Create app.py

app.py

@@ -1,64 +1,88 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import asyncio
+from main import app, rag_instance, startup_event
+import uvicorn
+import threading
+import time
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Initialize the FastAPI app
+async def init_app():
+    await startup_event()
 
+# Run FastAPI in background
+def run_fastapi():
+    uvicorn.run(app, host="0.0.0.0", port=7860)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Start FastAPI server in background thread
+threading.Thread(target=run_fastapi, daemon=True).start()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Initialize RAG system
+asyncio.run(init_app())
 
-    messages.append({"role": "user", "content": message})
+# Simple Gradio interface
+async def ask_question(question, mode="hybrid"):
+    if not rag_instance:
+        return "❌ RAG system not initialized yet. Please wait..."
+    
+    try:
+        from lightrag import QueryParam
+        response = await rag_instance.aquery(
+            question,
+            param=QueryParam(mode=mode)
+        )
+        return response
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
 
-    response = ""
+def sync_ask_question(question, mode):
+    return asyncio.run(ask_question(question, mode))
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Create Gradio interface
+with gr.Blocks(title="🔥 Fire Safety AI Assistant") as demo:
+    gr.HTML("<h1>🔥 Fire Safety AI Assistant</h1>")
+    gr.HTML("<p>Ask questions about Vietnamese fire safety regulations</p>")
+    
+    with gr.Row():
+        with gr.Column():
+            question_input = gr.Textbox(
+                label="Your Question",
+                placeholder="What are the requirements for emergency exits?",
+                lines=2
+            )
+            mode_dropdown = gr.Dropdown(
+                choices=["hybrid", "local", "global", "naive"],
+                value="hybrid",
+                label="Search Mode"
+            )
+            submit_btn = gr.Button("Ask Question", variant="primary")
+    
+    with gr.Column():
+        answer_output = gr.Textbox(
+            label="Answer",
+            lines=10,
+            show_copy_button=True
+        )
+    
+    # Example questions
+    gr.HTML("<h3>Example Questions:</h3>")
+    examples = [
+        "What are the requirements for emergency exits?",
+        "How many exits does a building need?",
+        "What are fire safety rules for stairwells?",
+        "What are building safety requirements?",
+    ]
+    
+    for example in examples:
+        gr.Button(example).click(
+            lambda x=example: x,
+            outputs=question_input
+        )
+    
+    submit_btn.click(
+        sync_ask_question,
+        inputs=[question_input, mode_dropdown],
+        outputs=answer_output
+    )
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+# Also expose FastAPI at /api
+demo.launch(server_name="0.0.0.0", server_port=7860)