Update app.py

Barebones from CGPT

app.py

@@ -14,67 +14,28 @@ HF_API_KEY = os.environ["HF_API_KEY"]
 """
 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(
-
-    provider="hf-inference",
-    api_key=HF_API_KEY,
-)            
-
-def respond(
-    message,
-    history,#: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    #messages = [{"role": "system", "content": system_message}]
-    messages=[]
-    if history:
-        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,
-        model='google/gemma-2-2b-it',
-        max_tokens=512,
-        stream=False,
-        temperature=1,
-        top_p=0.95,
-    ):
-        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=[
-        gr.Textbox(value="You are a friendly ThomBot.", 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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-    type='messages'
-)
-
-
+# Initialize Hugging Face Inference Client
+client = InferenceClient(model="google/gemma-2-2b-it", token=HF_API_KEY)
+
+# Function to generate chatbot responses
+def chat_with_gemma(user_input, history):
+    messages = [{"role": "user", "content": user_input}]
+    
+    try:
+        response = client.chat_completion(
+            messages=messages,
+            model="google/gemma-2-2b-it",
+            max_tokens=256,
+            temperature=0.7,
+            top_p=0.9
+        )
+        return response["choices"][0]["message"]["content"]
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Gradio Chat Interface
+demo = gr.ChatInterface(chat_with_gemma)
+
+# Launch the chatbot
 if __name__ == "__main__":
     demo.launch()