app.py

"""import gradio as gr
from huggingface_hub import InferenceClient


client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    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]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


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()
"""

import os
import gradio as gr
from huggingface_hub import InferenceClient
import json

# Retrieve the API token from the environment variable
API_TOKEN = os.getenv("HF_READ_TOKEN")

# Initialize the Hugging Face Inference Client
client = InferenceClient(
    "mistralai/Mistral-Nemo-Instruct-2407",
    token=API_TOKEN
)

# System prompt to define model behavior
system_prompt = "You are a helpful assistant that provides concise and accurate answers."

# Function to handle the chat completion
def hf_chat(user_input):
    messages = [
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": user_input}
    ]
    response = ""
    
    try:
        # Stream the response
        for message in client.chat_completion(
            messages=messages,
            max_tokens=500,
            stream=True,
        ):
            try:
                # Parse each part of the response carefully
                content = message.choices[0].delta.content
                response += content
            except (KeyError, json.JSONDecodeError) as e:
                # Print error details for debugging
                print(f"Error while parsing response: {e}")
                continue  # Continue receiving the stream

    except Exception as e:
        # Catch and print any unexpected errors during the stream
        return f"Error occurred: {str(e)}"
    
    return response

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# mistral nemo prompt enhancer")
    with gr.Row():
        with gr.Column():
            user_input = gr.Textbox(
                label="Enter your message", 
                placeholder="Ask me anything..."
            )
            submit_btn = gr.Button("Submit")
        with gr.Column():
            output = gr.Textbox(label="Response")

    submit_btn.click(fn=hf_chat, inputs=user_input, outputs=output)

# Launch Gradio app
if __name__ == "__main__":
    demo.launch(show_api=True, share=False)