Spaces:
Running
Running
| import streamlit as st | |
| from PyPDF2 import PdfReader | |
| from langchain_text_splitters import RecursiveCharacterTextSplitter | |
| import os | |
| from langchain_google_genai import GoogleGenerativeAIEmbeddings | |
| from langchain_community.vectorstores import Chroma | |
| from langchain_google_genai import ChatGoogleGenerativeAI | |
| from langchain.chains.question_answering import load_qa_chain | |
| from langchain.prompts import PromptTemplate | |
| st.set_page_config(page_title="PDF CHATBOT", layout="wide") | |
| st.markdown(""" | |
| ## Document Genie: Get instant insights from your Documents | |
| This chatbot is built using the Retrieval-Augmented Generation (RAG) framework, leveraging Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by breaking them down into manageable chunks, creates a searchable vector store, and generates accurate answers to user queries. This advanced approach ensures high-quality, contextually relevant responses for an efficient and effective user experience. | |
| ### How It Works | |
| Follow these simple steps to interact with the chatbot: | |
| 1. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights. | |
| 2. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer. | |
| """) | |
| def get_pdf(pdf_docs): | |
| text = "" | |
| for pdf in pdf_docs: | |
| pdf_reader = PdfReader(pdf) | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| return text | |
| GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY") | |
| def response_generate(text,query): | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| # Set a really small chunk size, just to show. | |
| chunk_size=500, | |
| chunk_overlap=20, | |
| separators=["\n\n","\n"," ",".",","]) | |
| chunks=text_splitter.split_text(text) | |
| embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001") | |
| db = Chroma.from_documents(chunks, embeddings) | |
| # Create retriever interface | |
| retriever = db.as_retriever() | |
| qa = RetrievalQA.from_chain_type(llm = GoogleGenerativeAI(model="gemini-pro", google_api_key=GOOGLE_API_KEY ), chain_type='stuff', retriever=retriever) | |
| return qa.run(query_text) | |
| def main(): | |
| st.header("Chat with your pdf💁") | |
| query = st.text_input("Ask a Question from the PDF Files", key="query") | |
| #if query: | |
| # user_call(query) | |
| st.title("Menu:") | |
| pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True, key="pdf_uploader") | |
| if st.button("Submit & Process", key="process_button"): | |
| with st.spinner("Processing..."): | |
| raw_text = get_pdf(pdf_docs) | |
| #text_chunks = text_splitter(raw_text) | |
| response = response_generate(raw_text,query) | |
| st.success("Done") | |
| st.write("Reply: ", response) | |
| if __name__ == "__main__": | |
| main() |