use chat completion

app.py

@@ -65,15 +65,16 @@ def format_messages(user_text: str, level: int) -> t.Mapping[str, str]:
 
 
 def simplify_text(user_text: str, level: int) -> str:
-    client = InferenceClient(token=HF_API_TOKEN)
+    client = InferenceClient(model=MODEL_REPO_ID, token=HF_API_TOKEN)
     messages = format_messages(user_text, level)
 
-    response = client.text_generation(
-        model=MODEL_REPO_ID,
-        inputs={"messages": messages},
-        parameters={"max_new_tokens": 512, "temperature": 0.7, "top_p": 0.9},
-    )
-    return response
+    response = client.chat_completion(messages, max_tokens=512)
+    if response is not None and response.choices is not None:
+        content = response.choices[0].message.content
+        return content
+    else:
+        return "Error: No valid response generated."
+
 
 
 with gr.Blocks() as demo: