import streamlit as st from PyPDF2 import PdfReader from langchain.text_splitter import CharacterTextSplitter from langchain.embeddings.openai import OpenAIEmbeddings from langchain.vectorstores import FAISS from langchain.chains.question_answering import load_qa_chain from langchain.llms import OpenAI from langchain.callbacks import get_openai_callback import os import openai from streamlit_chat import message def openai_pdf(): OPENAI_API_KEY = st.text_input("Input your OpenAI API key", "") os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY # st.header("Ask your PDF 💬") # upload file pdf = st.file_uploader("Upload your PDF", type="pdf") # extract the text if pdf is not None: pdf_reader = PdfReader(pdf) text = "" for page in pdf_reader.pages: text += page.extract_text() # split into chunks text_splitter = CharacterTextSplitter( separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len ) chunks = text_splitter.split_text(text) # create embeddings embeddings = OpenAIEmbeddings() knowledge_base = FAISS.from_texts(chunks, embeddings) # if 'generated' not in st.session_state: # st.session_state['generated'] = [] # if 'past' not in st.session_state: # st.session_state['past'] = [] # show user input user_question = st.text_input("Ask a question about your PDF:") if user_question: docs = knowledge_base.similarity_search(user_question) llm = OpenAI() chain = load_qa_chain(llm, chain_type="stuff") with get_openai_callback() as cb: response = chain.run(input_documents=docs, question=user_question) print(cb) st.write(response) # st.session_state.past.append(user_question) # st.session_state.generated.append(response) # if st.session_state['generated']: # for i in range(len(st.session_state['generated'])-1, -1, -1): # message(st.session_state["generated"][i], key=str(i)) # message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')