app.py

import gradio as gr
from huggingface_hub import InferenceClient

import os 
import time 
import asyncio

from pipeline import PromptEnhancer

"""
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("HuggingFaceH4/zephyr-7b-beta")


async def advancedPromptPipeline(InputPrompt):
    
    model="gpt-4o-mini"
    
    if model == "gpt-4o":
        i_cost=5/10**6
        o_cost=15/10**6
    elif model == "gpt-4o-mini":
        i_cost=0.15/10**6
        o_cost=0.6/10**6
    
    enhancer = PromptEnhancer(model)
    
    start_time = time.time()
    advanced_prompt = await enhancer.enhance_prompt(input_prompt, perform_eval=False)
    elapsed_time = time.time() - start_time
    
    yield {
        "model": model,
        "elapsed_time": elapsed_time,
        "prompt_tokens": enhancer.prompt_tokens,
        "completion_tokens": enhancer.completion_tokens,
        "approximate_cost": (enhancer.prompt_tokens*i_cost)+(enhancer.completion_tokens*o_cost),
        "inout_prompt": input_prompt,
        "advanced_prompt": advanced_prompt["advanced_prompt"],
    }


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

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    advancedPromptPipeline,
    #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()