Update app.py

app.py

@@ -1,30 +1,97 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from fastapi import FastAPI, HTTPException
 import os
 
-API_KEY = os.getenv("API_KEY", "your-secret-key-123")  # Set in Space Settings
+# Initialize clients
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+app = FastAPI()
 
-def predict(message, api_key):
-    if api_key != API_KEY:
-        return {"error": "Invalid API key"}
+# Configuration - Change this default key for production!
+DEFAULT_SYSTEM_MESSAGE = "You are a chatbot that helps in mood detection and recommends recipes"
+API_TOKEN = "default-secret-key"  # 👈 Change this for production deployments
+
+def generate_response(
+    message: str,
+    history: list[tuple[str, str]] = None,
+    system_message: str = DEFAULT_SYSTEM_MESSAGE,
+    max_tokens: int = 512,
+    temperature: float = 0.7,
+    top_p: float = 0.95
+):
+    """Core response generation logic"""
+    messages = [{"role": "system", "content": system_message}]
+
+    if history:
+        for user_msg, assistant_msg in history:
+            if user_msg:
+                messages.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                messages.append({"role": "assistant", "content": assistant_msg})
+
+    messages.append({"role": "user", "content": message})
+
+    try:
+        response = ""
+        for chunk in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            response += chunk.choices[0].delta.content or ""
+        return response
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# FastAPI Endpoints
+@app.post("/api/chat")
+async def api_chat_endpoint(
+    message: str,
+    api_token: str,
+    system_message: str = DEFAULT_SYSTEM_MESSAGE,
+    max_tokens: int = 512,
+    temperature: float = 0.7,
+    top_p: float = 0.95
+):
+    """External API endpoint"""
+    if api_token != API_TOKEN:
+        raise HTTPException(status_code=403, detail="Invalid API token")
     
-    response = client.chat_completion(
-        messages=[{"role": "user", "content": message}],
-        max_tokens=500
-    )
-    return {"response": response.choices[0].message.content}
-
-# Create Gradio interface
-with gr.Blocks() as demo:
-    with gr.Tab("API Endpoint"):
-        gr.Interface(
-            fn=predict,
-            inputs=[gr.Textbox(), gr.Textbox(type="password")],
-            outputs="json",
-            api_name="predict"  # This creates the /run/predict endpoint
+    return {
+        "response": generate_response(
+            message=message,
+            system_message=system_message,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p
         )
-    with gr.Tab("Chat UI"):
-        gr.ChatInterface(lambda msg: predict(msg, API_KEY)["response"])
+    }
+
+# Gradio Interface - Now includes API key validation
+def chat_ui(message: str, history: list[tuple[str, str]], api_key: str):
+    if api_key != API_TOKEN:
+        return "🔒 Error: Invalid API Key"
+    return generate_response(message, history)
+
+chat_interface = gr.ChatInterface(
+    fn=chat_ui,
+    additional_inputs=[
+        gr.Textbox(API_TOKEN, label="API Key", type="password"),
+        gr.Textbox(DEFAULT_SYSTEM_MESSAGE, label="System message"),
+        gr.Slider(1, 2048, 512, step=1, label="Max new tokens"),
+        gr.Slider(0.1, 4.0, 0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, 0.95, step=0.05, label="Top-p sampling"),
+    ],
+    title="🍳 Mood-Based Recipe Assistant",
+    description=f"API Key: {API_TOKEN}"  # Shows default key for testing
+)
+
+# Mount Gradio to FastAPI
+chat_interface.mount_to(app, path="/")
 
-demo.launch()
+if __name__ == "__main__":
+    import uvicorn
+    print(f"🔑 Default API Token: {API_TOKEN}")  # Visible in console
+    uvicorn.run(app, host="0.0.0.0", port=7860)