Fix: ChatInterface examples must be list-of-lists matching additional_inputs count

app.py

@@ -12,10 +12,7 @@ Architecture:
 
 import gradio as gr
 import numpy as np
-import json
 import os
-import re
-import time
 from pathlib import Path
 
 # ── Conditional imports with fallbacks ────────────────────────────────────────
@@ -60,6 +57,9 @@ CHUNK_SIZE = 400
 CHUNK_OVERLAP = 60
 TOP_K_RETRIEVAL = 3
 
+DEFAULT_SYSTEM_PROMPT = SYSTEM_PROMPTS["ask_tutor"]
+DEFAULT_RAG_STATE = {"chunks": [], "embeddings": None}
+
 
 # ============================================================================
 # BACKEND SERVICES — Singleton Pattern
@@ -104,30 +104,11 @@ class LLMService:
     def is_available(self):
         return self.client is not None
 
-    def _format_messages(self, messages, system_prompt=None, rag_context=None):
-        """Build message list with optional system prompt and RAG context."""
-        formatted = []
-        if system_prompt:
-            formatted.append({"role": "system", "content": system_prompt})
-        if rag_context:
-            formatted.append({"role": "system", "content": rag_context})
-        # Add conversation history (already formatted)
-        for m in messages:
-            if isinstance(m, dict) and "role" in m:
-                formatted.append(m)
-            elif isinstance(m, (list, tuple)) and len(m) >= 2:
-                # Handle tuple format (text, response)
-                formatted.append({"role": "user", "content": str(m[0])})
-                if len(m) > 1 and m[1]:
-                    formatted.append({"role": "assistant", "content": str(m[1])})
-        return formatted
-
     def stream_chat(self, messages, temperature=0.7, max_tokens=1024):
         """Stream chat completion. Yields partial response strings."""
         if not self.is_available():
             yield self._fallback_response(messages)
             return
-
         try:
             partial = ""
             for chunk in self.client.chat_completion(
@@ -152,7 +133,6 @@ class LLMService:
         """Non-streaming generation. Returns complete response."""
         if not self.is_available():
             return self._fallback_response(messages)
-
         try:
             response = self.client.chat_completion(
                 messages=messages,
@@ -164,30 +144,25 @@ class LLMService:
             return response.choices[0].message.content
         except Exception as e:
             print(f"LLM generate error: {e}")
-            return f"⚠️ LLM API error: {str(e)}\n\nThe tutor can still answer from its knowledge base. Try asking about specific concepts like 'DESeq2 normalization' or 'variant calling pipeline'!"
+            return f"⚠️ LLM API error: {str(e)}\n\nThe tutor can still answer from its knowledge base. Try asking about specific concepts!"
 
     def _fallback_response(self, messages):
         """Knowledge-base fallback when LLM unavailable."""
-        # Extract user query
         user_msg = ""
         for m in reversed(messages):
             if isinstance(m, dict) and m.get("role") == "user":
                 user_msg = m.get("content", "").lower()
                 break
-
         if not user_msg:
             return "⚠️ **LLM not available.** Add HF_TOKEN in Space settings to enable AI responses.\n\nMeanwhile, the knowledge base covers: DESeq2, variant calling, microbiome diversity, scRNA-seq clustering, and more. Try asking a specific question!"
 
         response_parts = []
-
-        # Glossary match
         for term, definition in GLOSSARY.items():
             if term.lower() in user_msg:
                 response_parts.append(f"**{term}**: {definition}")
                 if len(response_parts) >= 3:
                     break
 
-        # Workflow match
         for wf_key, wf in WORKFLOWS.items():
             if any(kw in user_msg for kw in wf["name"].lower().split()):
                 response_parts.append(f"\n### {wf['name']}")
@@ -195,7 +170,6 @@ class LLMService:
                     response_parts.append(f"**Step {step['step']}: {step['name']}**\n{step['description']}")
                 break
 
-        # Misconception match
         for misc in COMMON_MISCONCEPTIONS:
             if misc["domain"].replace("_", " ") in user_msg or any(w in user_msg for w in misc["misconception"].lower().split()[:5]):
                 response_parts.append(f"\n⚠️ **Common Misconception**: {misc['misconception']}\n\n✅ **Correction**: {misc['correction']}")
@@ -235,16 +209,14 @@ class RAGService:
         self._build_kb_index()
 
