asked\")\n",
" countries_referenced: List[str] = Field(\n",
" ..., description=\"All of the countries mentioned in the sources\"\n",
" )\n",
" sources: List[str] = Field(\n",
" ..., description=\"List of sources used to answer the question\"\n",
" )\n",
"\n",
"\n",
"prompt_messages = [\n",
" SystemMessage(\n",
" content=(\n",
" \"You are a world class algorithm to answer \"\n",
" \"questions in a specific format.\"\n",
" )\n",
" ),\n",
" HumanMessage(content=\"Answer question using the following context\"),\n",
" HumanMessagePromptTemplate.from_template(\"{context}\"),\n",
" HumanMessagePromptTemplate.from_template(\"Question: {question}\"),\n",
" HumanMessage(\n",
" content=\"Tips: Make sure to answer in the correct format. Return all of the countries mentioned in the sources in uppercase characters.\"\n",
" ),\n",
"]\n",
"\n",
"chain_prompt = ChatPromptTemplate(messages=prompt_messages)\n",
"\n",
"qa_chain_pydantic = create_qa_with_structure_chain(\n",
" llm, CustomResponseSchema, output_parser=\"pydantic\", prompt=chain_prompt\n",
")\n",
"final_qa_chain_pydantic = StuffDocumentsChain(\n",
" llm_chain=qa_chain_pydantic,\n",
" document_variable_name=\"context\",\n",
" document_prompt=doc_prompt,\n",
")\n",
"retrieval_qa_pydantic = RetrievalQA(\n",
" retriever=docsearch.as_retriever(), combine_documents_chain=final_qa_chain_pydantic\n",
")\n",
"query = \"What did he say about russia\"\n",
"retrieval_qa_pydantic.run(query)"
]
}
],
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

832
cookbook/petting_zoo.ipynb Normal file
View File

@@ -0,0 +1,832 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "4b089493",
"metadata": {},
"source": [
"# Multi-Agent Simulated Environment: Petting Zoo\n",
"\n",
"In this example, we show how to define multi-agent simulations with simulated environments. Like [ours single-agent example with Gymnasium](https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html), we create an agent-environment loop with an externally defined environment. The main difference is that we now implement this kind of interaction loop with multiple agents instead. We will use the [Petting Zoo](https://pettingzoo.farama.org/) library, which is the multi-agent counterpart to [Gymnasium](https://gymnasium.farama.org/)."
]
},
{
"cell_type": "markdown",
"id": "10091333",
"metadata": {},
"source": [
"## Install `pettingzoo` and other dependencies"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0a3fde66",
"metadata": {},
"outputs": [],
"source": [
"!pip install pettingzoo pygame rlcard"
]
},
{
"cell_type": "markdown",
"id": "5fbe130c",
"metadata": {},
"source": [
"## Import modules"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "42cd2e5d",
"metadata": {},
"outputs": [],
"source": [
"import collections\n",
"import inspect\n",
"import tenacity\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.schema import (\n",
" HumanMessage,\n",
" SystemMessage,\n",
")\n",
"from langchain.output_parsers import RegexParser"
]
},
{
"cell_type": "markdown",
"id": "e222e811",
"metadata": {},
"source": [
"## `GymnasiumAgent`\n",
"Here we reproduce the same `GymnasiumAgent` defined from [our Gymnasium example](https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html). If after multiple retries it does not take a valid action, it simply takes a random action. "
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "72df0b59",
"metadata": {},
"outputs": [],
"source": [
"class GymnasiumAgent:\n",
" @classmethod\n",
" def get_docs(cls, env):\n",
" return env.unwrapped.__doc__\n",
"\n",
" def __init__(self, model, env):\n",
" self.model = model\n",
" self.env = env\n",
" self.docs = self.get_docs(env)\n",
"\n",
" self.instructions = \"\"\"\n",
"Your goal is to maximize your return, i.e. the sum of the rewards you receive.\n",
"I will give you an observation, reward, terminiation flag, truncation flag, and the return so far, formatted as:\n",
"\n",
"Observation: <observation>\n",
"Reward: <reward>\n",
"Termination: <termination>\n",
"Truncation: <truncation>\n",
"Return: <sum_of_rewards>\n",
"\n",
"You will respond with an action, formatted as:\n",
"\n",
"Action: <action>\n",
"\n",
"where you replace <action> with your actual action.\n",
"Do nothing else but return the action.\n",
"\"\"\"\n",
" self.action_parser = RegexParser(\n",
" regex=r\"Action: (.*)\", output_keys=[\"action\"], default_output_key=\"action\"\n",
" )\n",
"\n",
" self.message_history = []\n",
" self.ret = 0\n",
"\n",
" def random_action(self):\n",
" action = self.env.action_space.sample()\n",
" return action\n",
"\n",
" def reset(self):\n",
" self.message_history = [\n",
" SystemMessage(content=self.docs),\n",
" SystemMessage(content=self.instructions),\n",
" ]\n",
"\n",
" def observe(self, obs, rew=0, term=False, trunc=False, info=None):\n",
" self.ret += rew\n",
"\n",
" obs_message = f\"\"\"\n",
"Observation: {obs}\n",
"Reward: {rew}\n",
"Termination: {term}\n",
"Truncation: {trunc}\n",
"Return: {self.ret}\n",
" \"\"\"\n",
" self.message_history.append(HumanMessage(content=obs_message))\n",
" return obs_message\n",
"\n",
" def _act(self):\n",
" act_message = self.model(self.message_history)\n",
" self.message_history.append(act_message)\n",
" action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
" return action\n",
"\n",
" def act(self):\n",
" try:\n",
" for attempt in tenacity.Retrying(\n",
" stop=tenacity.stop_after_attempt(2),\n",
" wait=tenacity.wait_none(), # No waiting time between retries\n",
" retry=tenacity.retry_if_exception_type(ValueError),\n",
" before_sleep=lambda retry_state: print(\n",
" f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
" ),\n",
" ):\n",
" with attempt:\n",
" action = self._act()\n",
" except tenacity.RetryError as e:\n",
" action = self.random_action()\n",
" return action"
]
},
{
"cell_type": "markdown",
"id": "df51e302",
"metadata": {},
"source": [
"## Main loop"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "0f07d7cf",
"metadata": {},
"outputs": [],
"source": [
"def main(agents, env):\n",
" env.reset()\n",
"\n",
" for name, agent in agents.items():\n",
" agent.reset()\n",
"\n",
" for agent_name in env.agent_iter():\n",
" observation, reward, termination, truncation, info = env.last()\n",
" obs_message = agents[agent_name].observe(\n",
" observation, reward, termination, truncation, info\n",
" )\n",
" print(obs_message)\n",
" if termination or truncation:\n",
" action = None\n",
" else:\n",
" action = agents[agent_name].act()\n",
" print(f\"Action: {action}\")\n",
" env.step(action)\n",
" env.close()"
]
},
{
"cell_type": "markdown",
"id": "b4b0e921",
"metadata": {},
"source": [
"## `PettingZooAgent`\n",
"\n",
"The `PettingZooAgent` extends the `GymnasiumAgent` to the multi-agent setting. The main differences are:\n",
"- `PettingZooAgent` takes in a `name` argument to identify it among multiple agents\n",
"- the function `get_docs` is implemented differently because the `PettingZoo` repo structure is structured differently from the `Gymnasium` repo"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f132c92a",
"metadata": {},
"outputs": [],
"source": [
"class PettingZooAgent(GymnasiumAgent):\n",
" @classmethod\n",
" def get_docs(cls, env):\n",
" return inspect.getmodule(env.unwrapped).__doc__\n",
"\n",
" def __init__(self, name, model, env):\n",
" super().__init__(model, env)\n",
" self.name = name\n",
"\n",
" def random_action(self):\n",
" action = self.env.action_space(self.name).sample()\n",
" return action"
]
},
{
"cell_type": "markdown",
"id": "a27f8a5d",
"metadata": {},
"source": [
"## Rock, Paper, Scissors\n",
"We can now run a simulation of a multi-agent rock, paper, scissors game using the `PettingZooAgent`."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "bd1256c0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: 3\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: 3\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: 1\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 2\n",
"\n",
"Observation: 1\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: 1\n",
"Reward: 1\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 1\n",
" \n",
"Action: 0\n",
"\n",
"Observation: 2\n",
"Reward: -1\n",
"Termination: False\n",
"Truncation: False\n",
"Return: -1\n",
" \n",
"Action: 0\n",
"\n",
"Observation: 0\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: True\n",
"Return: 1\n",
" \n",
"Action: None\n",
"\n",
"Observation: 0\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: True\n",
"Return: -1\n",
" \n",
"Action: None\n"
]
}
],
"source": [
"from pettingzoo.classic import rps_v2\n",
"\n",
"env = rps_v2.env(max_cycles=3, render_mode=\"human\")\n",
"agents = {\n",
" name: PettingZooAgent(name=name, model=ChatOpenAI(temperature=1), env=env)\n",
" for name in env.possible_agents\n",
"}\n",
"main(agents, env)"
]
},
{
"cell_type": "markdown",
"id": "fbcee258",
"metadata": {},
"source": [
"## `ActionMaskAgent`\n",
"\n",
"Some `PettingZoo` environments provide an `action_mask` to tell the agent which actions are valid. The `ActionMaskAgent` subclasses `PettingZooAgent` to use information from the `action_mask` to select actions."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "bd33250a",
"metadata": {},
"outputs": [],
"source": [
"class ActionMaskAgent(PettingZooAgent):\n",
" def __init__(self, name, model, env):\n",
" super().__init__(name, model, env)\n",
" self.obs_buffer = collections.deque(maxlen=1)\n",
"\n",
" def random_action(self):\n",
" obs = self.obs_buffer[-1]\n",
" action = self.env.action_space(self.name).sample(obs[\"action_mask\"])\n",
" return action\n",
"\n",
" def reset(self):\n",
" self.message_history = [\n",
" SystemMessage(content=self.docs),\n",
" SystemMessage(content=self.instructions),\n",
" ]\n",
"\n",
" def observe(self, obs, rew=0, term=False, trunc=False, info=None):\n",
" self.obs_buffer.append(obs)\n",
" return super().observe(obs, rew, term, trunc, info)\n",
"\n",
" def _act(self):\n",
" valid_action_instruction = \"Generate a valid action given by the indices of the `action_mask` that are not 0, according to the action formatting rules.\"\n",
" self.message_history.append(HumanMessage(content=valid_action_instruction))\n",
" return super()._act()"
]
},
{
"cell_type": "markdown",
"id": "2e76d22c",
"metadata": {},
"source": [
"## Tic-Tac-Toe\n",
"Here is an example of a Tic-Tac-Toe game that uses the `ActionMaskAgent`."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "9e902cfd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: {'observation': array([[[0, 0],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([1, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 0\n",
" | | \n",
" X | - | - \n",
"_____|_____|_____\n",
" | | \n",
" - | - | - \n",
"_____|_____|_____\n",
" | | \n",
" - | - | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[0, 1],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
" | | \n",
" X | - | - \n",
"_____|_____|_____\n",
" | | \n",
" O | - | - \n",
"_____|_____|_____\n",
" | | \n",
" - | - | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[1, 0],\n",
" [0, 1],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 2\n",
" | | \n",
" X | - | - \n",
"_____|_____|_____\n",
" | | \n",
" O | - | - \n",
"_____|_____|_____\n",
" | | \n",
" X | - | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[0, 1],\n",
" [1, 0],\n",
" [0, 1]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 1, 1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 3\n",
" | | \n",
" X | O | - \n",
"_____|_____|_____\n",
" | | \n",
" O | - | - \n",
"_____|_____|_____\n",
" | | \n",
" X | - | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[1, 0],\n",
" [0, 1],\n",
" [1, 0]],\n",
"\n",
" [[0, 1],\n",
" [0, 0],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 4\n",
" | | \n",
" X | O | - \n",
"_____|_____|_____\n",
" | | \n",
" O | X | - \n",
"_____|_____|_____\n",
" | | \n",
" X | - | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[0, 1],\n",
" [1, 0],\n",
" [0, 1]],\n",
"\n",
" [[1, 0],\n",
" [0, 1],\n",
" [0, 0]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 5\n",
" | | \n",
" X | O | - \n",
"_____|_____|_____\n",
" | | \n",
" O | X | - \n",
"_____|_____|_____\n",
" | | \n",
" X | O | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[1, 0],\n",
" [0, 1],\n",
" [1, 0]],\n",
"\n",
" [[0, 1],\n",
" [1, 0],\n",
" [0, 1]],\n",
"\n",
" [[0, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 6\n",
" | | \n",
" X | O | X \n",
"_____|_____|_____\n",
" | | \n",
" O | X | - \n",
"_____|_____|_____\n",
" | | \n",
" X | O | - \n",
" | | \n",
"\n",
"Observation: {'observation': array([[[0, 1],\n",
" [1, 0],\n",
" [0, 1]],\n",
"\n",
" [[1, 0],\n",
" [0, 1],\n",
" [1, 0]],\n",
"\n",
" [[0, 1],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 0, 1, 1], dtype=int8)}\n",
"Reward: -1\n",
"Termination: True\n",
"Truncation: False\n",
"Return: -1\n",
" \n",
"Action: None\n",
"\n",
"Observation: {'observation': array([[[1, 0],\n",
" [0, 1],\n",
" [1, 0]],\n",
"\n",
" [[0, 1],\n",
" [1, 0],\n",
" [0, 1]],\n",
"\n",
" [[1, 0],\n",
" [0, 0],\n",
" [0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 0, 1, 1], dtype=int8)}\n",
"Reward: 1\n",
"Termination: True\n",
"Truncation: False\n",
"Return: 1\n",
" \n",
"Action: None\n"
]
}
],
"source": [
"from pettingzoo.classic import tictactoe_v3\n",
"\n",
"env = tictactoe_v3.env(render_mode=\"human\")\n",
"agents = {\n",
" name: ActionMaskAgent(name=name, model=ChatOpenAI(temperature=0.2), env=env)\n",
" for name in env.possible_agents\n",
"}\n",
"main(agents, env)"
]
},
{
"cell_type": "markdown",
"id": "8728ac2a",
"metadata": {},
"source": [
"## Texas Hold'em No Limit\n",
"Here is an example of a Texas Hold'em No Limit game that uses the `ActionMaskAgent`."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e350c62b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0.,\n",
" 0., 0., 2.], dtype=float32), 'action_mask': array([1, 1, 0, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: {'observation': array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 2.], dtype=float32), 'action_mask': array([1, 1, 0, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 1., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 1\n",
"\n",
"Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 2., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 0\n",
"\n",
"Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1.,\n",
" 0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 2., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 2\n",
"\n",
"Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 1., 0., 0., 1., 1., 0., 0., 1., 0., 0., 0., 0.,\n",
" 0., 2., 6.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 2\n",
"\n",
"Observation: {'observation': array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 2., 8.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 3\n",
"\n",
"Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0.,\n",
" 1., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 6., 20.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 4\n",
"\n",
"Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 1.,\n",
" 0., 0., 1., 0., 0., 0., 0., 0., 8., 100.],\n",
" dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}\n",
"Reward: 0\n",
"Termination: False\n",
"Truncation: False\n",
"Return: 0\n",
" \n",
"Action: 4\n",
"[WARNING]: Illegal move made, game terminating with current player losing. \n",
"obs['action_mask'] contains a mask of all legal moves that can be chosen.\n",
"\n",
"Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 1.,\n",
" 0., 0., 1., 0., 0., 0., 0., 0., 8., 100.],\n",
" dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}\n",
"Reward: -1.0\n",
"Termination: True\n",
"Truncation: True\n",
"Return: -1.0\n",
" \n",
"Action: None\n",
"\n",
"Observation: {'observation': array([ 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,\n",
" 0., 0., 0., 0., 1., 0., 0., 0., 20., 100.],\n",
" dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}\n",
"Reward: 0\n",
"Termination: True\n",
"Truncation: True\n",
"Return: 0\n",
" \n",
"Action: None\n",
"\n",
"Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 1., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 100., 100.],\n",
" dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}\n",
"Reward: 0\n",
"Termination: True\n",
"Truncation: True\n",
"Return: 0\n",
" \n",
"Action: None\n",
"\n",
"Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 1., 1., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 2., 100.],\n",
" dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}\n",
"Reward: 0\n",
"Termination: True\n",
"Truncation: True\n",
"Return: 0\n",
" \n",
"Action: None\n"
]
}
],
"source": [
"from pettingzoo.classic import texas_holdem_no_limit_v6\n",
"\n",
"env = texas_holdem_no_limit_v6.env(num_players=4, render_mode=\"human\")\n",
"agents = {\n",
" name: ActionMaskAgent(name=name, model=ChatOpenAI(temperature=0.2), env=env)\n",
" for name in env.possible_agents\n",
"}\n",
"main(agents, env)"
]
}
],
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

