Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| from dotenv import load_dotenv | |
| from PyPDF2 import PdfReader | |
| from langchain.text_splitter import CharacterTextSplitter | |
| from langchain_community.vectorstores import FAISS | |
| from langchain.memory import ConversationBufferMemory | |
| from langchain.chains import ConversationalRetrievalChain | |
| from langchain.llms import HuggingFaceHub | |
| from langchain.embeddings import HuggingFaceEmbeddings | |
| def get_pdf_text(pdf_docs): | |
| text = "" | |
| for pdf in pdf_docs: | |
| try: | |
| pdf_reader = PdfReader(pdf) | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| except Exception as e: | |
| st.error(f"Error reading {pdf.name}: {e}. Skipping this file.") | |
| return text | |
| def get_text_chunks(text): | |
| text_splitter = CharacterTextSplitter( | |
| separator="\n", | |
| chunk_size=1000, | |
| chunk_overlap=200, | |
| length_function=len | |
| ) | |
| chunks = text_splitter.split_text(text) | |
| return chunks | |
| def get_vectorstore(text_chunks): | |
| try: | |
| embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") | |
| vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embedding) | |
| return vectorstore | |
| except Exception as e: | |
| st.error(f"Error creating vector store: {e}") | |
| return None | |
| def get_conversation_chain(vectorstore): | |
| # Fetch the HuggingFace API token from environment variable | |
| api_token = os.getenv("HUGGINGFACE_API_TOKEN") | |
| if not api_token: | |
| st.error("HuggingFace API token not found. Please ensure it is set in the environment variables.") | |
| return None | |
| llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.5, "max_length": 512}, huggingfacehub_api_token=api_token) | |
| 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 | |
| def handle_userinput(user_question): | |
| response = st.session_state.conversation({'question': user_question}) | |
| st.session_state.chat_history = response['chat_history'] | |
| def main(): | |
| load_dotenv() | |
| st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:") | |
| 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 | |
| st.header("Chat with multiple 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 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) | |
| if raw_text: # Proceed only if there is valid text | |
| # get the text chunks | |
| text_chunks = get_text_chunks(raw_text) | |
| # create vector store | |
| vectorstore = get_vectorstore(text_chunks) | |
| if vectorstore: # Check if vectorstore is valid | |
| # create conversation chain | |
| st.session_state.conversation = get_conversation_chain(vectorstore) | |
| if __name__ == '__main__': | |
| main() | |