app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient(
    "mistralai/Mixtral-8x7B-Instruct-v0.1"
)

def format_prompt(message, history):
    prompt = "<s>"
    for user_prompt, bot_response in history:
        prompt += f"[INST] {user_prompt} [/INST]"
        prompt += f" {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    return prompt

def generate_from_file(file_path, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
    # Read the file content
    with open(file_path, 'r', encoding='utf-8') as file:
        file_content = file.read()
    
    # You might need to modify this part to fit how you want to use the file content in your prompt
    prompt = file_content[:1000]  # Example: using first 1000 characters of the file content
    
    return generate(prompt, history, system_prompt, temperature, max_new_tokens, top_p, repetition_penalty)

def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output

iface = gr.Interface(
    fn=generate_from_file,
    inputs=[gr.File(label="Upload File"), gr.State(), gr.Textbox(label="System Prompt")],
    outputs="text",
    title="SRT File Translation",
    concurrency_limit=20,
)

iface.launch()