     def _ensure_embedder(self):
-        """Lazy load the embedding model."""
         if self.embedder is not None:
             return True
         if not HAS_ST:
             return False
         try:
-            print("RAGService: Loading embedding model (this may take a moment)...")
+            print("RAGService: Loading embedding model...")
             self.embedder = SentenceTransformer(EMBED_MODEL)
             print("RAGService: Embedding model loaded")
-            # Now embed the KB
             if self.kb_chunks:
                 self.kb_embeddings = self.embedder.encode(
                     self.kb_chunks,
@@ -260,16 +232,11 @@ class RAGService:
             return False
 
     def _build_kb_index(self):
-        """Build searchable chunks from knowledge base."""
         chunks = []
         metadata = []
-
-        # Glossary
         for term, definition in GLOSSARY.items():
             chunks.append(f"{term}: {definition}")
             metadata.append({"source": "glossary", "topic": term, "type": "definition"})
-
-        # Workflows
         for wf_key, wf in WORKFLOWS.items():
             for step in wf["steps"]:
                 step_text = f"{wf['name']} - Step {step['step']}: {step['name']}. {step['description']}"
@@ -285,8 +252,6 @@ class RAGService:
                     "step": step["step"],
                     "workflow": wf_key
                 })
-
-        # Misconceptions
         for misc in COMMON_MISCONCEPTIONS:
             text = f"Misconception: {misc['misconception']} Correction: {misc['correction']}"
             chunks.append(text)
@@ -296,32 +261,24 @@ class RAGService:
                 "type": "misconception",
                 "severity": misc["severity"]
             })
-
-        # Taxonomy
         for key, domain in DOMAIN_TAXONOMY.items():
             text = f"{domain['name']} covers: {', '.join(domain['subtopics'][:10])}"
             chunks.append(text)
             metadata.append({"source": "taxonomy", "topic": key, "type": "domain_overview"})
-
         self.kb_chunks = chunks
         self.kb_metadata = metadata
         print(f"RAGService: Built KB with {len(chunks)} chunks")
 
     def search(self, query, top_k=TOP_K_RETRIEVAL, user_chunks=None, user_embeddings=None):
-        """Search KB and optionally user-uploaded content."""
         if not self._ensure_embedder():
             return self._keyword_search(query, top_k)
-
         try:
             query_embedding = self.embedder.encode(
                 [query],
                 convert_to_numpy=True,
                 normalize_embeddings=True,
             )
-
             results = []
-
-            # Search KB
             if self.kb_embeddings is not None and len(self.kb_embeddings) > 0:
                 kb_scores = np.dot(query_embedding, self.kb_embeddings.T)[0]
                 top_indices = np.argsort(kb_scores)[::-1][:top_k]
@@ -332,8 +289,6 @@ class RAGService:
                             "score": float(kb_scores[idx]),
                             "metadata": self.kb_metadata[idx]
                         })
-
-            # Search user content
             if user_chunks and user_embeddings is not None and len(user_embeddings) > 0:
                 user_scores = np.dot(query_embedding, user_embeddings.T)[0]
                 top_user = np.argsort(user_scores)[::-1][:top_k]
@@ -344,7 +299,6 @@ class RAGService:
                             "score": float(user_scores[idx]),
                             "metadata": {"source": "uploaded", "type": "user_content"}
                         })
-
             results.sort(key=lambda x: x["score"], reverse=True)
             return results[:top_k]
         except Exception as e:
@@ -352,7 +306,6 @@ class RAGService:
             return self._keyword_search(query, top_k)
 
     def _keyword_search(self, query, top_k=3):
-        """Fallback keyword search."""
         query_words = set(query.lower().split())
         scored = []
         for i, chunk in enumerate(self.kb_chunks):
@@ -368,7 +321,6 @@ class RAGService:
         return scored[:top_k]
 
     def embed_chunks(self, chunks):
-        """Embed text chunks. Returns numpy array or None."""
         if not self._ensure_embedder() or not chunks:
             return None
         try:
@@ -385,16 +337,12 @@ class RAGService:
 
 
 class DocumentParser:
-    """Parse uploaded documents."""
-
     @staticmethod
     def parse_file(filepath):
-        """Extract text from uploaded file."""
         if filepath is None:
             return "", []
         filepath = str(filepath)
         ext = Path(filepath).suffix.lower()
-
         try:
             if ext == ".pdf" and HAS_FITZ:
                 return DocumentParser._parse_pdf(filepath)
@@ -438,7 +386,6 @@ class DocumentParser:
         return chunks
 
 
-# ── Initialize services (lightweight, no heavy downloads) ───────────────────────
 llm_service = LLMService()
 rag_service = RAGService()
 doc_parser = DocumentParser()
@@ -446,11 +393,10 @@ print(f"🧬 BB Tutor initialized. LLM: {llm_service.is_available()}, Embeddings
 