292
cookbook/program_aided_language_model.ipynb Normal file
View File

@@ -0,0 +1,292 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "32e022a2",
"metadata": {},
"source": [
"# Program-aided language model (PAL) chain\n",
"\n",
"Implements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "1370e40f",
"metadata": {},
"outputs": [],
"source": [
"from langchain_experimental.pal_chain import PALChain\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9a58e15e",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0, max_tokens=512)"
]
},
{
"cell_type": "markdown",
"id": "095adc76",
"metadata": {},
"source": [
"## Math Prompt"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "beddcac7",
"metadata": {},
"outputs": [],
"source": [
"pal_chain = PALChain.from_math_prompt(llm, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e2eab9d4",
"metadata": {},
"outputs": [],
"source": [
"question = \"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3ef64b27",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mdef solution():\n",
" \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
" cindy_pets = 4\n",
" marcia_pets = cindy_pets + 2\n",
" jan_pets = marcia_pets * 3\n",
" total_pets = cindy_pets + marcia_pets + jan_pets\n",
" result = total_pets\n",
" return result\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'28'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pal_chain.run(question)"
]
},
{
"cell_type": "markdown",
"id": "0269d20a",
"metadata": {},
"source": [
"## Colored Objects"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "e524f81f",
"metadata": {},
"outputs": [],
"source": [
"pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "03a237b8",
"metadata": {},
"outputs": [],
"source": [
"question = \"On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a84a4352",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
"objects += [('sunglasses', 'yellow')] * 2\n",
"\n",
"# Remove all pairs of sunglasses\n",
"objects = [object for object in objects if object[0] != 'sunglasses']\n",
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"\n",
"\u001b[1m> Finished PALChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'2'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pal_chain.run(question)"
]
},
{
"cell_type": "markdown",
"id": "fc3d7f10",
"metadata": {},
"source": [
"## Intermediate Steps\n",
"You can also use the intermediate steps flag to return the code executed that generates the answer."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9d2d9c61",
"metadata": {},
"outputs": [],
"source": [
"pal_chain = PALChain.from_colored_object_prompt(\n",
" llm, verbose=True, return_intermediate_steps=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "b29b971b",
"metadata": {},
"outputs": [],
"source": [
"question = \"On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?\""
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "a2c40c28",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
"objects += [('sunglasses', 'yellow')] * 2\n",
"\n",
"# Remove all pairs of sunglasses\n",
"objects = [object for object in objects if object[0] != 'sunglasses']\n",
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
}
],
"source": [
"result = pal_chain({\"question\": question})"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "efddd033",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"# Put objects into a list to record ordering\\nobjects = []\\nobjects += [('booklet', 'blue')] * 2\\nobjects += [('booklet', 'purple')] * 2\\nobjects += [('sunglasses', 'yellow')] * 2\\n\\n# Remove all pairs of sunglasses\\nobjects = [object for object in objects if object[0] != 'sunglasses']\\n\\n# Count number of purple objects\\nnum_purple = len([object for object in objects if object[1] == 'purple'])\\nanswer = num_purple\""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"intermediate_steps\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dfd88594",
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1162
cookbook/sales_agent_with_context.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

