Update app.py

app.py

@@ -2,14 +2,14 @@ import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Load HF Token from environment variables
 hf_token = os.getenv("HF_TOKEN")
 if not hf_token:
     raise ValueError("HF_TOKEN is not set in environment variables!")
 
-# Initialize InferenceClient
+
 client = InferenceClient(model="huihui-ai/Llama-3.3-70B-Instruct-abliterated", token=hf_token)
 
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -21,33 +21,36 @@ def respond(
     # Prepare messages for the API
     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]})
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
 
     messages.append({"role": "user", "content": message})
 
     response = ""
 
     try:
-        # Use 'messages' instead of 'inputs'
-        for message in client.chat_completion(
+        # Call the chat_completion method with the correct parameters
+        completion = client.chat_completion(
             model="huihui-ai/Llama-3.3-70B-Instruct-abliterated",
-            messages=messages,  # Correct argument
-            parameters={
-                "max_tokens": max_tokens,
-                "temperature": temperature,
-                "top_p": top_p,
-            },
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
             stream=True,
-        ):
+        )
+
+        # Handle streaming responses
+        for message in completion:
             token = message.choices[0].delta.content
             response += token
             yield response
+
     except Exception as e:
-        yield f"Error: {str(e)}" 
+        yield f"Error: {str(e)}"
+
 
 demo = gr.ChatInterface(
     respond,