 
 # ============================================================================
-# HANDLER FUNCTIONS — All receive/return plain Python values (not components)
+# HELPER FUNCTIONS
 # ============================================================================
 
 def _rag_context(query, user_chunks=None, user_embeddings=None):
-    """Retrieve RAG context as formatted string."""
     results = rag_service.search(query, top_k=TOP_K_RETRIEVAL,
                                    user_chunks=user_chunks, user_embeddings=user_embeddings)
     if not results:
@@ -463,7 +409,6 @@ def _rag_context(query, user_chunks=None, user_embeddings=None):
 
 
 def _format_history(history):
-    """Convert Gradio history to OpenAI-style messages."""
     messages = []
     for h in history:
         if isinstance(h, dict):
@@ -476,140 +421,107 @@ def _format_history(history):
     return messages
 
 
-# ── Module 1: Ask the Tutor ───────────────────────────────────────────────────
+# ============================================================================
+# MODULE HANDLERS
+# ============================================================================
 
 def tutor_respond(message, history, system_prompt, temperature, max_tokens, rag_state):
-    """Ask the Tutor handler — streaming."""
     if not message or not message.strip():
         yield ""
         return
-
-    rag_state = rag_state or {"chunks": [], "embeddings": None}
+    rag_state = rag_state or DEFAULT_RAG_STATE
     user_chunks = rag_state.get("chunks", [])
     user_embeddings = rag_state.get("embeddings")
-
     rag_ctx = _rag_context(message, user_chunks, user_embeddings)
-
     messages = [{"role": "system", "content": system_prompt}]
     if rag_ctx:
         messages.append({"role": "system", "content": rag_ctx})
     messages.extend(_format_history(history))
     messages.append({"role": "user", "content": message})
-
     for partial in llm_service.stream_chat(messages, temperature, max_tokens):
         yield partial
 
 
-# ── Module 2: Upload & Explain ──────────────────────────────────────────────
-
 def process_upload(file, rag_state):
-    """Process uploaded file. Returns (explanation_markdown, raw_text, new_rag_state)."""
-    rag_state = rag_state or {"chunks": [], "embeddings": None}
-
+    rag_state = rag_state or DEFAULT_RAG_STATE
     if file is None:
         return "📁 Please upload a file first.", "", rag_state
-
     full_text, chunks = doc_parser.parse_file(file)
-
     if not chunks:
         return "⚠️ Could not extract text from the uploaded file.", full_text[:2000] if full_text else "", rag_state
-
     embeddings = rag_service.embed_chunks(chunks)
     new_state = {"chunks": chunks, "embeddings": embeddings}
-
     preview = full_text[:2500] if len(full_text) > 2500 else full_text
     msgs = [
         {"role": "system", "content": SYSTEM_PROMPTS["upload_explain"]},
         {"role": "user", "content": f"Analyze and explain this bioinformatics document:\n\n{preview}"}
     ]
     explanation = llm_service.generate(msgs, temperature=0.5, max_tokens=1500)
-
     stats = f"📊 **Document Stats:** {len(chunks)} chunks, ~{len(full_text.split())} words | "
     stats += f"File type: {Path(str(file)).suffix} | "
     stats += "🤖 AI-powered" if llm_service.is_available() else "📚 Knowledge-base mode"
     stats += f"\n\n---\n\n"
-
     return stats + explanation, full_text[:5000], new_state
 
 
 def upload_chat_respond(message, history, rag_state):
-    """Chat about uploaded documents."""
     if not message or not message.strip():
         yield ""
         return
-
-    rag_state = rag_state or {"chunks": [], "embeddings": None}
+    rag_state = rag_state or DEFAULT_RAG_STATE
     user_chunks = rag_state.get("chunks", [])
     user_embeddings = rag_state.get("embeddings")
-
     if not user_chunks:
         yield "📁 Please upload a document in the panel above, then ask questions about it.\n\nYour uploaded document will be indexed and searchable across all modules!"
         return
-
     rag_results = rag_service.search(message, top_k=4, user_chunks=user_chunks, user_embeddings=user_embeddings)
-
     ctx = "CONTEXT FROM UPLOADED DOCUMENT:\n"
     if rag_results:
         for r in rag_results:
             ctx += f"\n{r['text'][:600]}\n"
     else:
         ctx += "(No highly relevant passages found — answering from general knowledge)\n"
-
     messages = [
         {"role": "system", "content": SYSTEM_PROMPTS["upload_explain"]},
         {"role": "system", "content": ctx},
     ]
     messages.extend(_format_history(history))
     messages.append({"role": "user", "content": message})
-
     for partial in llm_service.stream_chat(messages, temperature=0.5, max_tokens=1024):
         yield partial
 