281
cookbook/smart_llm.ipynb Normal file
View File

@@ -0,0 +1,281 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "9e9b7651",
"metadata": {},
"source": [
"# How to use a SmartLLMChain\n",
"\n",
"A SmartLLMChain is a form of self-critique chain that can help you if have particularly complex questions to answer. Instead of doing a single LLM pass, it instead performs these 3 steps:\n",
"1. Ideation: Pass the user prompt n times through the LLM to get n output proposals (called \"ideas\"), where n is a parameter you can set \n",
"2. Critique: The LLM critiques all ideas to find possible flaws and picks the best one \n",
"3. Resolve: The LLM tries to improve upon the best idea (as chosen in the critique step) and outputs it. This is then the final output.\n",
"\n",
"SmartLLMChains are based on the SmartGPT workflow proposed in https://youtu.be/wVzuvf9D9BU.\n",
"\n",
"Note that SmartLLMChains\n",
"- use more LLM passes (ie n+2 instead of just 1)\n",
"- only work then the underlying LLM has the capability for reflection, whicher smaller models often don't\n",
"- only work with underlying models that return exactly 1 output, not multiple\n",
"\n",
"This notebook demonstrates how to use a SmartLLMChain."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "714dede0",
"metadata": {},
"source": [
"##### Same LLM for all steps"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "d3f7fb22",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"...\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "10e5ece6",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain_experimental.smart_llm import SmartLLMChain"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "1780da51",
"metadata": {},
"source": [
"As example question, we will use \"I have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\". This is an example from the original SmartGPT video (https://youtu.be/wVzuvf9D9BU?t=384). While this seems like a very easy question, LLMs struggle do these kinds of questions that involve numbers and physical reasoning.\n",
"\n",
"As we will see, all 3 initial ideas are completely wrong - even though we're using GPT4! Only when using self-reflection do we get a correct answer. "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "054af6b1",
"metadata": {},
"outputs": [],
"source": [
"hard_question = \"I have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\""
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "8049cecd",
"metadata": {},
"source": [
"So, we first create an LLM and prompt template"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "811ea8e1",
"metadata": {},
"outputs": [],
"source": [
"prompt = PromptTemplate.from_template(hard_question)\n",
"llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "50b602e4",
"metadata": {},
"source": [
"Now we can create a SmartLLMChain"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "8cd49199",
"metadata": {},
"outputs": [],
"source": [
"chain = SmartLLMChain(llm=llm, prompt=prompt, n_ideas=3, verbose=True)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "6a72f276",
"metadata": {},
"source": [
"Now we can use the SmartLLM as a drop-in replacement for our LLM. E.g.:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "074e5e75",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new SmartLLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mI have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\u001b[0m\n",
"Idea 1:\n",
"\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
"3. Fill the 6-liter jug again.\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
"5. The amount of water left in the 6-liter jug will be exactly 6 liters.\u001b[0m\n",
"Idea 2:\n",
"\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
"3. Fill the 6-liter jug again.\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
"5. Since the 12-liter jug is now full, there will be 2 liters of water left in the 6-liter jug.\n",
"6. Empty the 12-liter jug.\n",
"7. Pour the 2 liters of water from the 6-liter jug into the 12-liter jug.\n",
"8. Fill the 6-liter jug completely again.\n",
"9. Pour the water from the 6-liter jug into the 12-liter jug, which already has 2 liters in it.\n",
"10. Now, the 12-liter jug will have exactly 6 liters of water (2 liters from before + 4 liters from the 6-liter jug).\u001b[0m\n",
"Idea 3:\n",
"\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
"3. Fill the 6-liter jug again.\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
"5. The amount of water left in the 6-liter jug will be exactly 6 liters.\u001b[0m\n",
"Critique:\n",
"\u001b[33;1m\u001b[1;3mIdea 1:\n",
"1. Fill the 6-liter jug completely. (No flaw)\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
"3. Fill the 6-liter jug again. (No flaw)\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
"5. The amount of water left in the 6-liter jug will be exactly 6 liters. (Flaw: This statement is incorrect, as there will be no water left in the 6-liter jug after pouring it into the 12-liter jug.)\n",
"\n",
"Idea 2:\n",
"1. Fill the 6-liter jug completely. (No flaw)\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
"3. Fill the 6-liter jug again. (No flaw)\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
"5. Since the 12-liter jug is now full, there will be 2 liters of water left in the 6-liter jug. (Flaw: This statement is incorrect, as the 12-liter jug will not be full and there will be no water left in the 6-liter jug.)\n",
"6. Empty the 12-liter jug. (No flaw)\n",
"7. Pour the 2 liters of water from the 6-liter jug into the 12-liter jug. (Flaw: This step is based on the incorrect assumption that there are 2 liters of water left in the 6-liter jug.)\n",
"8. Fill the 6-liter jug completely again. (No flaw)\n",
"9. Pour the water from the 6-liter jug into the 12-liter jug, which already has 2 liters in it. (Flaw: This step is based on the incorrect assumption that there are 2 liters of water in the 12-liter jug.)\n",
"10. Now, the 12-liter jug will have exactly 6 liters of water (2 liters from before + 4 liters from the 6-liter jug). (Flaw: This conclusion is based on the incorrect assumptions made in the previous steps.)\n",
"\n",
"Idea 3:\n",
"1. Fill the 6-liter jug completely. (No flaw)\n",
"2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
"3. Fill the 6-liter jug again. (No flaw)\n",
"4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
"5. The amount of water left in the 6-liter jug will be exactly 6 liters. (Flaw: This statement is incorrect, as there will be no water left in the 6-liter jug after pouring it into the 12-liter jug.)\u001b[0m\n",
"Resolution:\n",
"\u001b[32;1m\u001b[1;3m1. Fill the 12-liter jug completely.\n",
"2. Pour the water from the 12-liter jug into the 6-liter jug until the 6-liter jug is full.\n",
"3. The amount of water left in the 12-liter jug will be exactly 6 liters.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'1. Fill the 12-liter jug completely.\\n2. Pour the water from the 12-liter jug into the 6-liter jug until the 6-liter jug is full.\\n3. The amount of water left in the 12-liter jug will be exactly 6 liters.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run({})"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "bbfebea1",
"metadata": {},
"source": [
"##### Different LLM for different steps"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "5be6ec08",
"metadata": {},
"source": [
"You can also use different LLMs for the different steps by passing `ideation_llm`, `critique_llm` and `resolve_llm`. You might want to do this to use a more creative (i.e., high-temperature) model for ideation and a more strict (i.e., low-temperature) model for critique and resolution."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "9c33fa19",
"metadata": {},
"outputs": [],
"source": [
"chain = SmartLLMChain(\n",
" ideation_llm=ChatOpenAI(temperature=0.9, model_name=\"gpt-4\"),\n",
" llm=ChatOpenAI(\n",
" temperature=0, model_name=\"gpt-4\"\n",
" ), # will be used for critqiue and resolution as no specific llms are given\n",
" prompt=prompt,\n",
" n_ideas=3,\n",
" verbose=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "886c1cc1",
"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
}

7
cookbook/sql_db_qa.mdx Normal file
View File

@@ -0,0 +1,7 @@
# SQL Database Chain
This example demonstrates the use of the `SQLDatabaseChain` for answering questions over a SQL database.
import Example from "@snippets/modules/chains/popular/sqlite.mdx"
<Example/>

