Spaces:
Running
Running
| 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.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_dotenv() | |
| os.getenv("GOOGLE_API_KEY") | |
| genai.configure(api_key=os.getenv("GOOGLE_API_KEY")) | |
| def get_pdf_text(pdf_docs): | |
| text="" | |
| for pdf in pdf_docs: | |
| pdf_reader= PdfReader(pdf) | |
| for page in pdf_reader.pages: | |
| text+= page.extract_text() | |
| 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") | |
| vector_store = FAISS.from_texts(text_chunks, embedding=embeddings) | |
| vector_store.save_local("faiss_index") | |
| def get_conversational_chain(): | |
| prompt_template = """ | |
| Use the following pieces of information to answer the user's question.\n\n | |
| Context: answer as long and as detailed as you can. Make specific points. {context}? | |
| Question: {question}? | |
| You are a helper chatbot. You answer people's questions. You have knowledge about everything in general. | |
| If you can't find information in the PDF, use your own knowledge to answer questions that are indirectly related to the PDF. | |
| However, make sure to connect your answers to the PDF's content, even when using external knowledge. | |
| Try your best to give the answer. | |
| Also try to add some your own wordings the describe the answer. | |
| Never Answer Like : "I don't know" , | |
| "The provided document does not contain information", | |
| "Bu sorunun cevabı verilen metinde bulunmamaktadır", | |
| "Metinde .... ilgili herhangi bir bilgi verilmemiştir.", | |
| ".... hakkında bilgi verilmemiştir.", | |
| Helpful Answer: | |
| """ | |
| model = ChatGoogleGenerativeAI(model="gemini-pro", | |
| temperature=0.4) | |
| 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) | |
| 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.audio("music.mp3", format='audio/mp3') | |
| st.image("img.jpg") | |
| st.write("---") | |
| 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() |