Querying PDFs using RAG

I am trying to create a streamlit app where I can query multiple PDFs using RAG and Google Gemini and I am getting various errors after making multiple changes to my code. I just want to know what is wrong and how can I rectify my errors :sweat_smile:

Here’s my entire code:

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai
from langchain.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration, RagSequenceForGeneration
import torch
from transformers import pipeline
from datasets import load_dataset

load_dotenv()
os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))

def get_pdf_text(pdf_docs):
    text=""
    for pdf in pdf_docs:
        pdf_reader= PdfReader(pdf)
        for page in pdf_reader.pages:
            text+= page.extract_text()
    return  text

def get_text_chunks(text):
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks


def get_vector_store(text_chunks):
    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")


def get_conversational_chain():

    prompt_template = """
    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
    Context:\n {context}?\n
    Question: \n{question}\n

    Answer:
    """

    model = ChatGoogleGenerativeAI(model="gemini-pro",
                             temperature=0.3)

    prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])
    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)

    return chain

tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-base")
retriever = RagRetriever.from_pretrained("facebook/rag-token-base")
generator = RagSequenceForGeneration.from_pretrained("facebook/rag-token-base")

def get_rag_answer(question, context):
    #Encode question and context
    input_dict = tokenizer(question, context, return_tensors="pt")
    input_ids = input_dict["input_ids"]
    attention_mask = input_dict["attention_mask"]

    #Retrieve relevant documents
    doc_scores, doc_ids = retriever(input_ids, attention_mask)

    #Generate answers
    generated = generator.generate(
        input_ids = input_ids,
        attention_mask = attention_mask,
        doc_scores = doc_scores,
        num_beams = 4,
        max_length = 100,
        early_stopping = True
    )

    #Decode the generated answer
    answer = tokenizer.decode(generated[0], skip_special_tokens = True)
    return answer

def user_input(user_question):
    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")

    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization = True)
    docs = new_db.similarity_search(user_question)
    chain = get_conversational_chain()

    response = chain(
        {"input_documents": docs, "question": user_question},
        return_only_outputs = True
    )
    print(response)
    st.write("Reply: ", response["output_text"])

    #Get RAG answer
    rag_answer = get_rag_answer(user_question, response["output_text"])
    st.write("RAG Answer: ", rag_answer)

def main():
    st.set_page_config("PDF Alchemist")
    st.header("PDF Alchemist: Obtain information from your PDF..")

    user_question = st.text_input("Ask a Question from the PDFs")

    if user_question:
        user_input(user_question)

    with st.sidebar:
        st.title("Menu:")
        pdf_docs = st.file_uploader("Upload your PDFs and Click on the Submit Button", accept_multiple_files=True)
        if st.button("SUBMIT"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                get_vector_store(text_chunks)
                st.success("Done")

if __name__ == "__main__":
    main()

Also my requirements.txt file contains:
streamlit
google-generativeai
python-dotenv
langchain
PyPDF2
faiss-cpu
langchain_google_genai
transformers
datasets
torch
torchvision
torchaudio

Hello @LLMLover , can you please share the errors so I can specifically look into that portion of code and guide you .

Thanks

This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.