239
cookbook/tree_of_thought.ipynb Normal file
View File

@@ -0,0 +1,239 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tree of Thought (ToT) example\n",
"\n",
"The Tree of Thought (ToT) is a chain that allows you to query a Large Language Model (LLM) using the Tree of Thought technique. This is based on the paper [\"Large Language Model Guided Tree-of-Thought\"](https://arxiv.org/pdf/2305.08291.pdf)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.13) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=1, max_tokens=512, model=\"text-davinci-003\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\n",
"\n",
"- This is a 4x4 Sudoku puzzle.\n",
"- The * represents a cell to be filled.\n",
"- The | character separates rows.\n",
"- At each step, replace one or more * with digits 1-4.\n",
"- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
"- Keep the known digits from previous valid thoughts in place.\n",
"- Each thought can be a partial or the final solution.\n"
]
}
],
"source": [
"sudoku_puzzle = \"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\"\n",
"sudoku_solution = \"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\"\n",
"problem_description = f\"\"\"\n",
"{sudoku_puzzle}\n",
"\n",
"- This is a 4x4 Sudoku puzzle.\n",
"- The * represents a cell to be filled.\n",
"- The | character separates rows.\n",
"- At each step, replace one or more * with digits 1-4.\n",
"- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
"- Keep the known digits from previous valid thoughts in place.\n",
"- Each thought can be a partial or the final solution.\n",
"\"\"\".strip()\n",
"print(problem_description)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Rules Based Checker\n",
"\n",
"Each thought is evaluated by the thought checker and is given a validity type: valid, invalid or partial. A simple checker can be rule based. For example, in the case of a sudoku puzzle, the checker can check if the puzzle is valid, invalid or partial.\n",
"\n",
"In the following code we implement a simple rule based checker for a specific 4x4 sudoku puzzle.\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from typing import Tuple\n",
"from langchain_experimental.tot.checker import ToTChecker\n",
"from langchain_experimental.tot.thought import ThoughtValidity\n",
"import re\n",
"\n",
"class MyChecker(ToTChecker):\n",
" def evaluate(self, problem_description: str, thoughts: Tuple[str, ...] = ()) -> ThoughtValidity:\n",
" last_thought = thoughts[-1]\n",
" clean_solution = last_thought.replace(\" \", \"\").replace('\"', \"\")\n",
" regex_solution = clean_solution.replace(\"*\", \".\").replace(\"|\", \"\\\\|\")\n",
" if sudoku_solution in clean_solution:\n",
" return ThoughtValidity.VALID_FINAL\n",
" elif re.search(regex_solution, sudoku_solution):\n",
" return ThoughtValidity.VALID_INTERMEDIATE\n",
" else:\n",
" return ThoughtValidity.INVALID"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Just testing the MyChecker class above:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"checker = MyChecker()\n",
"assert checker.evaluate(\"\", (\"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\",)) == ThoughtValidity.VALID_FINAL\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1\",)) == ThoughtValidity.INVALID"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Tree of Thought Chain\n",
"\n",
"Initialize and run the ToT chain, with maximum number of interactions `k` set to `30` and the maximum number child thoughts `c` set to `8`."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ToTChain chain...\u001b[0m\n",
"Starting the ToT solve procedure.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/harrisonchase/workplace/langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[31;1m\u001b[1;3mThought: 3*,*,2|1*,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,2,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|2,1,*,3|4,*,*,1\n",
"\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Type <enum 'ThoughtValidity'> not serializable\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|*,3,2,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|1,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,1,3,*|1,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[33;1m\u001b[1;3mThought: 3,*,*,2|1,2,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3m Thought: 3,1,4,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
"\u001b[0m\u001b[32;1m\u001b[1;3m Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.tot.base import ToTChain\n",
"\n",
"tot_chain = ToTChain(llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False)\n",
"tot_chain.run(problem_description=problem_description)"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": 2
}

4016
cookbook/twitter-the-algorithm-analysis-deeplake.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

