Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from dotenv import load_dotenv | |
| from PyPDF2 import PdfReader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.embeddings import HuggingFaceInstructEmbeddings | |
| from langchain_community.vectorstores import FAISS | |
| from langchain.memory import ConversationBufferMemory | |
| from langchain.chains import ConversationalRetrievalChain | |
| from langchain.llms import HuggingFaceHub | |
| from htmltemplates import css, bot_template, user_template | |
| def get_text_chunks(text): | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| chunk_size=1000, | |
| chunk_overlap=200, | |
| length_function=len | |
| ) | |
| chunks = text_splitter.split_text(text) | |
| return chunks | |
| 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_vectorstore(text_chunks): | |
| try: | |
| embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl") | |
| vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings) | |
| return vectorstore | |
| except Exception as e: | |
| st.error(f"Error in get_vectorstore: {e}") | |
| return None | |
| def get_conversation_chain(vectorstore): | |
| try: | |
| llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.8, "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 | |
| ) | |
| return conversation_chain | |
| except Exception as e: | |
| st.error(f"Error in get_conversation_chain: {e}") | |
| return None | |
| def handle_userinput(user_question): | |
| if st.session_state.conversation: | |
| try: | |
| 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) | |
| except Exception as e: | |
| st.error(f"Error in handle_userinput: {e}") | |
| else: | |
| st.error("Conversation chain is not initialized. Please upload and process documents first.") | |
| def main(): | |
| load_dotenv() | |
| st.set_page_config(page_title="Chat with your PDFs", page_icon=":books:") | |
| 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 = [] | |
| st.header("Chat with your PDFs :books:") | |
| user_question = st.text_input("Ask a question about your documents:") | |
| if user_question: | |
| handle_userinput(user_question) | |
| with st.sidebar: | |
| st.subheader("Your Documents") | |
| pdf_docs = st.file_uploader("Upload your PDFs here", accept_multiple_files=True) | |
| if st.button("Enter"): | |
| with st.spinner("Processing"): | |
| # Get PDF text | |
| raw_text = get_pdf_text(pdf_docs) | |
| # Get text chunks | |
| text_chunks = get_text_chunks(raw_text) | |
| if text_chunks: | |
| # Create vector store | |
| vectorstore = get_vectorstore(text_chunks) | |
| if vectorstore: | |
| # Initialize conversation chain | |
| st.session_state.conversation = get_conversation_chain(vectorstore) | |
| if st.session_state.conversation: | |
| st.success("Conversation chain initialized successfully.") | |
| if __name__ == "__main__": | |
| main() | |