pdf_bot.py

import os
from dotenv import load_dotenv
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain_community.llms import ChatGroq

load_dotenv()
groq_api_key = os.getenv("GROQ_API_KEY")

# Load PDF and prepare QA chain
def create_qa_chain_from_pdf(pdf_path):
    loader = PyPDFLoader(pdf_path)
    documents = loader.load()
    
    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    texts = splitter.split_documents(documents)
    
    embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-m3")
    vectorstore = FAISS.from_documents(texts, embeddings)

    llm = ChatGroq(
        model="llama3-8b-8192",
        temperature=0.3,
        api_key=groq_api_key,
    )

    qa_chain = RetrievalQA.from_chain_type(
        llm=llm,
        chain_type="stuff",
        retriever=vectorstore.as_retriever(search_kwargs={"k": 1}),
        return_source_documents=True
    )
    return qa_chain