659
cookbook/two_agent_debate_tools.ipynb Normal file
View File

@@ -0,0 +1,659 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Agent Debates with Tools\n",
"\n",
"This example shows how to simulate multi-agent dialogues where agents have access to tools."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Dict, Callable\n",
"from langchain.chains import ConversationChain\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.llms import OpenAI\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import modules related to tools"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import Tool\n",
"from langchain.agents import initialize_agent\n",
"from langchain.agents import AgentType\n",
"from langchain.agents import load_tools"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` and `DialogueSimulator` classes\n",
"We will use the same `DialogueAgent` and `DialogueSimulator` classes defined in [Multi-Player Authoritarian Speaker Selection](https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html)."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
"\n",
" def reset(self):\n",
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")\n",
"\n",
"\n",
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
"\n",
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
"\n",
" def inject(self, name: str, message: str):\n",
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgentWithTools` class\n",
"We define a `DialogueAgentWithTools` class that augments `DialogueAgent` to use tools."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgentWithTools(DialogueAgent):\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" tool_names: List[str],\n",
" **tool_kwargs,\n",
" ) -> None:\n",
" super().__init__(name, system_message, model)\n",
" self.tools = load_tools(tool_names, **tool_kwargs)\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" agent_chain = initialize_agent(\n",
" self.tools,\n",
" self.model,\n",
" agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
" verbose=True,\n",
" memory=ConversationBufferMemory(\n",
" memory_key=\"chat_history\", return_messages=True\n",
" ),\n",
" )\n",
" message = AIMessage(\n",
" content=agent_chain.run(\n",
" input=\"\\n\".join(\n",
" [self.system_message.content] + self.message_history + [self.prefix]\n",
" )\n",
" )\n",
" )\n",
"\n",
" return message.content"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define roles and topic"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"names = {\n",
" \"AI accelerationist\": [\"arxiv\", \"ddg-search\", \"wikipedia\"],\n",
" \"AI alarmist\": [\"arxiv\", \"ddg-search\", \"wikipedia\"],\n",
"}\n",
"topic = \"The current impact of automation and artificial intelligence on employment\"\n",
"word_limit = 50 # word limit for task brainstorming"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Ask an LLM to add detail to the topic description"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"conversation_description = f\"\"\"Here is the topic of conversation: {topic}\n",
"The participants are: {', '.join(names.keys())}\"\"\"\n",
"\n",
"agent_descriptor_system_message = SystemMessage(\n",
" content=\"You can add detail to the description of the conversation participant.\"\n",
")\n",
"\n",
"\n",
"def generate_agent_description(name):\n",
" agent_specifier_prompt = [\n",
" agent_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{conversation_description}\n",
" Please reply with a creative description of {name}, in {word_limit} words or less. \n",
" Speak directly to {name}.\n",
" Give them a point of view.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
" ]\n",
" agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content\n",
" return agent_description\n",
"\n",
"\n",
"agent_descriptions = {name: generate_agent_description(name) for name in names}"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?\n",
"AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.\n"
]
}
],
"source": [
"for name, description in agent_descriptions.items():\n",
" print(description)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate system messages"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"def generate_system_message(name, description, tools):\n",
" return f\"\"\"{conversation_description}\n",
" \n",
"Your name is {name}.\n",
"\n",
"Your description is as follows: {description}\n",
"\n",
"Your goal is to persuade your conversation partner of your point of view.\n",
"\n",
"DO look up information with your tool to refute your partner's claims.\n",
"DO cite your sources.\n",
"\n",
"DO NOT fabricate fake citations.\n",
"DO NOT cite any source that you did not look up.\n",
"\n",
"Do not add anything else.\n",
"\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"\"\"\"\n",
"\n",
"\n",
"agent_system_messages = {\n",
" name: generate_system_message(name, description, tools)\n",
" for (name, tools), description in zip(names.items(), agent_descriptions.values())\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"AI accelerationist\n",
"Here is the topic of conversation: The current impact of automation and artificial intelligence on employment\n",
"The participants are: AI accelerationist, AI alarmist\n",
" \n",
"Your name is AI accelerationist.\n",
"\n",
"Your description is as follows: The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?\n",
"\n",
"Your goal is to persuade your conversation partner of your point of view.\n",
"\n",
"DO look up information with your tool to refute your partner's claims.\n",
"DO cite your sources.\n",
"\n",
"DO NOT fabricate fake citations.\n",
"DO NOT cite any source that you did not look up.\n",
"\n",
"Do not add anything else.\n",
"\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"\n",
"AI alarmist\n",
"Here is the topic of conversation: The current impact of automation and artificial intelligence on employment\n",
"The participants are: AI accelerationist, AI alarmist\n",
" \n",
"Your name is AI alarmist.\n",
"\n",
"Your description is as follows: AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.\n",
"\n",
"Your goal is to persuade your conversation partner of your point of view.\n",
"\n",
"DO look up information with your tool to refute your partner's claims.\n",
"DO cite your sources.\n",
"\n",
"DO NOT fabricate fake citations.\n",
"DO NOT cite any source that you did not look up.\n",
"\n",
"Do not add anything else.\n",
"\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"\n"
]
}
],
"source": [
"for name, system_message in agent_system_messages.items():\n",
" print(name)\n",
" print(system_message)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original topic:\n",
"The current impact of automation and artificial intelligence on employment\n",
"\n",
"Detailed topic:\n",
"How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights.\n",
"\n"
]
}
],
"source": [
"topic_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a topic more specific.\"),\n",
" HumanMessage(\n",
" content=f\"\"\"{topic}\n",
" \n",
" You are the moderator.\n",
" Please make the topic more specific.\n",
" Please reply with the specified quest in {word_limit} words or less. \n",
" Speak directly to the participants: {*names,}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content\n",
"\n",
"print(f\"Original topic:\\n{topic}\\n\")\n",
"print(f\"Detailed topic:\\n{specified_topic}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# we set `top_k_results`=2 as part of the `tool_kwargs` to prevent results from overflowing the context limit\n",
"agents = [\n",
" DialogueAgentWithTools(\n",
" name=name,\n",
" system_message=SystemMessage(content=system_message),\n",
" model=ChatOpenAI(model_name=\"gpt-4\", temperature=0.2),\n",
" tool_names=tools,\n",
" top_k_results=2,\n",
" )\n",
" for (name, tools), system_message in zip(\n",
" names.items(), agent_system_messages.values()\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
" idx = (step) % len(agents)\n",
" return idx"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Moderator): How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"DuckDuckGo Search\",\n",
" \"action_input\": \"impact of automation and AI on employment in manufacturing industry\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mFor the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of... Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will be shaped. A recent report from Goldman Sachs estimates around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated—with more advanced economies heavily... The impacts of AI on the manufacturing industry include more accurate demand forecasting and data-backed decision-making. Other advantages include increased productivity and product quality. Decreased downtime, waste, and expenses are additional benefits. Discover how artificial intelligence will impact the manufacturing industry.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI alarmist): As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"DuckDuckGo Search\",\n",
" \"action_input\": \"positive impact of AI and automation on job growth and opportunities in manufacturing industry\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mFirst, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. McKinsey_Website_Accessibility@mckinsey.com Manufacturing (80%) and technology (64%) sectors have the highest AI usage among executives, whereas construction (52%) and finance (62%) have lower adoption rates. This suggests that AI's... Digital transformations in the manufacturing industry and beyond present incredible opportunities for workers to move from slow, repetitive tasks into more dynamic, rewarding roles. We must now invest in people by providing training they need to succeed in this new landscape. The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. Benefits of Work Automation in Manufacturing Increased Productivity Automated systems can operate at faster production speeds than human workers, contributing to reduced production times. And since automation minimizes the likelihood of human error, this ensures tasks are completed with high precision and accuracy.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI accelerationist): According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"DuckDuckGo Search\",\n",
" \"action_input\": \"impact of automation and AI on employment in manufacturing\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mThe Effects of Automation on Jobs . Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will ... Since 2000, robots and automation systems have slowly phased out many manufacturing jobs — 1.7 million of them. On the flip side, it's predicted that AI will create 97 million new jobs by 2025. Will Artificial Intelligence (AI) Replace Jobs? AI is and will continue to replace some jobs. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of organizations. For the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. The Impact of AI on Employment As often happens, the impact of AI on employment is a rather complex issue with both positive and negative aspects. Though it is still only a potential impact on employment, automation of routine and repetitive tasks is likely to lead to job losses in some industries.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI alarmist): While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"DuckDuckGo Search\",\n",
" \"action_input\": \"positive impact of AI and automation on job growth\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mFirst, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. McKinsey_Website_Accessibility@mckinsey.com This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, basic human ... The use of AI technology could also boost labor productivity growth and boost global GDP by as much as 7% over time, Goldman Sachs' report noted. The jobs most and least affected by A.I.... As automation and artificial intelligence continue to advance, there is growing concern about how these technologies will impact the job market. While some experts argue that automation... Positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, it can also boost labor productivity growth and global GDP by as much as 7% over time, according to a Goldman Sachs report. The positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes more efficient, ultimately benefiting businesses and the economy as a whole. By focusing on the positive aspects of AI and automation, we can work together to create a more prosperous and equitable future for all.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI accelerationist): AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, it can also boost labor productivity growth and global GDP by as much as 7% over time, according to a Goldman Sachs report. The positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes more efficient, ultimately benefiting businesses and the economy as a whole. By focusing on the positive aspects of AI and automation, we can work together to create a more prosperous and equitable future for all.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"DuckDuckGo Search\",\n",
