Update app.py

Solve runtime error

app.py

@@ -2,14 +2,7 @@
 app.py
 ──────
 Gradio UI — the entry point for Hugging Face Spaces.
-
-This module ONLY handles UI concerns:
-  - Layout and theming
-  - Wiring user inputs to the RAG pipeline
-  - Displaying answers and source citations
-  - Error handling / friendly messages
-
-It delegates ALL logic to rag_pipeline.py.
+Delegates ALL logic to rag_pipeline.py.
 """
 
 import logging
@@ -20,9 +13,8 @@ from config import cfg
 from rag_pipeline import RAGPipeline, build_pipeline
 
 # ── Gradio version guard ──────────────────────────────────────────────────────
-# Detect which optional Chatbot kwargs are available in the installed version.
 import inspect as _inspect
-_chatbot_params = set(_inspect.signature(gr.Chatbot.__init__).parameters)
+_chatbot_params  = set(_inspect.signature(gr.Chatbot.__init__).parameters)
 _SUPPORTS_COPY   = "show_copy_button"  in _chatbot_params
 _SUPPORTS_BUBBLE = "bubble_full_width" in _chatbot_params
 
@@ -45,34 +37,111 @@ except Exception as exc:
     logger.exception("Pipeline initialisation failed: %s", exc)
 
 
-# ── Chat handler ──────────────────────────────────────────────────────────────
+# ── Helpers ───────────────────────────────────────────────────────────────────
 
 def _msg(role: str, content: str) -> dict:
     """Return a Gradio-compatible message dict."""
     return {"role": role, "content": content}
 
 
-def chat(user_message: str, history: list, show_sources: bool):
+def _handle_debug_command(command: str) -> str:
     """
-    Called by Gradio on every user message.
-
-    Parameters
-    ----------
-    user_message : str
-    history : list
-        Gradio chat history — list of {"role": ..., "content": ...} dicts.
-    show_sources : bool
-        Whether to append source citations below the answer.
-
-    Returns
-    -------
-    tuple[str, list, str]
-        (cleared input, updated history, sources markdown)
+    Handle special slash commands for in-chat debugging.
+    No terminal needed — results appear directly in the chat.
     """
+    from data_loader import get_dataset_info
+    import vector_store as vs_module
+
+    cmd = command.strip().lower()
+
+    # ── /debug — show dataset info ────────────────────────────────────────────
+    if cmd == "/debug":
+        info = get_dataset_info()
+        if info["status"] == "error":
+            return f"❌ **Dataset error:**\n```\n{info['error']}\n```"
+        lines = [
+            "### 🔍 Dataset Debug Info",
+            f"**Dataset:** `{info['dataset']}`",
+            f"**Total rows:** {info['total_rows']}",
+            f"**All columns:** `{info['columns']}`",
+            f"**Detected text column:** `{info['detected_text_col']}`",
+            f"**Non-empty rows:** {info['non_empty_rows']}",
+            "",
+            "**Sample text from row 0:**",
+            f"```\n{info['sample_text']}\n```",
+            "",
+        ]
+        if info["detected_text_col"] not in ["text", "content", "body", "page_content", "extracted_text"]:
+            lines.append(
+                f"⚠️ **Column `{info['detected_text_col']}` is not a standard name.**\n"
+                "Add it to `text_column_candidates` in `config.py`."
+            )
+        lines.append(
+            "❌ **No usable text rows found.**" if info["non_empty_rows"] == 0
+            else "✅ Dataset looks healthy."
+        )
+        return "\n".join(lines)
+
+    # ── /retrieve <query> — show raw retrieval results ────────────────────────
+    if cmd.startswith("/retrieve "):
+        test_query = command[len("/retrieve "):].strip()
+        if not test_query:
+            return "Usage: `/retrieve your test query here`"
+        if pipeline is None:
+            return "❌ Pipeline not initialised."
+        docs = vs_module.retrieve(pipeline._index, test_query, k=5)
+        if not docs:
+            return (
+                f"❌ **No chunks retrieved** for: `{test_query}`\n"
+                "FAISS index may be empty or text column is wrong."
+            )
+        lines = [f"### 📄 Retrieved {len(docs)} chunks for: `{test_query}`\n"]
+        for i, doc in enumerate(docs, 1):
+            src = doc.metadata.get("source", doc.metadata.get("source_row", "?"))
+            lines.append(f"**Chunk {i}** (source: {src})")
+            lines.append(f"```\n{doc.page_content[:300]}\n```")
+        return "\n".join(lines)
+
+    # ── /status — pipeline health ─────────────────────────────────────────────
+    if cmd == "/status":
+        if init_error:
+            return f"❌ **Pipeline failed:**\n```\n{init_error}\n```"
+        if pipeline is None:
+            return "❌ Pipeline is None — startup may still be in progress."
+        total_vectors = pipeline._index.index.ntotal
+        lines = [
+            "### ✅ Pipeline Status",
+            f"**FAISS vectors:** {total_vectors}",
+            f"**Groq model:** `{cfg.groq_model}`",
+            f"**Dataset:** `{cfg.hf_dataset}`",
+            f"**Chunk size:** {cfg.chunk_size} | **Top-K:** {cfg.top_k}",
+            (
+                "\n❌ **0 vectors — retrieval will always fail!**"
+                if total_vectors == 0
+                else "\n✅ Index looks healthy."
+            ),
+        ]
+        return "\n".join(lines)
+
+    return (
+        "**Debug commands:**\n"
+        "- `/debug` — dataset columns, row count, sample text\n"
+        "- `/status` — pipeline health and vector count\n"
+        "- `/retrieve your question` — raw retrieval results"
+    )
+
+
+def chat(user_message: str, history: list, show_sources: bool):
+    """Called by Gradio on every user message."""
+
+    # ── Handle debug slash commands first ─────────────────────────────────────
+    if user_message.strip().startswith("/"):
+        bot_reply = _handle_debug_command(user_message)
+        return "", history + [_msg("user", user_message), _msg("assistant", bot_reply)], ""
+
     if init_error:
-        bot_reply = f"⚠️ **Setup error:** {init_error}\n\nPlease check your Space secrets and logs."
-        history = history + [_msg("user", user_message), _msg("assistant", bot_reply)]
-        return "", history, ""
+        bot_reply = f"⚠️ **Setup error:** {init_error}\n\nCheck Space secrets and logs."
+        return "", history + [_msg("user", user_message), _msg("assistant", bot_reply)], ""
 