 
-# ── Module 3: Quiz Me ─────────────────────────────────────────────────────────
-
 def generate_quiz(topic, quiz_type, num_questions, difficulty, rag_state):
-    """Generate quiz. Returns (quiz_markdown, answer_key_string)."""
     if not topic:
         return "❓ Please select or enter a topic first.", ""
-
-    rag_state = rag_state or {"chunks": [], "embeddings": None}
     rag_results = rag_service.search(topic, top_k=3)
     context = ""
     if rag_results:
         context = "Reference material:\n" + "\n".join(r["text"][:500] for r in rag_results)
-
     template_key = {
         "Multiple Choice (MCQ)": "mcq",
         "True/False": "true_false",
         "Short Answer": "short_answer"
     }.get(quiz_type, "mcq")
-
     quiz_prompt = QUIZ_TEMPLATES[template_key].format(
         n=int(num_questions), topic=topic, difficulty=difficulty
     )
-
     messages = [{"role": "system", "content": SYSTEM_PROMPTS["quiz_me"]}]
     if context:
         messages.append({"role": "system", "content": context})
     messages.append({"role": "user", "content": quiz_prompt})
-
     response = llm_service.generate(messages, temperature=0.8, max_tokens=2000)
-
     formatted = f"## 🧠 {topic} Quiz — {difficulty}\n\n"
     formatted += f"*Format: {quiz_type} | Questions: {int(num_questions)}*\n\n---\n\n"
     formatted += response
-
     return formatted, response
 
 
 def check_quiz_answers(user_answers, answer_key):
-    """Grade quiz answers."""
     if not user_answers or not user_answers.strip():
         return "✍️ Please enter your answers above before checking."
     if not answer_key:
         return "⚠️ Please generate a quiz first (use the panel above)."
-
     messages = [
         {"role": "system", "content": "You are a bioinformatics tutor grading a quiz. Compare student answers to correct answers. For each: mark ✅ or ❌, explain briefly, provide correct answer if wrong. Be encouraging. Give final score."},
         {"role": "user", "content": f"QUIZ AND ANSWERS:\n{answer_key}\n\nSTUDENT ANSWERS:\n{user_answers}\n\nGrade each:"}
@@ -617,40 +529,29 @@ def check_quiz_answers(user_answers, answer_key):
     return llm_service.generate(messages, temperature=0.3, max_tokens=1500)
 
 
-# ── Module 4: Build a Lesson ──────────────────────────────────────────────────
-
 def generate_lesson(topic, level, include_exercises, include_quiz):
-    """Generate structured lesson."""
     if not topic:
         return "📚 Please select or enter a topic."
-
     rag_results = rag_service.search(topic, top_k=4)
     context = ""
     if rag_results:
         context = "Reference:\n" + "\n".join(r["text"][:500] for r in rag_results)
-
     prompt = LESSON_TEMPLATE.format(topic=topic, level=level)
     if include_exercises:
         prompt += "\n\nInclude 2-3 practical exercises with clear instructions."
     if include_quiz:
         prompt += "\n\nInclude a 5-question self-assessment quiz (with answers)."
-
     messages = [{"role": "system", "content": SYSTEM_PROMPTS["build_lesson"]}]
     if context:
         messages.append({"role": "system", "content": context})
     messages.append({"role": "user", "content": prompt})
-
     return llm_service.generate(messages, temperature=0.7, max_tokens=3000)
 
 
-# ── Module 5: Workflow Coach ──────────────────────────────────────────────────
-
 def workflow_respond(message, history, selected_workflow, temperature):
-    """Workflow Coach handler."""
     if not message or not message.strip():
         yield ""
         return
-
     workflow_context = ""
     for wf_key, wf in WORKFLOWS.items():
         if wf["name"] in selected_workflow or selected_workflow.lower() in wf["name"].lower():
@@ -664,78 +565,60 @@ def workflow_respond(message, history, selected_workflow, temperature):
                     workflow_context += f"  ⚠️ Common mistakes: {'; '.join(step['common_mistakes'])}\n"
                 workflow_context += "\n"
             break
-
     rag_results = rag_service.search(message, top_k=2)
     if rag_results:
         workflow_context += "\nADDITIONAL CONTEXT:\n" + "\n".join(r["text"][:500] for r in rag_results)
-
     messages = [{"role": "system", "content": SYSTEM_PROMPTS["workflow_coach"]}]
     if workflow_context:
         messages.append({"role": "system", "content": workflow_context})
     messages.extend(_format_history(history))
     messages.append({"role": "user", "content": message})
-
     for partial in llm_service.stream_chat(messages, temperature, 1500):
         yield partial
 
