Powered by Multi-LLM RAG + FAISS
", unsafe_allow_html=True) # Sidebar controls with improved organization with st.sidebar: st.markdown("### ⚙️ Configuration") with st.expander("📊 Dataset Info", expanded=False): index_repo = os.environ.get("HF_DATASET_REPO_ID", "Wasifjafri/research-paper-vdb") index_dir = os.environ.get("FAISS_INDEX_REMOTE_DIR", "faiss_index") source_ds = os.environ.get("HF_SOURCE_DATASET", "") st.markdown(f""" **Vector index:** downloaded from `{index_repo}/{index_dir}` (HF dataset) Rebuild (optional) requires a papers dataset set via env: - `HF_SOURCE_DATASET` = `🔍 Searching research papers...
', unsafe_allow_html=True) # Check if casual conversation if is_casual_conversation(msg["query"]): casual_response = get_casual_response(msg["query"]) # Smooth streaming effect response_placeholder = st.empty() full_response = "" words = casual_response.split() for word in words: full_response += word + " " response_placeholder.markdown(full_response) time.sleep(0.02) st.session_state["messages"][i]["answer"] = casual_response st.rerun() else: # Research question - full RAG pipeline rag_chain, adv_retriever = build_chain() docs = [] answer_text = "" error_occurred = False try: docs = adv_retriever.get_relevant_documents(msg["query"]) if not docs: answer_text = """I couldn't find any relevant research papers in the database that match your query. **💡 Suggestions:** - Try using broader or different search terms - Check the spelling of technical terms - The database may not contain papers on this specific topic - Consider rebuilding the index with more data The current database focuses on ArXiv ML papers, but may not cover all research areas comprehensively.""" else: thinking_placeholder.markdown('🧠 Analyzing documents...
', unsafe_allow_html=True) # Check relevance formatted_context = format_docs(docs) relevance_check_chain = {"context": RunnablePassthrough(), "question": RunnablePassthrough()} | relevance_prompt | llm relevance_result = relevance_check_chain.invoke({"context": formatted_context, "question": msg["query"]}) relevance_text = relevance_result.content if hasattr(relevance_result, "content") else str(relevance_result) if "IRRELEVANT" in relevance_text.strip().upper(): answer_text = f"""I found {len(docs)} documents in the database, but they don't contain relevant information about your question. **📋 Retrieved topics:** - {docs[0].metadata.get('title', 'Various topics') if docs else 'N/A'} **💡 Suggestions:** - Try rephrasing with different keywords - Use more specific technical terms - Search for related concepts or broader topics - The database may not have papers specifically on this topic I can only provide answers based on the ArXiv papers in the database.""" else: # Generate answer with streaming thinking_placeholder.markdown('✍️ Generating response...
', unsafe_allow_html=True) answer = rag_chain.invoke(msg["query"]) answer_text = answer.content if hasattr(answer, "content") else str(answer) except Exception as e: error_occurred = True msg_err = str(e) if "models/" in msg_err and "not found" in msg_err.lower(): answer_text = "⚠️ Selected model not found. Try a different model in the sidebar." else: answer_text = f"⚠️ An error occurred: {e}\n\nPlease try again or rebuild the index." # Clear thinking and display response with streaming thinking_placeholder.empty() # Stream response import re response_placeholder = st.empty() parts = re.split(r'(\n\n|(?<=[.!?])\s+)', answer_text) full_response = "" for part in parts: full_response += part response_placeholder.markdown(full_response) time.sleep(0.03) # Update session state st.session_state["messages"][i]["answer"] = answer_text st.session_state["messages"][i]["context"] = docs # Show retrieved documents if docs: with st.expander(f"📄 View {len(docs)} Retrieved Documents", expanded=False): for idx, doc in enumerate(docs, 1): st.markdown(f"**📎 Document {idx}**") st.caption(_format_metadata(doc.metadata)) st.text_area( f"Content {idx}", doc.page_content[:800] + ("..." if len(doc.page_content) > 800 else ""), height=150, key=f"new_doc_{i}_{idx}", disabled=True ) if idx < len(docs): st.markdown("---") st.rerun() # Process new query if query: # Add message to session state immediately st.session_state["messages"].append({ "query": query, "answer": None, "context": [] }) # Force rerun to show the user message immediately st.rerun() # Footer with tips - only show if there are messages if len(st.session_state["messages"]) > 0: st.markdown("---") with st.expander("💡 Tips for Better Results", expanded=False): col1, col2 = st.columns(2) with col1: st.markdown(""" **🎯 Asking Better Questions** ✅ Use specific ML terminology ✅ Mention techniques or methods ✅ Ask for comparisons ✅ Reference specific problems **Examples:** - "Papers on transformer architecture" - "Compare CNNs vs Vision Transformers" - "Explain BERT training methodology" """) with col2: st.markdown(""" **📚 Understanding Responses** ✅ All answers from actual papers ✅ View source documents anytime ✅ Check relevance of results ✅ Adjust settings if needed **⚡ Advanced Tips:** - Use sidebar filters (year, category) - Adjust retrieval settings - Try different LLM providers - Rebuild index for fresh data """) # Add a "Clear Chat" button at the bottom of sidebar with st.sidebar: st.markdown("---") if st.button("🗑️ Clear Chat History", use_container_width=True): st.session_state["messages"] = [] st.session_state["show_welcome"] = True st.rerun()