import streamlit as st from PyPDF2 import PdfReader from langchain.text_splitter import RecursiveCharacterTextSplitter import os import io from langchain_huggingface import HuggingFaceEmbeddings import google.generativeai as genai from langchain_community.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 # load the environment variables load_dotenv() # configure api key genai.configure(api_key=os.getenv("GOOGLE_API_KEY")) # function to extract text from pdfs def get_pdf_text(pdf_docs): text="" for pdf in pdf_docs: pdf_reader = PdfReader(io.BytesIO(pdf.read())) for page in pdf_reader.pages: text+=page.extract_text() return text # function to convert text to chunks def get_text_chunks(text): text_splitter=RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000) chunks=text_splitter.split_text(text) return chunks # function to create vector embedding def get_vector_store(text_chunks): embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") 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 the provided context just say, "answer is not available in the context", don't provide any 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 def user_input(user_question): embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") 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"]) st.write(response["output_text"]) def main(): st.set_page_config("Chat With Multiple PDF") #st.header("Chat with Multiple PDF using Gemini") # App name st.markdown("
ChatPDF
", unsafe_allow_html=True) user_question = st.text_input("Ask a Question from the PDF Files") if user_question: user_input(user_question) with st.sidebar: #st.title("Menu:") pdf_docs = st.file_uploader("Upload PDFs and Click on Submit & Process", accept_multiple_files=True) if st.button("Submit & Process"): 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()