Update app.py

app.py

@@ -1,61 +1,44 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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("Futuresony/future_ai_12_10_2024.gguf")
 
+def format_alpaca_prompt(history, user_input, system_prompt):
+    """Formats input in Alpaca/LLaMA style with history"""
+    history_prompt = "\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in history])
+    prompt = f"""{system_prompt}
+
+{history_prompt}
+
+User: {user_input}
+Assistant:
+"""
+    return prompt
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    formatted_prompt = format_alpaca_prompt(history, message, system_message)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for user_message, assistant_message in history:
-        if user_message:
-            messages.append({"role": "user", "content": user_message})
-        if assistant_message:
-            messages.append({"role": "assistant", "content": assistant_message})
-
-    messages.append({"role": "user", "content": message})
-
-    response = client.chat_completion(
-        model='Futuresony/future_ai_12_10_2024.gguf',
-        messages=messages,
-        max_tokens=max_tokens,
+    response = client.text_generation(
+        formatted_prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-        stream=False
     )
 
-    return response["choices"][0]["message"]["content"]
-
+    # Extract only the response
+    cleaned_response = response.split("Assistant:")[-1].strip()
+    
+    yield cleaned_response  # Output only the answer
 
-"""
-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=1, maximum=250, value=128, 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()