document_analyzer.py

import os
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
from langchain.chains.question_answering import load_qa_chain
from langchain_community.llms import HuggingFaceHub
import config

def analyze_pdf(file_path):
    """
    Analyzes a PDF file and returns a question-answering chain.

    Args:
        file_path: The path to the PDF file.

    Returns:
        A Langchain QA chain object.
    """
    try:
        pdf_reader = PdfReader(file_path)
        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()

        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000,
            chunk_overlap=200,
            length_function=len
        )
        chunks = text_splitter.split_text(text=text)

        embeddings = HuggingFaceEmbeddings(model_name=config.EMBEDDING_MODEL_NAME)
        vector_store = FAISS.from_texts(chunks, embedding=embeddings)

        llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
        chain = load_qa_chain(llm=llm, chain_type="stuff")

        return chain, vector_store

    except Exception as e:
        print(f"Error analyzing PDF: {e}")
        return None, None

def query_pdf(chain, vector_store, query):
    """
    Queries the PDF using the QA chain.

    Args:
        chain: The Langchain QA chain object.
        vector_store: The FAISS vector store.
        query: The question to ask the PDF.

    Returns:
        The answer to the query.
    """
    try:
        docs = vector_store.similarity_search(query=query, k=3)
        answer = chain.run(input_documents=docs, question=query)
        return answer
    except Exception as e:
        print(f"Error querying PDF: {e}")
        return "Sorry, I couldn't find an answer to your question in the PDF."

import pandas as pd
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
from langchain_community.llms import HuggingFaceHub

def analyze_spreadsheet(file_path):
    """
    Analyzes a spreadsheet file and returns a question-answering agent.

    Args:
        file_path: The path to the spreadsheet file.

    Returns:
        A Langchain agent object.
    """
    try:
        df = pd.read_csv(file_path)
        llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
        agent = create_pandas_dataframe_agent(llm, df, verbose=True)
        return agent
    except Exception as e:
        print(f"Error analyzing spreadsheet: {e}")
        return None

def query_spreadsheet(agent, query):
    """
    Queries the spreadsheet using the agent.

    Args:
        agent: The Langchain agent object.
        query: The question to ask the spreadsheet.

    Returns:
        The answer to the query.
    """
    try:
        answer = agent.run(query)
        return answer
    except Exception as e:
        print(f"Error querying spreadsheet: {e}")
        return "Sorry, I couldn't find an answer to your question in the spreadsheet."