fix bug

app.py

@@ -1,93 +1,94 @@
-# import gradio as gr
-# from huggingface_hub import InferenceClient
+import os
+import gradio as gr
+from huggingface_hub import InferenceClient
 
-# """
-# 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("meta-llama/Meta-Llama-3-8B")
+"""
+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("meta-llama/Meta-Llama-3-8B",token=os.getenv('HF_API_TOKEN'))
 
-# ## None type 
-# def respond(
-#     message: str,
-#     history: list[tuple[str, str]],  # This will not be used
-#     system_message: str,
-#     max_tokens: int,
-#     temperature: float,
-#     top_p: float,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
+## None type 
+def respond(
+    message: str,
+    history: list[tuple[str, str]],  # This will not be used
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+):
+    messages = [{"role": "system", "content": system_message}]
     
-#     # Append only the latest user message
-#     messages.append({"role": "user", "content": message})
+    # Append only the latest user message
+    messages.append({"role": "user", "content": message})
 
-#     response = ""
+    response = ""
 
-#     try:
-#         # Generate response from the model
-#         for message in client.chat_completion(
-#             messages,
-#             max_tokens=max_tokens,
-#             stream=True,
-#             temperature=temperature,
-#             top_p=top_p,
-#         ):
-#             if message.choices[0].delta.content is not None:
-#                 token = message.choices[0].delta.content
-#                 response += token
-#             yield response
-#     except Exception as e:
-#         yield f"An error occurred: {e}"
+    try:
+        # Generate response from the model
+        for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            if message.choices[0].delta.content is not None:
+                token = message.choices[0].delta.content
+                response += token
+            yield response
+    except Exception as e:
+        yield f"An error occurred: {e}"
 
-# """
-# 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 Chatbot.", 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)",
-#         ),
-#     ],
-# )
+"""
+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 Chatbot.", 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)",
+        ),
+    ],
+)
 
-# if __name__ == "__main__":
-#     demo.launch()
+if __name__ == "__main__":
+    demo.launch()
 
 
-import os
-import gradio as gr
-from huggingface_hub import InferenceClient
+# import os
+# import gradio as gr
+# from huggingface_hub import InferenceClient
 
-# Initialize the Hugging Face Inference Client
-client = InferenceClient(
-    "meta-llama/Meta-Llama-3.1-8B-Instruct",
-    token=  os.getenv("HF_API_TOKEN"),# Replace with your actual token
-)
+# # Initialize the Hugging Face Inference Client
+# client = InferenceClient(
+#     "meta-llama/Meta-Llama-3.1-8B-Instruct",
+#     token=  os.getenv("HF_API_TOKEN"),# Replace with your actual token
+# )
 
-# Define a function to handle the chat input and get a response from the model
-def chat_with_model(user_input):
-    # Call the client to get the model's response
-    response = ""
-    for message in client.chat_completion(
-        messages=[{"role": "user", "content": user_input}],
-        max_tokens=500,
-        stream=True,
-    ):
-        response += message.choices[0].delta.content
-    return response
+# # Define a function to handle the chat input and get a response from the model
+# def chat_with_model(user_input):
+#     # Call the client to get the model's response
+#     response = ""
+#     for message in client.chat_completion(
+#         messages=[{"role": "user", "content": user_input}],
+#         max_tokens=500,
+#         stream=True,
+#     ):
+#         response += message.choices[0].delta.content
+#     return response
 
-# Create a Gradio interface with a chat component
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    with gr.Row():
-        txt = gr.Textbox(show_label=False, placeholder="Type your message here...")
-        txt.submit(chat_with_model, inputs=txt, outputs=chatbot)
+# # Create a Gradio interface with a chat component
+# with gr.Blocks() as demo:
+#     chatbot = gr.Chatbot()
+#     with gr.Row():
+#         txt = gr.Textbox(show_label=False, placeholder="Type your message here...")
+#         txt.submit(chat_with_model, inputs=txt, outputs=chatbot)
 
-demo.launch()
+# demo.launch()