Spaces:
Sleeping
Sleeping
| 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_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 | |
| from pdf2image import convert_from_bytes | |
| from PIL import Image | |
| import pytesseract | |
| import io | |
| load_dotenv() | |
| os.getenv("GOOGLE_API_KEY") | |
| genai.configure(api_key=os.getenv("GOOGLE_API_KEY")) | |
| def get_pdf_text(pdf_docs): | |
| text = "" | |
| for uploaded_file in pdf_docs: | |
| if uploaded_file.name.endswith(".pdf"): | |
| # Process actual PDF files | |
| pdf_reader = PdfReader(uploaded_file) | |
| for page in pdf_reader.pages: | |
| page_text = page.extract_text() | |
| if page_text: | |
| text += page_text | |
| # If no text extracted, try OCR | |
| if not text.strip(): | |
| images = convert_from_bytes(uploaded_file.read()) | |
| for img in images: | |
| text += pytesseract.image_to_string(img) | |
| else: | |
| # Process image files | |
| image = Image.open(uploaded_file) | |
| text += pytesseract.image_to_string(image) | |
| 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): | |
| if not text_chunks: | |
| raise ValueError("No text chunks generated from PDF. Please check the uploaded file.") | |
| 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=0.7) | |
| 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 = 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"]) | |
| def main(): | |
| st.set_page_config("Chat PDF") | |
| st.header("Chat with PDF using Gemini💁") | |
| 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 your PDF Files and Click on the Submit & Process Button", 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() |