Update app.py

app.py

@@ -13,12 +13,12 @@ from fastapi import FastAPI, HTTPException
 from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from typing import List, Optional, AsyncGenerator  # ✅ AsyncGenerator import
+from typing import List, Optional, AsyncGenerator
 import asyncio
 import gradio as gr
 
 # ==============================================================================
-# Model Architecture
+# Model Architecture (Same as before)
 # ==============================================================================
 
 @keras.saving.register_keras_serializable()
@@ -274,7 +274,7 @@ class KerasBackend(ModelBackend):
 CONFIG_TOKENIZER_REPO_ID = "Smilyai-labs/Sam-1-large-it-0002"
 
 print("="*60)
-print("🚀 SAM-X-1 Hybrid API + UI Loading...".center(60))
+print("🚀 SAM-X-1 API Server Loading...".center(60))
 print("="*60)
 
 # Download config/tokenizer
@@ -394,19 +394,6 @@ async def generate_stream(prompt: str, backend, temperature: float) -> AsyncGene
             yield new_chunk
 
 
-# ==============================================================================
-# Gradio Chat Function
-# ==============================================================================
-
-def chat_fn(message, history, model_choice="SAM-X-1-Large", temperature=0.7):
-    backend = available_models[model_choice]
-    prompt = f"User: {message}\nSam:    <think>"
-    response = ""
-    for chunk in generate_stream(prompt, backend, temperature):
-        response += chunk
-        yield response
-
-
 # ==============================================================================
 # FastAPI Endpoints (OpenAI-style)
 # ==============================================================================
@@ -484,29 +471,33 @@ async def list_models():
 
 
 # ==============================================================================
-# Gradio UI
+# Simple Gradio API Info Page (Replaces Chat UI)
 # ==============================================================================
 
-with gr.Blocks(title="SAM-X-1 Chat", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🤖 SAM-X-1 Multi-Model Chat")
-    
-    with gr.Row():
-        with gr.Column(scale=4):
-            chat = gr.ChatInterface(
-                fn=chat_fn,
-                additional_inputs=[
-                    gr.Dropdown(
-                        choices=list(available_models.keys()),
-                        value=list(available_models.keys())[0],
-                        label="Model"
-                    ),
-                    gr.Slider(0.0, 2.0, value=0.7, label="Temperature")
-                ],
-                examples=[
-                    "Explain quantum computing like I'm 5.",
-                    "Write a haiku about a robot learning to dream."
-                ]
-            )
-
-# Mount Gradio app on root path
-app = gr.mount_gradio_app(app, demo, path="/")
+def get_api_info():
+    model_info = "\n".join([f"- {name}" for name in available_models.keys()])
+    return f"""
+# 🤖 SAM-X-1 AI API Server
+
+This is a production-grade API server for the SAM-X-1 family of models.
+
+## 🚀 Available Models:
+{model_info}
+
+## 🔌 API Endpoints:
+- `POST /v1/chat/completions` - Chat completions (OpenAI-style)
+- `GET /v1/models` - List available models
+
+## 🌊 Streaming:
+Set `"stream": true` in your request to receive real-time token-by-token responses.
+
+## 🧪 Example Request:
+```json
+{{
+  "model": "SAM-X-1-Large",
+  "messages": [
+    {{"role": "user", "content": "Hello!"}}
+  ],
+  "stream": true,
+  "temperature": 0.7
+}}