Update app.py

app.py

@@ -2,11 +2,11 @@ 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
+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("Mattimax/DATA-AI_Chat_3_0.5B")
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,30 +15,30 @@ def respond(
     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,
+    # Prepara il prompt basato sulla cronologia
+    prompt = system_message + "\n"
+    for user_msg, bot_msg in history:
+        prompt += f"User: {user_msg}\n"
+        if bot_msg:
+            prompt += f"Assistant: {bot_msg}\n"
+    
+    prompt += f"User: {message}\nAssistant:"
+    
+    # Invia la richiesta al modello usando text_generation
+    response = client.text_generation(
+        prompt=prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
+        stream=True,
+    )
+    
+    # Costruisce la risposta a partire dal generato
+    generated_text = ""
+    for chunk in response:
+        token = chunk.token.text if hasattr(chunk.token, 'text') else chunk.token
+        generated_text += token
+        yield generated_text
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -46,7 +46,10 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are DATA-AI, created by M.INC.. You are a helpful assistant. Respond in the user language. DO NOT REPEAT THINGS. DO NOT START TO LOOP THE MESSAGES.", label="System message"),
+        gr.Textbox(
+            value="You are DATA-AI, created by M.INC.. You are a helpful assistant. Respond in the user language. DO NOT REPEAT THINGS. DO NOT START TO LOOP THE MESSAGES.",
+            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(
@@ -59,6 +62,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()