 
-# ── Module 6: Paper to Lesson ─────────────────────────────────────────────────
-
 def paper_to_lesson_respond(message, history, output_format, rag_state):
-    """Convert papers to teaching material."""
     if not message or not message.strip():
         yield ""
         return
-
-    rag_state = rag_state or {"chunks": [], "embeddings": None}
+    rag_state = rag_state or DEFAULT_RAG_STATE
     user_chunks = rag_state.get("chunks", [])
     user_embeddings = rag_state.get("embeddings")
-
     context = ""
     if user_chunks:
         rag_results = rag_service.search(message, top_k=4, user_chunks=user_chunks, user_embeddings=user_embeddings)
         if rag_results:
             context = "PAPER CONTENT:\n" + "\n".join(r["text"][:600] for r in rag_results)
-
     format_instruction = {
         "Lesson Plan": "Create a structured lesson plan with learning objectives, sections, and exercises.",
         "Slide Outline": "Create a slide-by-slide outline with key points for each slide.",
         "Study Notes": "Create concise study notes highlighting key methods, tools, and findings.",
         "Quiz Questions": "Generate 5-10 quiz questions based on the paper's methods and findings.",
     }.get(output_format, "Create a structured lesson plan.")
-
     messages = [{"role": "system", "content": SYSTEM_PROMPTS["paper_to_lesson"]}]
     if context:
         messages.append({"role": "system", "content": context})
     messages.extend(_format_history(history))
-
     full_msg = f"{message}\n\nOUTPUT FORMAT: {format_instruction}"
     messages.append({"role": "user", "content": full_msg})
-
     for partial in llm_service.stream_chat(messages, temperature=0.7, max_tokens=2500):
         yield partial
 
 
-# ── Module 7: Viva Practice ───────────────────────────────────────────────────
-
 def viva_respond(message, history, topic, difficulty):
-    """Viva practice handler."""
     if not message or not message.strip():
         yield ""
         return
-
     rag_results = rag_service.search(f"{topic} {message}", top_k=3)
     context = ""
     if rag_results:
         context = "Reference:\n" + "\n".join(r["text"][:500] for r in rag_results)
-
     messages = [
         {"role": "system", "content": SYSTEM_PROMPTS["viva_practice"]},
         {"role": "system", "content": f"VIVA TOPIC: {topic}\nDIFFICULTY: {difficulty}\n\n{context}"},
     ]
     messages.extend(_format_history(history))
     messages.append({"role": "user", "content": message})
-
     for partial in llm_service.stream_chat(messages, temperature=0.7, max_tokens=1000):
         yield partial
 
@@ -746,36 +629,23 @@ def viva_respond(message, history, topic, difficulty):
 
 CUSTOM_CSS = """
 .main-header {
-    text-align: center;
-    padding: 20px;
+    text-align: center; padding: 20px;
     background: linear-gradient(135deg, #1a5276 0%, #2e86c1 50%, #48c9b0 100%);
-    border-radius: 12px;
-    margin-bottom: 20px;
-    color: white;
+    border-radius: 12px; margin-bottom: 20px; color: white;
 }
 .main-header h1 { color: white; font-size: 2em; margin: 0; }
 .main-header p { color: #ecf0f1; margin: 5px 0; }
 .module-info {
-    background: #f0f9ff;
-    border-left: 4px solid #2e86c1;
-    padding: 12px 16px;
-    margin-bottom: 16px;
-    border-radius: 0 8px 8px 0;
+    background: #f0f9ff; border-left: 4px solid #2e86c1;
+    padding: 12px 16px; margin-bottom: 16px; border-radius: 0 8px 8px 0;
 }
 .safety-notice {
-    background: #fff3e0;
-    border-left: 4px solid #f39c12;
-    padding: 10px 14px;
-    margin-top: 10px;
-    border-radius: 0 8px 8px 0;
-    font-size: 0.9em;
+    background: #fff3e0; border-left: 4px solid #f39c12;
+    padding: 10px 14px; margin-top: 10px; border-radius: 0 8px 8px 0; font-size: 0.9em;
 }
 .status-badge {
-    display: inline-block;
-    padding: 4px 12px;
-    border-radius: 12px;
-    font-size: 0.85em;
-    font-weight: bold;
+    display: inline-block; padding: 4px 12px; border-radius: 12px;
+    font-size: 0.85em; font-weight: bold;
 }
 .status-on { background: #d4edda; color: #155724; }
 .status-off { background: #f8d7da; color: #721c24; }
@@ -786,7 +656,7 @@ def build_app():
     with gr.Blocks(title="Bioinformatics with BB Tutor", css=CUSTOM_CSS) as demo:
 
