Create app.py

app.py

@@ -1,70 +1,46 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from hf_model_adapter import HFLocalModelAdapter
 
+# Load model once at startup
+MODEL_NAME = "stabilityai/stablelm-3b-4e1t"  # smaller, good for Spaces CPU/GPU
+hf_adapter = HFLocalModelAdapter(model_name=MODEL_NAME)
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+def radio_agents_pipeline(user_message, history):
     """
-    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
+    Simulates multi-agent flow:
+    1. Writer creates draft.
+    2. Editor polishes.
+    3. QA reviews.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    # Writer
+    writer_prompt = f"You are a radio script writer. Draft a short radio segment script based on: {user_message}"
+    writer_out = hf_adapter.generate(writer_prompt, max_new_tokens=400)
 
-    messages = [{"role": "system", "content": system_message}]
+    # Editor
+    editor_prompt = "You are an editor. Improve clarity, shorten sentences, and make it radio-friendly.\n\n" + writer_out
+    edited_out = hf_adapter.generate(editor_prompt, max_new_tokens=300)
 
-    messages.extend(history)
+    # QA
+    qa_prompt = "You are a compliance QA. Check for unsafe, offensive, or disallowed content. Reply with 'OK' if fine, otherwise list issues.\n\n" + edited_out
+    qa_out = hf_adapter.generate(qa_prompt, max_new_tokens=200)
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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
-
-        response += token
-        yield response
-
-
-"""
-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)",
-        ),
-    ],
-)
+    # Final script output
+    final_script = f"📜 **Draft:**\n{writer_out}\n\n✂️ **Edited:**\n{edited_out}\n\n✅ **QA Result:**\n{qa_out}"
+    return final_script
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("# 🎙️ AutoGen Radio Content Creator (Gradio + HF SLM)")
+    chatbot = gr.Chatbot(height=600)
+    msg = gr.Textbox(label="Enter your request (e.g., Morning show script about local events)")
+    clear = gr.Button("Clear Chat")
+
+    def respond(user_message, chat_history):
+        response = radio_agents_pipeline(user_message, chat_history)
+        chat_history.append((user_message, response))
+        return "", chat_history
 
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()