文档比较

本笔记本展示了如何使用代理来比较两个文档。

高级思路是我们将为每个文档创建一个问答链，并使用该链来回答一系列问题。然后，我们可以使用这些问题的回答来比较这两个文档。

from pydantic import BaseModel, Field

from langchain.chat_models import ChatOpenAI
from langchain.agents import Tool
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.document_loaders import PyPDFLoader
from langchain.chains import RetrievalQA

/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 (3.6.4) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.
  warnings.warn(

class DocumentInput(BaseModel):
    question: str = Field()


llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")

tools = []
files = [
    # https://abc.xyz/investor/static/pdf/2023Q1_alphabet_earnings_release.pdf
    {
        "name": "alphabet-earnings", 
        "path": "/Users/harrisonchase/Downloads/2023Q1_alphabet_earnings_release.pdf",
    }, 
    # https://digitalassets.tesla.com/tesla-contents/image/upload/IR/TSLA-Q1-2023-Update
    {
        "name": "tesla-earnings", 
        "path": "/Users/harrisonchase/Downloads/TSLA-Q1-2023-Update.pdf"
    }
]

for file in files:
    loader = PyPDFLoader(file["path"])
    pages = loader.load_and_split()
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
    docs = text_splitter.split_documents(pages)
    embeddings = OpenAIEmbeddings()
    retriever = FAISS.from_documents(docs, embeddings).as_retriever()
    
    # Wrap retrievers in a Tool
    tools.append(
        Tool(
            args_schema=DocumentInput,
            name=file["name"], 
            description=f"useful when you want to answer questions about {file['name']}",
            func=RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
        )
    )

from langchain.agents import initialize_agent
from langchain.agents import AgentType

llm = ChatOpenAI(
    temperature=0,
    model="gpt-3.5-turbo-0613", 
)

agent = initialize_agent(
    agent=AgentType.OPENAI_FUNCTIONS,
    tools=tools,
    llm=llm,
    verbose=True,
)

agent({"input": "did alphabet or tesla have more revenue?"})

> Entering new  chain...

Invoking: `alphabet-earnings` with `{'question': 'revenue'}`


{'query': 'revenue', 'result': 'The revenue for Alphabet Inc. in the first quarter of 2023 was $69,787 million.'}
Invoking: `tesla-earnings` with `{'question': 'revenue'}`


{'query': 'revenue', 'result': 'Total revenue for Q1-2023 was $23.3 billion.'}Alphabet Inc. had more revenue than Tesla. In the first quarter of 2023, Alphabet Inc. had a revenue of $69,787 million, while Tesla had a revenue of $23.3 billion.

> Finished chain.





{'input': 'did alphabet or tesla have more revenue?',
 'output': 'Alphabet Inc. had more revenue than Tesla. In the first quarter of 2023, Alphabet Inc. had a revenue of $69,787 million, while Tesla had a revenue of $23.3 billion.'}