| import streamlit as st |
| from pypdf import PdfReader |
| from langchain.text_splitter import RecursiveCharacterTextSplitter |
| from langchain_google_genai import GoogleGenerativeAIEmbeddings |
| from langchain_community.vectorstores import FAISS |
| from langchain_google_genai import ChatGoogleGenerativeAI |
| from langchain.chains.question_answering import load_qa_chain |
| import google.generativeai as genai |
|
|
| |
| api_key = st.secrets["GOOGLE_API_KEY"] |
| genai.configure(api_key=api_key) |
|
|
| |
| st.set_page_config(page_title="PDF RAG Chatbot") |
|
|
| st.header("📄 Chat with PDF using Gemini AI") |
|
|
| |
| def get_pdf_text(pdf_docs): |
| text = "" |
|
|
| for pdf in pdf_docs: |
| pdf_reader = PdfReader(pdf) |
|
|
| for page in pdf_reader.pages: |
| extracted = page.extract_text() |
| if extracted: |
| text += extracted |
|
|
| return text |
|
|
| |
| def get_text_chunks(text): |
| text_splitter = RecursiveCharacterTextSplitter( |
| chunk_size=1000, |
| chunk_overlap=200 |
| ) |
|
|
| chunks = text_splitter.split_text(text) |
|
|
| return chunks |
|
|
| |
| def get_vector_store(text_chunks): |
| embeddings = GoogleGenerativeAIEmbeddings( |
| model="models/embedding-001", |
| google_api_key=api_key |
| ) |
|
|
| vector_store = FAISS.from_texts( |
| text_chunks, |
| embedding=embeddings |
| ) |
|
|
| vector_store.save_local("faiss_index") |
|
|
| |
| def get_conversational_chain(): |
|
|
| model = ChatGoogleGenerativeAI( |
| model="gemini-1.5-flash", |
| temperature=0.3, |
| google_api_key=api_key |
| ) |
|
|
| chain = load_qa_chain( |
| model, |
| chain_type="stuff" |
| ) |
|
|
| return chain |
|
|
| |
| def user_input(user_question): |
|
|
| embeddings = GoogleGenerativeAIEmbeddings( |
| model="models/embedding-001", |
| google_api_key=api_key |
| ) |
|
|
| 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 |
| ) |
|
|
| st.subheader("🤖 Answer") |
| st.write(response["output_text"]) |
|
|
| |
| with st.sidebar: |
| st.title("📚 Upload Your PDF Files") |
|
|
| pdf_docs = st.file_uploader( |
| "Upload PDF Files", |
| accept_multiple_files=True |
| ) |
|
|
| if st.button("Submit & Process"): |
|
|
| with st.spinner("Processing PDFs..."): |
|
|
| raw_text = get_pdf_text(pdf_docs) |
|
|
| text_chunks = get_text_chunks(raw_text) |
|
|
| get_vector_store(text_chunks) |
|
|
| st.success("PDF Processing Complete!") |
|
|
| |
| user_question = st.text_input( |
| "Ask a Question from the Uploaded PDF Files" |
| ) |
|
|
| if user_question: |
| user_input(user_question) |
|
|