     if not user_message.strip():
         return "", history, ""
@@ -86,21 +155,15 @@ def chat(user_message: str, history: list, show_sources: bool):
         bot_reply  = "🔭 Something went wrong while consulting the stars. Please try again."
         sources_md = ""
 
-    history = history + [_msg("user", user_message), _msg("assistant", bot_reply)]
-    return "", history, sources_md
+    return "", history + [_msg("user", user_message), _msg("assistant", bot_reply)], sources_md
 
 
 # ── Gradio UI ─────────────────────────────────────────────────────────────────
 
 CSS = """
-/* AstroBot custom styles */
 body, .gradio-container { font-family: 'Georgia', serif; }
 .title-banner { text-align: center; padding: 1rem 0 0.5rem; }
 .title-banner h1 { font-size: 2rem; letter-spacing: 0.04em; }
-.disclaimer {
-    background: #1a1a2e; color: #a0aec0; border-radius: 8px;
-    padding: 0.6rem 1rem; font-size: 0.82rem; margin-bottom: 0.5rem;
-}
 .sources-box { font-size: 0.82rem; color: #718096; }
 footer { display: none !important; }
 """
@@ -116,34 +179,25 @@ EXAMPLE_QUESTIONS = [
     "How does the Moon sign influence emotions?",
 ]
 
-# ── Gradio version-safe theme ─────────────────────────────────────────────────
 _SUPPORTS_THEMES = hasattr(gr, "themes") and hasattr(gr.themes, "Base")
 _theme = gr.themes.Base(
-    primary_hue="indigo",
-    secondary_hue="purple",
-    neutral_hue="slate",
+    primary_hue="indigo", secondary_hue="purple", neutral_hue="slate",
 ) if _SUPPORTS_THEMES else None
 
-with gr.Blocks(
-    title=cfg.app_title,
-    theme=_theme,
-    css=CSS,
-) as demo:
+with gr.Blocks(title=cfg.app_title, theme=_theme, css=CSS) as demo:
 
