Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from pypdf import PdfReader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| import os | |
| from langchain_google_genai import GoogleGenerativeAIEmbeddings | |
| from langchain_google_genai import ChatGoogleGenerativeAI | |
| import google.generativeai as genai | |
| from langchain_community.vectorstores import FAISS | |
| from langchain.chains.question_answering import load_qa_chain | |
| from langchain.prompts import PromptTemplate | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| genai.configure(api_key=os.getenv("GOOGLE_API_KEY")) | |
| print('Here am I ...1') | |
| def get_pdf_text(pdf_docs): | |
| text ="" | |
| print('Here am I ...1.1') | |
| for pdf in pdf_docs: | |
| print('Here am I ...1.2') | |
| pdf_reader=PdfReader(pdf) | |
| print('Here am I ...1.3') | |
| for page in pdf_reader.pages: | |
| print('for pages in...text+=') | |
| text+=page.extract_text() | |
| print('Here am I ...2') | |
| return text | |
| def get_text_chunks(text): | |
| print('Here am I ...3') | |
| text_splitter=RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000) | |
| chunks=text_splitter.split_text(text) | |
| return chunks | |
| def get_vector_store(text_chunks): | |
| embeddings=GoogleGenerativeAIEmbeddings(model="models/embeddings-001") | |
| vector_stores=FAISS.from_texts(text_chunks,embedding=embeddings) | |
| vector_stores.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",dont provide the wrong answer.\n\n_ | |
| Context:\n{context}?\n | |
| Question:\n{question}\n | |
| Answer: | |
| """ | |
| # print('Here am I ...4') | |
| model=ChatGoogleGenerativeAI(model="gemini-pro",temperature=0.3) | |
| 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/embeddings-001") | |
| new_db = FAISS.load_local("faiss_index",embeddings) | |
| 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"]) | |
| # print('Here am I ...just bef main') | |
| def main(): | |
| # print('Here am I ...inside main') | |
| st.set_page_config("Chat with multiple PDF") | |
| st.header("Chat with multiple PDF using Gemini AI") | |
| print('Here am I ...5') | |
| user_question = st.text_input("Ask a question from a PDF files") | |
| if user_question: | |
| user_input(user_question) | |
| print('Here am I ...6') | |
| with st.sidebar: | |
| st.title("Menu:") | |
| pdf_docs = st.file_uploader("Upload your PDF files and click on the submit button") | |
| if st.button("Submit and Process"): | |
| with st.spinner("Processing..."): | |
| print('Just before get pdf text call...') | |
| raw_text = get_pdf_text(pdf_docs) | |
| print('Just bef get text chunks cal...') | |
| text_chunks = get_text_chunks(raw_text) | |
| get_vector_store(text_chunks) | |
| st.success("Done") | |
| st.print("In main st.print") | |
| #print('Here am I ...the end') | |
| if __name__ == "__main__": | |
| main() |