         # ── Global shared state ─────────────────────────────────────────
-        rag_store = gr.State({"chunks": [], "embeddings": None})
+        rag_store = gr.State(DEFAULT_RAG_STATE)
 
         # ── Status indicator ────────────────────────────────────────────
         llm_status = "🟢 AI Enabled" if llm_service.is_available() else "🔴 AI Offline (Knowledge Base Active)"
@@ -813,31 +683,30 @@ def build_app():
             with gr.Tab("🧬 Ask the Tutor", id="ask"):
                 gr.HTML('<div class="module-info">💡 Ask any bioinformatics question. RAG-augmented responses from a curated knowledge base covering 15+ domains.</div>')
 
+                # Examples must be list-of-lists matching fn signature: (message, history, system_prompt, temperature, max_tokens, rag_state)
+                # Additional inputs: [system_prompt, temperature, max_tokens, rag_store] → 4 values per example
+                ask_examples = [
+                    ["What is the difference between DESeq2 and edgeR?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["Explain the GATK variant calling pipeline step by step.", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["What is the difference between alpha and beta diversity?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["Why should I use adjusted p-values instead of raw p-values?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["Explain the single-cell RNA-seq analysis workflow.", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["What is BQSR and why is it important?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["How do I choose between STAR and HISAT2 for alignment?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                    ["What common mistakes do students make with DESeq2?", DEFAULT_SYSTEM_PROMPT, 0.7, 1024, DEFAULT_RAG_STATE],
+                ]
+
                 gr.ChatInterface(
                     fn=tutor_respond,
                     type="messages",
                     additional_inputs=[
-                        gr.Textbox(
-                            value=SYSTEM_PROMPTS["ask_tutor"],
-                            label="System Prompt",
-                            lines=2,
-                            visible=False,
-                        ),
+                        gr.Textbox(value=DEFAULT_SYSTEM_PROMPT, label="System Prompt", lines=2, visible=False),
                         gr.Slider(0.1, 1.5, 0.7, step=0.1, label="Temperature", visible=False),
                         gr.Slider(256, 4096, 1024, step=256, label="Max Tokens", visible=False),
                         rag_store,
                     ],
                     additional_inputs_accordion=gr.Accordion("⚙️ Advanced", open=False, visible=False),
-                    examples=[
-                        "What is the difference between DESeq2 and edgeR?",
-                        "Explain the GATK variant calling pipeline step by step.",
-                        "What is the difference between alpha and beta diversity?",
-                        "Why should I use adjusted p-values instead of raw p-values?",
-                        "Explain the single-cell RNA-seq analysis workflow.",
-                        "What is BQSR and why is it important?",
-                        "How do I choose between STAR and HISAT2 for alignment?",
-                        "What common mistakes do students make with DESeq2?",
-                    ],
+                    examples=ask_examples,
                 )
                 gr.HTML('<div class="safety-notice">⚠️ <strong>Educational use only.</strong> Not for clinical interpretation. Always consult qualified professionals for clinical genomics.</div>')
 
@@ -854,12 +723,10 @@ def build_app():
                             file_types=[".pdf", ".txt", ".md", ".csv", ".tsv",
                                        ".fasta", ".fa", ".fastq", ".vcf", ".bed",
                                        ".gff", ".gtf", ".sam", ".bam"],
-                            file_count="single",
-                            type="filepath",
+                            file_count="single", type="filepath",
                         )
                         process_btn = gr.Button("🔍 Analyze Document", variant="primary")
                         gr.Markdown("**Supported:** PDF, text, FASTA/FASTQ, VCF, BED, GFF/GTF, SAM/BAM, CSV/TSV")
-
                     with gr.Column(scale=2):
                         explanation_output = gr.Markdown(label="Analysis & Explanation")
 
@@ -873,17 +740,20 @@ def build_app():
                 )
 
                 gr.Markdown("### 💬 Chat About Your Document")
+
+                # fn signature: (message, history, rag_state) → 1 additional input
+                upload_chat_examples = [
+                    ["Summarize the key methods in this paper.", DEFAULT_RAG_STATE],
+                    ["What bioinformatics tools are mentioned?", DEFAULT_RAG_STATE],
+                    ["Explain the main findings in simple terms.", DEFAULT_RAG_STATE],
+                    ["What are the limitations of this analysis?", DEFAULT_RAG_STATE],
+                ]
+
                 gr.ChatInterface(
                     fn=upload_chat_respond,
                     type="messages",
                     additional_inputs=[rag_store],
-                    additional_inputs_accordion=gr.Accordion("", open=False, visible=False),
-                    examples=[
-                        "Summarize the key methods in this paper.",
-                        "What bioinformatics tools are mentioned?",
-                        "Explain the main findings in simple terms.",
-                        "What are the limitations of this analysis?",
-                    ],
+                    examples=upload_chat_examples,
                 )
 
