from dotenv import load_dotenv import streamlit as st from langchain_community.document_loaders import UnstructuredPDFLoader from langchain_text_splitters.character import CharacterTextSplitter from langchain_community.vectorstores import FAISS from langchain_community.embeddings import HuggingFaceEmbeddings from langchain_groq import ChatGroq from langchain.memory import ConversationBufferMemory from langchain.chains import ConversationalRetrievalChain import os import nltk # Load environment variables load_dotenv() import nltk nltk.download('punkt_tab') working_dir = os.getcwd() def load_documents(file_path): loader = UnstructuredPDFLoader(file_path) documents = loader.load() return documents def setup_vectorstore(documents): embeddings = HuggingFaceEmbeddings() text_splitter = CharacterTextSplitter( separator="/n", chunk_size=1000, chunk_overlap=200 ) doc_chunks = text_splitter.split_documents(documents) vectorstores = FAISS.from_documents(doc_chunks, embeddings) return vectorstores def create_chain(vectorstores): llm = ChatGroq( model="llama-3.1-70b-versatile", temperature=0 ) retriever = vectorstores.as_retriever() memory = ConversationBufferMemory( llm=llm, output_key="answer", memory_key="chat_history", return_messages=True ) chain = ConversationalRetrievalChain.from_llm( llm=llm, retriever=retriever, memory=memory, verbose=True ) return chain st.set_page_config( page_title="Chat with your documents", page_icon="πŸ“‘", layout="centered" ) st.title("πŸ“Chat With your docs 😎") if "chat_history" not in st.session_state: st.session_state.chat_history = [] uploaded_file = st.file_uploader(label="Upload your PDF") if uploaded_file: file_path = f"{working_dir}{uploaded_file.name}" with open(file_path, "wb") as f: f.write(uploaded_file.getbuffer()) if "vectorstores" not in st.session_state: st.session_state.vectorstores = setup_vectorstore(load_documents(file_path)) if "conversation_chain" not in st.session_state: st.session_state.conversation_chain = create_chain(st.session_state.vectorstores) for message in st.session_state.chat_history: with st.chat_message(message["role"]): st.markdown(message["content"]) user_input = st.chat_input("Ask any questions relevant to uploaded pdf") if user_input: st.session_state.chat_history.append({"role": "user", "content": user_input}) with st.chat_message("user"): st.markdown(user_input) with st.chat_message("assistant"): response = st.session_state.conversation_chain({"question": user_input}) assistant_response = response["answer"] st.markdown(assistant_response) st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})