Update app.py

app.py

@@ -1,28 +1,48 @@
 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("davnas/Italian_Cousine_2.1")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    # Crea un prompt concatenando i messaggi precedenti e l'input attuale
-    prompt = system_message + "\n"
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            prompt += f"User: {user_msg}\n"
-        if assistant_msg:
-            prompt += f"Assistant: {assistant_msg}\n"
-    prompt += f"User: {message}\nAssistant:"
-
-    # Usa text_generation invece di chat_completion
-    response_data = client.text_generation(prompt, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)
-    # response_data è una lista di completamenti, generalmente prendi il primo
-    if response_data and len(response_data) > 0 and "generated_text" in response_data[0]:
-        # Estrai solo il testo generato dopo 'Assistant:' per pulizia
-        response_text = response_data[0]["generated_text"].split("Assistant:", 1)[-1].strip()
-        return response_text
-    else:
-        return "Mi dispiace, non sono riuscito a generare una risposta."
 
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    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,
+    ):
+        token = message.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
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -39,5 +59,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()