             # ══════════════════════════════════════════════════════════════
@@ -894,22 +764,16 @@ def build_app():
 
                 with gr.Row():
                     quiz_topic = gr.Dropdown(
-                        choices=TOPIC_CHOICES,
-                        label="Select Topic",
-                        allow_custom_value=True,
-                        value="RNA-seq: Differential Expression (DESeq2)"
+                        choices=TOPIC_CHOICES, label="Select Topic",
+                        allow_custom_value=True, value="RNA-seq: Differential Expression (DESeq2)"
                     )
                     quiz_type = gr.Radio(
                         choices=["Multiple Choice (MCQ)", "True/False", "Short Answer"],
-                        value="Multiple Choice (MCQ)",
-                        label="Format"
+                        value="Multiple Choice (MCQ)", label="Format"
                     )
-
                 with gr.Row():
                     quiz_difficulty = gr.Radio(
-                        choices=DIFFICULTY_LEVELS,
-                        value="Intermediate",
-                        label="Difficulty"
+                        choices=DIFFICULTY_LEVELS, value="Intermediate", label="Difficulty"
                     )
                     num_questions = gr.Slider(1, 10, 5, step=1, label="# Questions")
                     generate_quiz_btn = gr.Button("🎲 Generate Quiz", variant="primary")
@@ -928,9 +792,7 @@ def build_app():
                 with gr.Row():
                     user_answers = gr.Textbox(
                         label="Your Answers (e.g., '1: A, 2: B')",
-                        lines=5,
-                        placeholder="Type your answers here...",
-                        scale=3
+                        lines=5, placeholder="Type your answers here...", scale=3
                     )
                     check_btn = gr.Button("✅ Check", variant="primary", scale=1)
                 feedback_output = gr.Markdown(label="Feedback")
@@ -949,17 +811,12 @@ def build_app():
 
                 with gr.Row():
                     lesson_topic = gr.Dropdown(
-                        choices=TOPIC_CHOICES,
-                        label="Lesson Topic",
-                        allow_custom_value=True,
-                        value="RNA-seq: Differential Expression (DESeq2)"
+                        choices=TOPIC_CHOICES, label="Lesson Topic",
+                        allow_custom_value=True, value="RNA-seq: Differential Expression (DESeq2)"
                     )
                     lesson_level = gr.Radio(
-                        choices=DIFFICULTY_LEVELS,
-                        value="Intermediate",
-                        label="Level"
+                        choices=DIFFICULTY_LEVELS, value="Intermediate", label="Level"
                     )
-
                 with gr.Row():
                     include_exercises = gr.Checkbox(label="Include Exercises", value=True)
                     include_quiz = gr.Checkbox(label="Include Quiz", value=True)
@@ -980,12 +837,20 @@ def build_app():
                 gr.HTML('<div class="module-info">🔬 Step-by-step guidance through bioinformatics analysis pipelines. Select a workflow and ask about any step.</div>')
 
                 workflow_selector = gr.Dropdown(
-                    choices=WORKFLOW_CHOICES,
-                    label="Select Workflow",
-                    value="Bulk RNA-seq: Full DE Analysis Pipeline",
-                    allow_custom_value=True,
+                    choices=WORKFLOW_CHOICES, label="Select Workflow",
+                    value="Bulk RNA-seq: Full DE Analysis Pipeline", allow_custom_value=True,
                 )
 
+                # fn signature: (message, history, selected_workflow, temperature) → 2 additional inputs
+                workflow_examples = [
+                    ["Walk me through the complete pipeline from raw FASTQ to DE results.", "Bulk RNA-seq: Full DE Analysis Pipeline", 0.7],
+                    ["I'm at alignment. What should I check before counting?", "Bulk RNA-seq: Full DE Analysis Pipeline", 0.7],
+                    ["My mapping rate is only 45%. What could be wrong?", "Bulk RNA-seq: Full DE Analysis Pipeline", 0.7],
+                    ["How do I choose between STAR and HISAT2?", "Bulk RNA-seq: Full DE Analysis Pipeline", 0.7],
+                    ["What parameters for GATK HaplotypeCaller on exome data?", "Exome Sequencing: Variant Calling Pipeline", 0.7],
+                    ["How do I set DADA2 truncation parameters?", "Microbiome: 16S Amplicon Analysis (QIIME2)", 0.7],
+                ]
+
                 gr.ChatInterface(
                     fn=workflow_respond,
                     type="messages",
@@ -994,14 +859,7 @@ def build_app():
                         gr.Slider(0.1, 1.5, 0.7, step=0.1, label="Temperature", visible=False),
                     ],
                     additional_inputs_accordion=gr.Accordion("⚙️", open=False, visible=False),
-                    examples=[
-                        "Walk me through the complete pipeline from raw FASTQ to DE results.",
-                        "I'm at alignment. What should I check before counting?",
-                        "My mapping rate is only 45%. What could be wrong?",
-                        "How do I choose between STAR and HISAT2?",
-                        "What parameters for GATK HaplotypeCaller on exome data?",
-                        "How do I set DADA2 truncation parameters?",
-                    ],
+                    examples=workflow_examples,
                 )
 