     # ── Header ────────────────────────────────────────────────────────────────
-    gr.HTML(
-        """
+    gr.HTML("""
         <div class="title-banner">
             <h1>🔭 AstroBot Demo</h1>
             <p style="color:#9b8ec4; font-size:1.05rem;">
                 Your AI Astrology Assistant · Powered by Groq LLaMA-3.1-8b-instant
             </p>
         </div>
-        """
-    )
+    """)
 
-    gr.HTML(
-        """
+    # ── Disclaimer — fully inline styles for reliability ──────────────────────
+    gr.HTML("""
         <div style="background-color:#3b3777; color:#f0eeff; border:1px solid #6c67c4;
                     border-radius:8px; padding:10px 16px; font-size:0.92rem;
                     margin-bottom:8px; line-height:1.6;">
@@ -152,20 +206,17 @@ with gr.Blocks(
             It does <strong style="color:#ffffff;">not</strong> make personal predictions
             or interpret individual birth charts.
         </div>
-        """
-    )
+    """)
 
     # ── Main layout ────────��──────────────────────────────────────────────────
     with gr.Row():
         with gr.Column(scale=3):
             _chatbot_kwargs = {"label": "AstroBot", "height": 500}
-            if _SUPPORTS_BUBBLE:
-                _chatbot_kwargs["bubble_full_width"] = False
-            if _SUPPORTS_COPY:
-                _chatbot_kwargs["show_copy_button"] = True
-            if "type" in _chatbot_params:
-                _chatbot_kwargs["type"] = "messages"   # role/content dict format
+            if _SUPPORTS_BUBBLE: _chatbot_kwargs["bubble_full_width"] = False
+            if _SUPPORTS_COPY:   _chatbot_kwargs["show_copy_button"]  = True
+            if "type" in _chatbot_params: _chatbot_kwargs["type"] = "messages"
             chatbot = gr.Chatbot(**_chatbot_kwargs)
+
             with gr.Row():
                 txt_input = gr.Textbox(
                     placeholder="Ask a concept question about astrology…",
@@ -176,31 +227,29 @@ with gr.Blocks(
 
         with gr.Column(scale=1):
             gr.Markdown("### ⚙️ Options")
-            _checkbox_kwargs = {
-                "label": "Show source excerpts",
-                "value": False,
-            }
+            _checkbox_kwargs = {"label": "Show source excerpts", "value": False}
             _checkbox_params = set(_inspect.signature(gr.Checkbox.__init__).parameters)
             if "info" in _checkbox_params:
-                _checkbox_kwargs["info"] = "Display the course material passages used to answer."
+                _checkbox_kwargs["info"] = "Display course material passages used to answer."
             show_sources = gr.Checkbox(**_checkbox_kwargs)
+
             gr.Markdown("### 💡 Example Questions")
             for q in EXAMPLE_QUESTIONS:
-                gr.Button(q, size="sm").click(
-                    fn=lambda x=q: x, outputs=txt_input
-                )
+                gr.Button(q, size="sm").click(fn=lambda x=q: x, outputs=txt_input)
+
+            gr.Markdown(
+                "---\n🛠️ **Debug commands:**\n"
+                "`/status` · `/debug` · `/retrieve <query>`"
+            )
 
     # ── Source citations panel ────────────────────────────────────────────────
     sources_display = gr.Markdown(
-        value="",
-        label="Source Excerpts",
-        elem_classes=["sources-box"],
+        value="", label="Source Excerpts", elem_classes=["sources-box"]
     )
 
-    # ── State ────────────────────────────────────────────────────────────────
+    # ── State & event wiring ──────────────────────────────────────────────────
     state = gr.State([])
 
-    # ── Event wiring ──────────────────────────────────────────────────────────
     send_btn.click(
         fn=chat,
         inputs=[txt_input, state, show_sources],
@@ -212,13 +261,11 @@ with gr.Blocks(
         outputs=[txt_input, chatbot, sources_display],
     )
 
-    # ── Footer ────────────────────────────────────────────────────────────────
     gr.Markdown(
         "_Built with [Groq](https://groq.com) · [LangChain](https://langchain.com) · "
         "[Hugging Face](https://huggingface.co) — for astrology students everywhere 🌙_"
     )
 
 
-# ── Entry point ───────────────────────────────────────────────────────────────
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)