Update app.py

app.py

@@ -1,24 +1,17 @@
-
 !pip install huggingface_hub
 !pip install transformers
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import pipeline
 
+system_message = "You are a friendly chatbot."
 
-from transformers import pipeline
+def respond(message, history=None, system_message=system_message, max_tokens=512, temperature=0.7, top_p=0.95):
+    if history is None:
+        history = []
+    if isinstance(history, str):
+        history = json.loads(history)
 
-messages = [
-    {"role": "user", "content": "Who are you?"},
-]
-pipe = pipeline("text-generation", model="ibm-granite/granite-8b-code-instruct")
-pipe(messages)
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -31,21 +24,19 @@ pipe(messages)
 
     response = ""
 
+    client = InferenceClient(pipeline("text-generation", model="ibm-granite/granite-8b-code-instruct"))
+
     for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
+            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=[
@@ -62,6 +53,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()