             # ══════════════════════════════════════════════════════════════
@@ -1012,21 +870,22 @@ def build_app():
 
                 output_format = gr.Radio(
                     choices=["Lesson Plan", "Slide Outline", "Study Notes", "Quiz Questions"],
-                    value="Lesson Plan",
-                    label="Output Format"
+                    value="Lesson Plan", label="Output Format"
                 )
 
+                # fn signature: (message, history, output_format, rag_state) → 2 additional inputs
+                paper_examples = [
+                    ["Convert this paper into a 45-minute lecture plan.", "Lesson Plan", DEFAULT_RAG_STATE],
+                    ["Create a slide outline covering the key methods.", "Slide Outline", DEFAULT_RAG_STATE],
+                    ["Generate study notes on the bioinformatics methods.", "Study Notes", DEFAULT_RAG_STATE],
+                    ["Create quiz questions on this paper's methodology.", "Quiz Questions", DEFAULT_RAG_STATE],
+                ]
+
                 gr.ChatInterface(
                     fn=paper_to_lesson_respond,
                     type="messages",
                     additional_inputs=[output_format, rag_store],
-                    additional_inputs_accordion=gr.Accordion("", open=False, visible=False),
-                    examples=[
-                        "Convert this paper into a 45-minute lecture plan.",
-                        "Create a slide outline covering the key methods.",
-                        "Generate study notes on the bioinformatics methods.",
-                        "Create quiz questions on this paper's methodology.",
-                    ],
+                    examples=paper_examples,
                 )
 
             # ══════════════════════════════════════════════════════════════
@@ -1037,28 +896,26 @@ def build_app():
 
                 with gr.Row():
                     viva_topic = gr.Dropdown(
-                        choices=TOPIC_CHOICES,
-                        label="Viva Topic",
-                        allow_custom_value=True,
-                        value="RNA-seq: Differential Expression (DESeq2)"
+                        choices=TOPIC_CHOICES, label="Viva Topic",
+                        allow_custom_value=True, value="RNA-seq: Differential Expression (DESeq2)"
                     )
                     viva_difficulty = gr.Radio(
-                        choices=DIFFICULTY_LEVELS,
-                        value="Intermediate",
-                        label="Difficulty"
+                        choices=DIFFICULTY_LEVELS, value="Intermediate", label="Difficulty"
                     )
 
+                # fn signature: (message, history, topic, difficulty) → 2 additional inputs
+                viva_examples = [
+                    ["I'm ready for my viva. Start with your first question.", "RNA-seq: Differential Expression (DESeq2)", "Intermediate"],
+                    ["Focus on the statistical aspects of RNA-seq.", "RNA-seq: Differential Expression (DESeq2)", "Intermediate"],
+                    ["Ask me about variant calling and interpretation.", "Variant Interpretation: ACMG Guidelines", "Intermediate"],
+                    ["Test my understanding of microbiome diversity.", "Microbiome: Alpha & Beta Diversity", "Intermediate"],
+                ]
+
                 gr.ChatInterface(
                     fn=viva_respond,
                     type="messages",
                     additional_inputs=[viva_topic, viva_difficulty],
-                    additional_inputs_accordion=gr.Accordion("⚙️", open=False, visible=False),
-                    examples=[
-                        "I'm ready for my viva. Start with your first question.",
-                        "Focus on the statistical aspects of RNA-seq.",
-                        "Ask me about variant calling and interpretation.",
-                        "Test my understanding of microbiome diversity.",
-                    ],
+                    examples=viva_examples,
                 )
 
         # ── Footer ─────────────────────────────────────────────────────
@@ -1073,14 +930,6 @@ def build_app():
     return demo
 
 
-# ============================================================================
-# LAUNCH
-# ============================================================================
-
 if __name__ == "__main__":
     demo = build_app()
-    demo.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=False,
-    )
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)