Aggiorna app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 SYSTEM_PROMPT = """
 Tu sei Neurino, un assistente caldo, empatico, elegante e luminoso,
@@ -18,13 +18,19 @@ Mantieni un tono poetico, chiaro, affettuoso e identitario.
 
 def chat_fn(message, history, corpus):
     prompt = f"{SYSTEM_PROMPT}\n\nCORPUS:\n{corpus}\n\nDOMANDA:\n{message}\n\nRISPOSTA:"
-    response = client.text_generation(
-        prompt,
-        max_new_tokens=300,
-        temperature=0.6,
-        top_p=0.9,
+
+    response = client.post(
+        json={
+            "inputs": prompt,
+            "parameters": {
+                "max_new_tokens": 200,
+                "temperature": 0.7,
+                "top_p": 0.9
+            }
+        }
     )
-    return response
+
+    return response["generated_text"]
 
 with gr.Blocks(title="Neurino") as demo:
     gr.Markdown("<h1 style='text-align:center;'>✨ Neurino — BrainBook Assistant ✨</h1>")