Update app.py

app.py

@@ -1,70 +1,47 @@
+"""
+Hugging Face Spaces compatible app
+"""
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from main import app as fastapi_app
 
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+# Gradio wrapper cho Hugging Face Spaces
+def create_gradio_interface():
     """
-    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
+    Tạo Gradio interface để deploy trên Hugging Face Spaces
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
+    with gr.Blocks(title="Event Social Media Embeddings API") as demo:
+        gr.Markdown("""
+        # 🔍 Event Social Media Embeddings API
 
-    messages.extend(history)
+        API để embeddings và search multimodal (text + images) với **Jina CLIP v2** + **Qdrant Cloud**
 
-    messages.append({"role": "user", "content": message})
+        ## 🌟 Features:
+        - ✅ Multimodal: Text + Image embeddings
+        - ✅ Tiếng Việt: 100% support
+        - ✅ High Performance: ONNX + HNSW
+        - ✅ Cloud: Qdrant Cloud
 
-    response = ""
+        ## 📡 API Endpoints:
+        - `POST /index` - Index data
+        - `POST /search` - Hybrid search
+        - `POST /search/text` - Text search
+        - `POST /search/image` - Image search
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        ### 🔗 API Docs:
+        Truy cập `/docs` để xem API documentation đầy đủ
+        """)
 
-        response += token
-        yield response
+        gr.Markdown("### API is running at the `/docs` endpoint")
 
+    return demo
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# Mount FastAPI app
+demo = create_gradio_interface()
 
+# Wrap FastAPI với Gradio
+app = gr.mount_gradio_app(fastapi_app, demo, path="/")
 
 if __name__ == "__main__":
-    demo.launch()
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)