import streamlit as st from PyPDF2 import PdfReader from langchain.text_splitter import RecursiveCharacterTextSplitter 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 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=1000, chunk_overlap=1000) chunks = text_splitter.split_text(text) return chunks def get_vector_stores(text_chunks, api_key): embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", api_key=api_key) vector_store = FAISS.from_texts(text_chunks, embedding=embeddings) vector_store.save_local("faiss_index") def conversation_chain(api_key): prompt_template = """ Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, just say, "answer is not available in the context", don't provide the wrong answer or give answers by yourself.\n\n Context:\n{context}\n Question:\n{question}\n Answer: """ model = ChatGoogleGenerativeAI(model="gemini-pro", api_key=api_key, temperature=0.3) prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question']) chain = load_qa_chain(model, chain_type="stuff", prompt=prompt) return chain def user_input(user_q, api_key): embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", api_key=api_key) new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True) docs = new_db.similarity_search(user_q) chain = conversation_chain(api_key) response = chain({"input_documents": docs, "question": user_q}, return_only_outputs=True) st.write("Reply ->", response["output_text"]) def main(): st.set_page_config("Chat PDF") st.header("Chat with PDF using Gemini 💁") # Ask for API key input api_key = st.text_input("Enter your Gemini API Key", type="password") if api_key: # Configure the API genai.configure(api_key=api_key) # Input for user questions user_question = st.text_input("Ask a Question from the PDF Files") if user_question: user_input(user_question, api_key) with st.sidebar: st.title("Menu:") pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True) if st.button("Submit and Process"): with st.spinner("Processing..."): raw_text = get_pdf_text(pdf_docs) text_chunks = get_text_chunks(raw_text) get_vector_stores(text_chunks, api_key) st.success("Done") else: st.warning("Please enter your Gemini API key to proceed.") if __name__ == "__main__": main()