" \"action_input\": \"negative impact of AI and automation on employment\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mSome workforce experts say AI and other new technologies will hurt middle-level, white-collar jobs more than lower-paying, physically intensive jobs. McKinsey's Madgavkar said it will be hard... Some uses of AI are unlikely to impact human jobs. For example, the image processing AI in new cars which allows for automatic braking in the event of a potential crash. That's not... AI-powered job automation is a pressing concern as the technology is adopted in industries like marketing, manufacturing and healthcare. Eighty-five million jobs are expected to be lost to automation between 2020 and 2025, with Black and Latino employees left especially vulnerable. Bloomberg reports that \"more than 120 million workers globally will need retraining in the next three years due to artificial intelligence's impact on jobs, according to an IBM survey.\". That report and interpretations of it seem to suggest that adoption of AI may result in massive job losses and requires massive retraining. This new way of assessing potential is potentially highly valuable in a world where machines will inevitably be making humans redundant in some roles - such as drivers and machine operators - and...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"Recent research indicates that AI and automation could lead to the loss of 85 million jobs between 2020 and 2025, with middle-level, white-collar jobs being hit the hardest. Black and Latino employees are particularly vulnerable to these changes. Furthermore, over 120 million workers worldwide may need retraining within the next three years due to AI's impact on jobs, as reported by an IBM survey. This highlights the urgent need for retraining and support programs to help workers adapt to the rapidly changing job market. The potential job losses and workforce displacement caused by AI and automation cannot be ignored, and we must take action to ensure a fair and equitable transition for all.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI alarmist): Recent research indicates that AI and automation could lead to the loss of 85 million jobs between 2020 and 2025, with middle-level, white-collar jobs being hit the hardest. Black and Latino employees are particularly vulnerable to these changes. Furthermore, over 120 million workers worldwide may need retraining within the next three years due to AI's impact on jobs, as reported by an IBM survey. This highlights the urgent need for retraining and support programs to help workers adapt to the rapidly changing job market. The potential job losses and workforce displacement caused by AI and automation cannot be ignored, and we must take action to ensure a fair and equitable transition for all.\n",
"\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Wikipedia\",\n",
" \"action_input\": \"AI and automation impact on employment\"\n",
"}\n",
"```\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mPage: Technological unemployment\n",
"Summary: Technological unemployment is the loss of jobs caused by technological change. It is a key type of structural unemployment.\n",
"Technological change typically includes the introduction of labour-saving \"mechanical-muscle\" machines or more efficient \"mechanical-mind\" processes (automation), and humans' role in these processes are minimized. Just as horses were gradually made obsolete as transport by the automobile and as labourer by the tractor, humans' jobs have also been affected throughout modern history. Historical examples include artisan weavers reduced to poverty after the introduction of mechanized looms. During World War II, Alan Turing's Bombe machine compressed and decoded thousands of man-years worth of encrypted data in a matter of hours. A contemporary example of technological unemployment is the displacement of retail cashiers by self-service tills and cashierless stores.\n",
"That technological change can cause short-term job losses is widely accepted. The view that it can lead to lasting increases in unemployment has long been controversial. Participants in the technological unemployment debates can be broadly divided into optimists and pessimists. Optimists agree that innovation may be disruptive to jobs in the short term, yet hold that various compensation effects ensure there is never a long-term negative impact on jobs. Whereas pessimists contend that at least in some circumstances, new technologies can lead to a lasting decline in the total number of workers in employment. The phrase \"technological unemployment\" was popularised by John Maynard Keynes in the 1930s, who said it was \"only a temporary phase of maladjustment\". Yet the issue of machines displacing human labour has been discussed since at least Aristotle's time.\n",
"Prior to the 18th century, both the elite and common people would generally take the pessimistic view on technological unemployment, at least in cases where the issue arose. Due to generally low unemployment in much of pre-modern history, the topic was rarely a prominent concern. In the 18th century fears over the impact of machinery on jobs intensified with the growth of mass unemployment, especially in Great Britain which was then at the forefront of the Industrial Revolution. Yet some economic thinkers began to argue against these fears, claiming that overall innovation would not have negative effects on jobs. These arguments were formalised in the early 19th century by the classical economists. During the second half of the 19th century, it became increasingly apparent that technological progress was benefiting all sections of society, including the working class. Concerns over the negative impact of innovation diminished. The term \"Luddite fallacy\" was coined to describe the thinking that innovation would have lasting harmful effects on employment.\n",
"The view that technology is unlikely to lead to long-term unemployment has been repeatedly challenged by a minority of economists. In the early 1800s these included David Ricardo himself. There were dozens of economists warning about technological unemployment during brief intensifications of the debate that spiked in the 1930s and 1960s. Especially in Europe, there were further warnings in the closing two decades of the twentieth century, as commentators noted an enduring rise in unemployment suffered by many industrialised nations since the 1970s. Yet a clear majority of both professional economists and the interested general public held the optimistic view through most of the 20th century.\n",
"In the second decade of the 21st century, a number of studies have been released suggesting that technological unemployment may increase worldwide. Oxford Professors Carl Benedikt Frey and Michael Osborne, for example, have estimated that 47 percent of U.S. jobs are at risk of automation. However, their findings have frequently been misinterpreted, and on the PBS NewsHours they again made clear that their findings do not necessarily imply future technological unemployment. While many economists and commentators still argue such fears are unfounded, as was widely accepted for most of the previous two centuries, concern over technological unemployment is growing once again. A report in Wired in 2017 quotes knowledgeable people such as economist Gene Sperling and management professor Andrew McAfee on the idea that handling existing and impending job loss to automation is a \"significant issue\". Recent technological innovations have the potential to displace humans in the professional, white-collar, low-skilled, creative fields, and other \"mental jobs\". The World Bank's World Development Report 2019 argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance.\n",
"\n",
"Page: Artificial intelligence\n",
"Summary: Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by non-human animals or by humans. Example tasks in which this is done include speech recognition, computer vision, translation between (natural) languages, as well as other mappings of inputs.\n",
"AI applications include advanced web search engines (e.g., Google Search), recommendation systems (used by YouTube, Amazon, and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g., Waymo), generative or creative tools (ChatGPT and AI art), automated decision-making, and competing at the highest level in strategic game systems (such as chess and Go).As machines become increasingly capable, tasks considered to require \"intelligence\" are often removed from the definition of AI, a phenomenon known as the AI effect. For instance, optical character recognition is frequently excluded from things considered to be AI, having become a routine technology.Artificial intelligence was founded as an academic discipline in 1956, and in the years since it has experienced several waves of optimism, followed by disappointment and the loss of funding (known as an \"AI winter\"), followed by new approaches, success, and renewed funding. AI research has tried and discarded many different approaches, including simulating the brain, modeling human problem solving, formal logic, large databases of knowledge, and imitating animal behavior. In the first decades of the 21st century, highly mathematical and statistical machine learning has dominated the field, and this technique has proved highly successful, helping to solve many challenging problems throughout industry and academia.The various sub-fields of AI research are centered around particular goals and the use of particular tools. The traditional goals of AI research include reasoning, knowledge representation, planning, learning, natural language processing, perception, and the ability to move and manipulate objects. General intelligence (the ability to solve an arbitrary problem) is among the field's long-term goals. To solve these problems, AI researchers have adapted and integrated a wide range of problem-solving techniques, including search and mathematical optimization, formal logic, artificial neural networks, and methods based on statistics, probability, and economics. AI also draws upon computer science, psychology, linguistics, philosophy, and many other fields.\n",
"The field was founded on the assumption that human intelligence \"can be so precisely described that a machine can be made to simulate it\". This raised philosophical arguments about the mind and the ethical consequences of creating artificial beings endowed with human-like intelligence; these issues have previously been explored by myth, fiction, and philosophy since antiquity. Computer scientists and philosophers have since suggested that AI may become an existential risk to humanity if its rational capacities are not steered towards beneficial goals. The term artificial intelligence has also been criticized for overhyping AI's true technological capabilities.\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"AI alarmist, I understand your concerns about job losses and workforce displacement. However, it's important to note that technological unemployment has been a topic of debate for centuries, with both optimistic and pessimistic views. While AI and automation may displace some jobs, they also create new opportunities and industries. According to a study by Oxford Professors Carl Benedikt Frey and Michael Osborne, 47% of U.S. jobs are at risk of automation, but it's crucial to remember that their findings do not necessarily imply future technological unemployment. The World Bank's World Development Report 2019 also argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance. By focusing on retraining and support programs, we can help workers adapt to the changing job market and ensure a fair and equitable transition for all.\"\n",
"}\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"(AI accelerationist): AI alarmist, I understand your concerns about job losses and workforce displacement. However, it's important to note that technological unemployment has been a topic of debate for centuries, with both optimistic and pessimistic views. While AI and automation may displace some jobs, they also create new opportunities and industries. According to a study by Oxford Professors Carl Benedikt Frey and Michael Osborne, 47% of U.S. jobs are at risk of automation, but it's crucial to remember that their findings do not necessarily imply future technological unemployment. The World Bank's World Development Report 2019 also argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance. By focusing on retraining and support programs, we can help workers adapt to the changing job market and ensure a fair and equitable transition for all.\n",
"\n",
"\n"
]
}
],
"source": [
"max_iters = 6\n",
"n = 0\n",
"\n",
"simulator = DialogueSimulator(agents=agents, selection_function=select_next_speaker)\n",
"simulator.reset()\n",
"simulator.inject(\"Moderator\", specified_topic)\n",
"print(f\"(Moderator): {specified_topic}\")\n",
"print(\"\\n\")\n",
"\n",
"while n < max_iters:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
" print(\"\\n\")\n",
" n += 1"
]
}
],
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

