Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from PyPDF2 import PdfReader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| import os | |
| 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 | |
| from langchain_openai import OpenAI, ChatOpenAI | |
| from langchain_openai import OpenAIEmbeddings | |
| load_dotenv() | |
| os.environ["OPENAI_API_KEY"] = st.secrets["OPENAI_API_KEY"] | |
| os.environ["LANGCHAIN_TRACING_V2"]="true" | |
| os.environ["LANGCHAIN_API_KEY"] = st.secrets["LANGCHAIN_API_KEY"] | |
| def get_pdf_text(pdf_docs): | |
| text = "" | |
| for pdf in pdf_docs: | |
| pdf_reader = PdfReader(pdf) | |
| for page in pdf_reader.pages: | |
| try: | |
| page_text = page.extract_text() | |
| if page_text: | |
| text += page_text | |
| except Exception as e: | |
| print(f"Error reading page: {e}") | |
| return text | |
| def get_text_chunks(text): | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=2500, chunk_overlap=750) | |
| chunks = text_splitter.split_text(text) | |
| return chunks | |
| def get_vector_store(text_chunks): | |
| vector_store = FAISS.from_texts(text_chunks, OpenAIEmbeddings()) | |
| vector_store.save_local("faiss_index") | |
| def get_conversational_chain(): | |
| prompt_template = """You are an assistant for teachers. Your objective is to provide | |
| comprehensive and accurate responses based on the context provided. Make sure that | |
| you generate whole output. | |
| context: {context} | |
| question: {question} | |
| """ | |
| model = ChatOpenAI(model="gpt-3.5-turbo") | |
| 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 = OpenAIEmbeddings() | |
| new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True) | |
| docs = new_db.similarity_search(user_question) | |
| chain = get_conversational_chain() | |
| result = "" | |
| with st.spinner("Processing..."): | |
| response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True) | |
| result = response["output_text"] | |
| st.session_state.chat_history.append({"role": "assistant", "content": result}) | |
| def main(): | |
| st.set_page_config("Chat PDF") | |
| st.header("AI-powered EduPlanner💁") | |
| if "chat_history" not in st.session_state: | |
| st.session_state.chat_history = [] | |
| with st.sidebar: | |
| #st.image("pic123.png") | |
| 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"): | |
| if pdf_docs: | |
| 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") | |
| else: | |
| st.warning("Please upload PDF files first before submitting.") | |
| # Display chat history | |
| for idx, chat in enumerate(st.session_state.chat_history): | |
| with st.chat_message(chat["role"]): | |
| st.write(chat["content"]) | |
| if chat["role"] == "assistant": | |
| st.download_button( | |
| label="Download", | |
| data=chat["content"], | |
| file_name=f"response_{idx}.txt", | |
| mime="text/plain", | |
| key=f"download_{idx}", | |
| ) | |
| user_question = st.chat_input("Ask a Question from the PDF Files") | |
| if user_question: | |
| if not pdf_docs: | |
| st.warning("Please upload PDF files and process first before asking questions.") | |
| else: | |
| st.session_state.chat_history.append({"role": "user", "content": user_question}) | |
| st.chat_message("user").write(user_question) | |
| user_input(user_question) | |
| st.experimental_rerun() | |
| if __name__ == "__main__": | |
| main() | |