import streamlit as st from dotenv import load_dotenv from PyPDF2 import PdfReader from langchain.text_splitter import CharacterTextSplitter from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings from langchain.vectorstores import FAISS from langchain.chat_models import ChatOpenAI from langchain.memory import ConversationBufferMemory from langchain.chains import ConversationalRetrievalChain from langchain.llms import HuggingFaceHub from html_template import css, bot_template, user_template def get_pdf_text(pdf_docs): text = '' for pdf in pdf_docs: reader = PdfReader(pdf) for page in reader.pages: text += page.extract_text() return text def get_text_chuks(raw_text): text_splitter = CharacterTextSplitter( separator = '\n', chunk_size = 1000, chunk_overlap = 200, length_function = len ) chunks = text_splitter.split_text(raw_text) return chunks def get_vector_store(text_chunks): # embeddings = OpenAIEmbeddings() embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl") vector_store = FAISS.from_texts(text_chunks, embeddings) return vector_store def get_conversation_chain(vectorstore): llm = ChatOpenAI(temperature=0.2) # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.2, "max_length":512}) memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True) conversation_chain = ConversationalRetrievalChain.from_llm( llm=llm, retriever=vectorstore.as_retriever(), memory=memory, # retriever_kwargs={"k": 1}, ) return conversation_chain def handle_user_question(user_question): response = st.session_state.conversation({"question": user_question}) st.session_state.chat_history = response['chat_history'] for i, message in enumerate(st.session_state.chat_history): if i % 2 == 0: st.write(user_template.replace( "{{MSG}}", message.content), unsafe_allow_html=True) else: st.write(bot_template.replace( "{{MSG}}", message.content), unsafe_allow_html=True) def main(): load_dotenv() st.set_page_config(page_title='Chat with your PDFs', page_icon='📂', layout='wide') st.header('Chat with multiple PDFs :books:') # st.write(bot_template.replace('{{MSG}}', 'hello user'), unsafe_allow_html=True) # st.write(user_template.replace('{{MSG}}', 'hello bot'), unsafe_allow_html=True) st.write(css, unsafe_allow_html=True) if 'conversation' not in st.session_state: st.session_state.conversation = None if "chat_history" not in st.session_state: st.session_state.chat_history = None with st.sidebar: st.subheader('Document') pdf_docs = st.file_uploader('Upload your PDFs here and click on Process', accept_multiple_files=True) if st.button('Process'): with st.spinner('Processing...'): # get pdf text raw_text = get_pdf_text(pdf_docs) # get the text chunks text_chunks = get_text_chuks(raw_text) # create vector store vectorstore = get_vector_store(text_chunks) # create conversation chain st.session_state.conversation = get_conversation_chain(vectorstore) user_question = st.text_input('Ask a question about your pdf') if user_question: handle_user_question(user_question) if __name__ == '__main__': main()