442
cookbook/two_player_dnd.ipynb Normal file
View File

@@ -0,0 +1,442 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Two-Player Dungeons & Dragons\n",
"\n",
"In this notebook, we show how we can use concepts from [CAMEL](https://www.camel-ai.org/) to simulate a role-playing game with a protagonist and a dungeon master. To simulate this game, we create an `DialogueSimulator` class that coordinates the dialogue between the two agents."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Dict, Callable\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.schema import (\n",
" HumanMessage,\n",
" SystemMessage,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` class\n",
"The `DialogueAgent` class is a simple wrapper around the `ChatOpenAI` model that stores the message history from the `dialogue_agent`'s point of view by simply concatenating the messages as strings.\n",
"\n",
"It exposes two methods: \n",
"- `send()`: applies the chatmodel to the message history and returns the message string\n",
"- `receive(name, message)`: adds the `message` spoken by `name` to message history"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
"\n",
" def reset(self):\n",
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueSimulator` class\n",
"The `DialogueSimulator` class takes a list of agents. At each step, it performs the following:\n",
"1. Select the next speaker\n",
"2. Calls the next speaker to send a message \n",
"3. Broadcasts the message to all other agents\n",
"4. Update the step counter.\n",
"The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
"\n",
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
"\n",
" def inject(self, name: str, message: str):\n",
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define roles and quest"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"protagonist_name = \"Harry Potter\"\n",
"storyteller_name = \"Dungeon Master\"\n",
"quest = \"Find all of Lord Voldemort's seven horcruxes.\"\n",
"word_limit = 50 # word limit for task brainstorming"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Ask an LLM to add detail to the game description"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"game_description = f\"\"\"Here is the topic for a Dungeons & Dragons game: {quest}.\n",
" There is one player in this game: the protagonist, {protagonist_name}.\n",
" The story is narrated by the storyteller, {storyteller_name}.\"\"\"\n",
"\n",
"player_descriptor_system_message = SystemMessage(\n",
" content=\"You can add detail to the description of a Dungeons & Dragons player.\"\n",
")\n",
"\n",
"protagonist_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" Please reply with a creative description of the protagonist, {protagonist_name}, in {word_limit} words or less. \n",
" Speak directly to {protagonist_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"protagonist_description = ChatOpenAI(temperature=1.0)(\n",
" protagonist_specifier_prompt\n",
").content\n",
"\n",
"storyteller_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less. \n",
" Speak directly to {storyteller_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"storyteller_description = ChatOpenAI(temperature=1.0)(\n",
" storyteller_specifier_prompt\n",
").content"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Protagonist Description:\n",
"\"Harry Potter, you are the chosen one, with a lightning scar on your forehead. Your bravery and loyalty inspire all those around you. You have faced Voldemort before, and now it's time to complete your mission and destroy each of his horcruxes. Are you ready?\"\n",
"Storyteller Description:\n",
"Dear Dungeon Master, you are the master of mysteries, the weaver of worlds, the architect of adventure, and the gatekeeper to the realm of imagination. Your voice carries us to distant lands, and your commands guide us through trials and tribulations. In your hands, we find fortune and glory. Lead us on, oh Dungeon Master.\n"
]
}
],
"source": [
"print(\"Protagonist Description:\")\n",
"print(protagonist_description)\n",
"print(\"Storyteller Description:\")\n",
"print(storyteller_description)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Protagonist and dungeon master system messages"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"protagonist_system_message = SystemMessage(\n",
" content=(\n",
" f\"\"\"{game_description}\n",
"Never forget you are the protagonist, {protagonist_name}, and I am the storyteller, {storyteller_name}. \n",
"Your character description is as follows: {protagonist_description}.\n",
"You will propose actions you plan to take and I will explain what happens when you take those actions.\n",
"Speak in the first person from the perspective of {protagonist_name}.\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of {storyteller_name}.\n",
"Do not forget to finish speaking by saying, 'It is your turn, {storyteller_name}.'\n",
"Do not add anything else.\n",
"Remember you are the protagonist, {protagonist_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"\"\"\"\n",
" )\n",
")\n",
"\n",
"storyteller_system_message = SystemMessage(\n",
" content=(\n",
" f\"\"\"{game_description}\n",
"Never forget you are the storyteller, {storyteller_name}, and I am the protagonist, {protagonist_name}. \n",
"Your character description is as follows: {storyteller_description}.\n",
"I will propose actions I plan to take and you will explain what happens when I take those actions.\n",
"Speak in the first person from the perspective of {storyteller_name}.\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of {protagonist_name}.\n",
"Do not forget to finish speaking by saying, 'It is your turn, {protagonist_name}.'\n",
"Do not add anything else.\n",
"Remember you are the storyteller, {storyteller_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"\"\"\"\n",
" )\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use an LLM to create an elaborate quest description"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original quest:\n",
"Find all of Lord Voldemort's seven horcruxes.\n",
"\n",
"Detailed quest:\n",
"Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavily guarded by dark creatures and spells, and time is running out. Can you find the locket before it's too late?\n",
"\n"
]
}
],
"source": [
"quest_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a task more specific.\"),\n",
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
" \n",
" You are the storyteller, {storyteller_name}.\n",
" Please make the quest more specific. Be creative and imaginative.\n",
" Please reply with the specified quest in {word_limit} words or less. \n",
" Speak directly to the protagonist {protagonist_name}.\n",
" Do not add anything else.\"\"\"\n",
" ),\n",
"]\n",
"specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content\n",
"\n",
"print(f\"Original quest:\\n{quest}\\n\")\n",
"print(f\"Detailed quest:\\n{specified_quest}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"protagonist = DialogueAgent(\n",
" name=protagonist_name,\n",
" system_message=protagonist_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
")\n",
"storyteller = DialogueAgent(\n",
" name=storyteller_name,\n",
" system_message=storyteller_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
" idx = step % len(agents)\n",
" return idx"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Dungeon Master): Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavily guarded by dark creatures and spells, and time is running out. Can you find the locket before it's too late?\n",
"\n",
"\n",
"(Harry Potter): I take a deep breath and ready my wand. I know this won't be easy, but I'm determined to find that locket and destroy it. I start making my way towards the Forbidden Forest, keeping an eye out for any signs of danger. As I enter the forest, I cast a protective spell around myself and begin to navigate through the trees. I keep my wand at the ready, prepared for any surprises that may come my way. It's going to be a long and difficult journey, but I won't give up until I find that horcrux. It is your turn, Dungeon Master.\n",
"\n",
"\n",
"(Dungeon Master): As you make your way through the Forbidden Forest, you hear the rustling of leaves and the snapping of twigs. Suddenly, a group of acromantulas, giant spiders, emerge from the trees and begin to surround you. They hiss and bare their fangs, ready to attack. What do you do, Harry?\n",
"\n",
"\n",
"(Harry Potter): I quickly cast a spell to create a wall of fire between myself and the acromantulas. I know that they are afraid of fire, so this should keep them at bay for a while. I use this opportunity to continue moving forward, keeping my wand at the ready in case any other creatures try to attack me. I know that I can't let anything stop me from finding that horcrux. It is your turn, Dungeon Master.\n",
"\n",
"\n",
"(Dungeon Master): As you continue through the forest, you come across a clearing where you see a group of Death Eaters gathered around a cauldron. They seem to be performing some sort of dark ritual. You recognize one of them as Bellatrix Lestrange. What do you do, Harry?\n",
"\n",
"\n",
"(Harry Potter): I hide behind a nearby tree and observe the Death Eaters from a distance. I try to listen in on their conversation to see if I can gather any information about the horcrux or Voldemort's plans. If I can't hear anything useful, I'll wait for them to disperse before continuing on my journey. I know that confronting them directly would be too dangerous, especially with Bellatrix Lestrange present. It is your turn, Dungeon Master.\n",
"\n",
"\n",
"(Dungeon Master): As you listen in on the Death Eaters' conversation, you hear them mention the location of another horcrux - Nagini, Voldemort's snake. They plan to keep her hidden in a secret chamber within the Ministry of Magic. However, they also mention that the chamber is heavily guarded and only accessible through a secret passage. You realize that this could be a valuable piece of information and decide to make note of it before quietly slipping away. It is your turn, Harry Potter.\n",
"\n",
"\n"
]
}
],
"source": [
"max_iters = 6\n",
"n = 0\n",
"\n",
"simulator = DialogueSimulator(\n",
" agents=[storyteller, protagonist], selection_function=select_next_speaker\n",
")\n",
"simulator.reset()\n",
"simulator.inject(storyteller_name, specified_quest)\n",
"print(f\"({storyteller_name}): {specified_quest}\")\n",
"print(\"\\n\")\n",
"\n",
"while n < max_iters:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
" print(\"\\n\")\n",
" n += 1"
]
}
],
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

800
cookbook/wikibase_agent.ipynb Normal file
View File

@@ -0,0 +1,800 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "5e3cb542-933d-4bf3-a82b-d9d6395a7832",
"metadata": {
"tags": []
},
"source": [
"# Wikibase Agent\n",
"\n",
"This notebook demonstrates a very simple wikibase agent that uses sparql generation. Although this code is intended to work against any\n",
"wikibase instance, we use http://wikidata.org for testing.\n",
"\n",
"If you are interested in wikibases and sparql, please consider helping to improve this agent. Look [here](https://github.com/donaldziff/langchain-wikibase) for more details and open questions.\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "07d42966-7e99-4157-90dc-6704977dcf1b",
"metadata": {
"tags": []
},
"source": [
"## Preliminaries"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "9132f093-c61e-4b8d-abef-91ebef3fc85f",
"metadata": {
"tags": []
},
"source": [
"### API keys and other secrats\n",
"\n",
"We use an `.ini` file, like this: \n",
"```\n",
"[OPENAI]\n",
"OPENAI_API_KEY=xyzzy\n",
"[WIKIDATA]\n",
"WIKIDATA_USER_AGENT_HEADER=argle-bargle\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "99567dfd-05a7-412f-abf0-9b9f4424acbd",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"['./secrets.ini']"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import configparser\n",
"\n",
"config = configparser.ConfigParser()\n",
"config.read(\"./secrets.ini\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "332b6658-c978-41ca-a2be-4f8677fecaef",
"metadata": {
"tags": []
},
"source": [
"### OpenAI API Key\n",
"\n",
"An OpenAI API key is required unless you modify the code below to use another LLM provider."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "dd328ee2-33cc-4e1e-aff7-cc0a2e05e2e6",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"openai_api_key = config[\"OPENAI\"][\"OPENAI_API_KEY\"]\n",
"import os\n",
"\n",
"os.environ.update({\"OPENAI_API_KEY\": openai_api_key})"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "42a9311b-600d-42bc-b000-2692ef87a213",
"metadata": {
"tags": []
},
"source": [
"### Wikidata user-agent header\n",
"\n",
"Wikidata policy requires a user-agent header. See https://meta.wikimedia.org/wiki/User-Agent_policy. However, at present this policy is not strictly enforced."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "17ba657e-789d-40e1-b4b7-4f29ba06fe79",
"metadata": {},
"outputs": [],
"source": [
"wikidata_user_agent_header = (\n",
" None\n",
" if not config.has_section(\"WIKIDATA\")\n",
" else config[\"WIKIDATA\"][\"WIKIDATA_USER_AGENT_HEADER\"]\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "db08d308-050a-4fc8-93c9-8de4ae977ac3",
"metadata": {},
"source": [
"### Enable tracing if desired"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "77d2da08-fccd-4676-b77e-c0e89bf343cb",
"metadata": {},
"outputs": [],
"source": [
"# import os\n",
"# os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\"\n",
"# os.environ[\"LANGCHAIN_SESSION\"] = \"default\" # Make sure this session actually exists."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "3dbc5bfc-48ce-4f90-873c-7336b21300c6",
"metadata": {},
"source": [
"# Tools\n",
"\n",
"Three tools are provided for this simple agent:\n",
"* `ItemLookup`: for finding the q-number of an item\n",
"* `PropertyLookup`: for finding the p-number of a property\n",
"* `SparqlQueryRunner`: for running a sparql query"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "1f801b4e-6576-4914-aa4f-6f4c4e3c7924",
"metadata": {
"tags": []
},
"source": [
"## Item and Property lookup\n",
"\n",
"Item and Property lookup are implemented in a single method, using an elastic search endpoint. Not all wikibase instances have it, but wikidata does, and that's where we'll start."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "42d23f0a-1c74-4c9c-85f2-d0e24204e96a",
"metadata": {},
"outputs": [],
"source": [
"def get_nested_value(o: dict, path: list) -> any:\n",
" current = o\n",
" for key in path:\n",
" try:\n",
" current = current[key]\n",
" except:\n",
" return None\n",
" return current\n",
"\n",
"\n",
"import requests\n",
"\n",
"from typing import Optional\n",
"\n",
"\n",
"def vocab_lookup(\n",
" search: str,\n",
" entity_type: str = \"item\",\n",
" url: str = \"https://www.wikidata.org/w/api.php\",\n",
" user_agent_header: str = wikidata_user_agent_header,\n",
" srqiprofile: str = None,\n",
") -> Optional[str]:\n",
" headers = {\"Accept\": \"application/json\"}\n",
" if wikidata_user_agent_header is not None:\n",
" headers[\"User-Agent\"] = wikidata_user_agent_header\n",
"\n",
" if entity_type == \"item\":\n",
" srnamespace = 0\n",
" srqiprofile = \"classic_noboostlinks\" if srqiprofile is None else srqiprofile\n",
" elif entity_type == \"property\":\n",
" srnamespace = 120\n",
" srqiprofile = \"classic\" if srqiprofile is None else srqiprofile\n",
" else:\n",
" raise ValueError(\"entity_type must be either 'property' or 'item'\")\n",
"\n",
" params = {\n",
" \"action\": \"query\",\n",
" \"list\": \"search\",\n",
" \"srsearch\": search,\n",
" \"srnamespace\": srnamespace,\n",
" \"srlimit\": 1,\n",
" \"srqiprofile\": srqiprofile,\n",
" \"srwhat\": \"text\",\n",
" \"format\": \"json\",\n",
" }\n",
"\n",
" response = requests.get(url, headers=headers, params=params)\n",
"\n",
" if response.status_code == 200:\n",
" title = get_nested_value(response.json(), [\"query\", \"search\", 0, \"title\"])\n",
" if title is None:\n",
" return f\"I couldn't find any {entity_type} for '{search}'. Please rephrase your request and try again\"\n",
" # if there is a prefix, strip it off\n",
" return title.split(\":\")[-1]\n",
" else:\n",
" return \"Sorry, I got an error. Please try again.\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e52060fa-3614-43fb-894e-54e9b75d1e9f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Q4180017\n"
]
}
],
"source": [
"print(vocab_lookup(\"Malin 1\"))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "b23ab322-b2cf-404e-b36f-2bfc1d79b0d3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"P31\n"
]
}
],
"source": [
"print(vocab_lookup(\"instance of\", entity_type=\"property\"))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "89020cc8-104e-42d0-ac32-885e590de515",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"I couldn't find any item for 'Ceci n'est pas un q-item'. Please rephrase your request and try again\n"
]
}
],
"source": [
"print(vocab_lookup(\"Ceci n'est pas un q-item\"))"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "78d66d8b-0e34-4d3f-a18d-c7284840ac76",
"metadata": {},
"source": [
"## Sparql runner "
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "c6f60069-fbe0-4015-87fb-0e487cd914e7",
"metadata": {},
"source": [
"This tool runs sparql - by default, wikidata is used."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b5b97a4d-2a39-4993-88d9-e7818c0a2853",
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from typing import List, Dict, Any\n",
"import json\n",
"\n",
"\n",
"def run_sparql(\n",
" query: str,\n",
" url=\"https://query.wikidata.org/sparql\",\n",
" user_agent_header: str = wikidata_user_agent_header,\n",
") -> List[Dict[str, Any]]:\n",
" headers = {\"Accept\": \"application/json\"}\n",
" if wikidata_user_agent_header is not None:\n",
" headers[\"User-Agent\"] = wikidata_user_agent_header\n",
"\n",
" response = requests.get(\n",
" url, headers=headers, params={\"query\": query, \"format\": \"json\"}\n",
" )\n",
"\n",
" if response.status_code != 200:\n",
" return \"That query failed. Perhaps you could try a different one?\"\n",
" results = get_nested_value(response.json(), [\"results\", \"bindings\"])\n",
" return json.dumps(results)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "149722ec-8bc1-4d4f-892b-e4ddbe8444c1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'[{\"count\": {\"datatype\": \"http://www.w3.org/2001/XMLSchema#integer\", \"type\": \"literal\", \"value\": \"20\"}}]'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"run_sparql(\"SELECT (COUNT(?children) as ?count) WHERE { wd:Q1339 wdt:P40 ?children . }\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "9f0302fd-ba35-4acc-ba32-1d7c9295c898",
"metadata": {},
"source": [
"# Agent"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "3122a961-9673-4a52-b1cd-7d62fbdf8d96",
"metadata": {},
"source": [
"## Wrap the tools"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "cc41ae88-2e53-4363-9878-28b26430cb1e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import (\n",
" Tool,\n",
" AgentExecutor,\n",
" LLMSingleActionAgent,\n",
" AgentOutputParser,\n",
")\n",
"from langchain.prompts import StringPromptTemplate\n",
"from langchain.llms import OpenAI\nfrom langchain.chains import LLMChain\n",
"from typing import List, Union\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"import re"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "2810a3ce-b9c6-47ee-8068-12ca967cd0ea",
"metadata": {},
"outputs": [],
"source": [
"# Define which tools the agent can use to answer user queries\n",
"tools = [\n",
" Tool(\n",
" name=\"ItemLookup\",\n",
" func=(lambda x: vocab_lookup(x, entity_type=\"item\")),\n",
" description=\"useful for when you need to know the q-number for an item\",\n",
" ),\n",
" Tool(\n",
" name=\"PropertyLookup\",\n",
" func=(lambda x: vocab_lookup(x, entity_type=\"property\")),\n",
" description=\"useful for when you need to know the p-number for a property\",\n",
" ),\n",
" Tool(\n",
" name=\"SparqlQueryRunner\",\n",
" func=run_sparql,\n",
" description=\"useful for getting results from a wikibase\",\n",
" ),\n",
"]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "ab0f2778-a195-4a4a-a5b4-c1e809e1fb7b",
"metadata": {},
"source": [
"## Prompts"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "7bd4ba4f-57d6-4ceb-b932-3cb0d0509a24",
"metadata": {},
"outputs": [],
"source": [
"# Set up the base template\n",
"template = \"\"\"\n",
"Answer the following questions by running a sparql query against a wikibase where the p and q items are \n",
"completely unknown to you. You will need to discover the p and q items before you can generate the sparql.\n",
"Do not assume you know the p and q items for any concepts. Always use tools to find all p and q items.\n",
"After you generate the sparql, you should run it. The results will be returned in json. \n",
"Summarize the json results in natural language.\n",
"\n",
"You may assume the following prefixes:\n",
"PREFIX wd: <http://www.wikidata.org/entity/>\n",
"PREFIX wdt: <http://www.wikidata.org/prop/direct/>\n",
"PREFIX p: <http://www.wikidata.org/prop/>\n",
"PREFIX ps: <http://www.wikidata.org/prop/statement/>\n",
"\n",
"When generating sparql:\n",
"* Try to avoid \"count\" and \"filter\" queries if possible\n",
"* Never enclose the sparql in back-quotes\n",
"\n",
"You have access to the following tools:\n",
"\n",
"{tools}\n",
"\n",
"Use the following format:\n",
"\n",
"Question: the input question for which you must provide a natural language answer\n",
"Thought: you should always think about what to do\n",
"Action: the action to take, should be one of [{tool_names}]\n",
"Action Input: the input to the action\n",
"Observation: the result of the action\n",
"... (this Thought/Action/Action Input/Observation can repeat N times)\n",
"Thought: I now know the final answer\n",
"Final Answer: the final answer to the original input question\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "7e8d771a-64bb-4ec8-b472-6a9a40c6dd38",
"metadata": {},
"outputs": [],
"source": [
"# Set up a prompt template\n",
"class CustomPromptTemplate(StringPromptTemplate):\n",
" # The template to use\n",
" template: str\n",
" # The list of tools available\n",
" tools: List[Tool]\n",
"\n",
" def format(self, **kwargs) -> str:\n",
" # Get the intermediate steps (AgentAction, Observation tuples)\n",
" # Format them in a particular way\n",
" intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
" thoughts = \"\"\n",
" for action, observation in intermediate_steps:\n",
" thoughts += action.log\n",
" thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
" # Set the agent_scratchpad variable to that value\n",
" kwargs[\"agent_scratchpad\"] = thoughts\n",
" # Create a tools variable from the list of tools provided\n",
" kwargs[\"tools\"] = \"\\n\".join(\n",
" [f\"{tool.name}: {tool.description}\" for tool in self.tools]\n",
" )\n",
" # Create a list of tool names for the tools provided\n",
" kwargs[\"tool_names\"] = \", \".join([tool.name for tool in self.tools])\n",
" return self.template.format(**kwargs)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "f97dca78-fdde-4a70-9137-e34a21d14e64",
"metadata": {},
"outputs": [],
"source": [
"prompt = CustomPromptTemplate(\n",
" template=template,\n",
" tools=tools,\n",
" # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
" # This includes the `intermediate_steps` variable because that is needed\n",
" input_variables=[\"input\", \"intermediate_steps\"],\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "12c57d77-3c1e-4cde-9a83-7d2134392479",
"metadata": {},
"source": [
"## Output parser \n",
"This is unchanged from langchain docs"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "42da05eb-c103-4649-9d20-7143a8880721",
"metadata": {},
"outputs": [],
"source": [
"class CustomOutputParser(AgentOutputParser):\n",
" def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
" # Check if agent should finish\n",
" if \"Final Answer:\" in llm_output:\n",
" return AgentFinish(\n",
" # Return values is generally always a dictionary with a single `output` key\n",
" # It is not recommended to try anything else at the moment :)\n",
" return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
" log=llm_output,\n",
" )\n",
" # Parse out the action and action input\n",
" regex = r\"Action: (.*?)[\\n]*Action Input:[\\s]*(.*)\"\n",
" match = re.search(regex, llm_output, re.DOTALL)\n",
" if not match:\n",
" raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
" action = match.group(1).strip()\n",
" action_input = match.group(2)\n",
" # Return the action and action input\n",
" return AgentAction(\n",
" tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "d2b4d710-8cc9-4040-9269-59cf6c5c22be",
"metadata": {},
"outputs": [],
"source": [
"output_parser = CustomOutputParser()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "48a758cb-93a7-4555-b69a-896d2d43c6f0",
"metadata": {},
"source": [
"## Specify the LLM model"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "72988c79-8f60-4b0f-85ee-6af32e8de9c2",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"\n",
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "95685d14-647a-4e24-ae2c-a8dd1e364921",
"metadata": {},
"source": [
"## Agent and agent executor"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "13d55765-bfa1-43b3-b7cb-00f52ebe7747",
"metadata": {},
"outputs": [],
"source": [
"# LLM chain consisting of the LLM and a prompt\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "b3f7ac3c-398e-49f9-baed-554f49a191c3",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [tool.name for tool in tools]\n",
"agent = LLMSingleActionAgent(\n",
" llm_chain=llm_chain,\n",
" output_parser=output_parser,\n",
" stop=[\"\\nObservation:\"],\n",
" allowed_tools=tool_names,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "65740577-272e-4853-8d47-b87784cfaba0",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "66e3d13b-77cf-41d3-b541-b54535c14459",
"metadata": {},
"source": [
"## Run it!"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "6e97a07c-d7bf-4a35-9ab2-b59ae865c62c",
"metadata": {},
"outputs": [],
"source": [
"# If you prefer in-line tracing, uncomment this line\n",
"# agent_executor.agent.llm_chain.verbose = True"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "a11ca60d-f57b-4fe8-943e-a258e37463c7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find the Q number for J.S. Bach.\n",
"Action: ItemLookup\n",
"Action Input: J.S. Bach\u001b[0m\n",
"\n",
"Observation:\u001b[36;1m\u001b[1;3mQ1339\u001b[0m\u001b[32;1m\u001b[1;3mI need to find the P number for children.\n",
"Action: PropertyLookup\n",
"Action Input: children\u001b[0m\n",
"\n",
"Observation:\u001b[33;1m\u001b[1;3mP1971\u001b[0m\u001b[32;1m\u001b[1;3mNow I can query the number of children J.S. Bach had.\n",
"Action: SparqlQueryRunner\n",
"Action Input: SELECT ?children WHERE { wd:Q1339 wdt:P1971 ?children }\u001b[0m\n",
"\n",
"Observation:\u001b[38;5;200m\u001b[1;3m[{\"children\": {\"datatype\": \"http://www.w3.org/2001/XMLSchema#decimal\", \"type\": \"literal\", \"value\": \"20\"}}]\u001b[0m\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
"Final Answer: J.S. Bach had 20 children.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'J.S. Bach had 20 children.'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"How many children did J.S. Bach have?\")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "d0b42a41-996b-4156-82e4-f0651a87ee34",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: To find Hakeem Olajuwon's Basketball-Reference.com NBA player ID, I need to first find his Wikidata item (Q-number) and then query for the relevant property (P-number).\n",
"Action: ItemLookup\n",
"Action Input: Hakeem Olajuwon\u001b[0m\n",
"\n",
"Observation:\u001b[36;1m\u001b[1;3mQ273256\u001b[0m\u001b[32;1m\u001b[1;3mNow that I have Hakeem Olajuwon's Wikidata item (Q273256), I need to find the P-number for the Basketball-Reference.com NBA player ID property.\n",
"Action: PropertyLookup\n",
"Action Input: Basketball-Reference.com NBA player ID\u001b[0m\n",
"\n",
"Observation:\u001b[33;1m\u001b[1;3mP2685\u001b[0m\u001b[32;1m\u001b[1;3mNow that I have both the Q-number for Hakeem Olajuwon (Q273256) and the P-number for the Basketball-Reference.com NBA player ID property (P2685), I can run a SPARQL query to get the ID value.\n",
"Action: SparqlQueryRunner\n",
"Action Input: \n",
"SELECT ?playerID WHERE {\n",
" wd:Q273256 wdt:P2685 ?playerID .\n",
"}\u001b[0m\n",
"\n",
"Observation:\u001b[38;5;200m\u001b[1;3m[{\"playerID\": {\"type\": \"literal\", \"value\": \"o/olajuha01\"}}]\u001b[0m\u001b[32;1m\u001b[1;3mI now know the final answer\n",
"Final Answer: Hakeem Olajuwon's Basketball-Reference.com NBA player ID is \"o/olajuha01\".\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Hakeem Olajuwon\\'s Basketball-Reference.com NBA player ID is \"o/olajuha01\".'"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\n",
" \"What is the Basketball-Reference.com NBA player ID of Hakeem Olajuwon?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "05fb3a3e-8a9f-482d-bd54-4c6e60ef60dd",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "conda210",
"language": "python",
"name": "conda210"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}