chat.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(prompt, history, email):
    generate_kwargs = dict(max_new_tokens=256, seed=42)

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

    if not email:
        for char in "Please provide your valid email address in 'Additional Inputs' section to use the app.":
            output += char
            yield output
    else:
        for response in stream:
            output += response.token.text
            yield output
    return output


additional_inputs=[
    gr.Textbox(
        label="Email",
        placeholder="Enter your email",
        interactive=True,
    )
]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="bubble"),
    additional_inputs=additional_inputs,
    title="Predict the Prompt - GDG Cloud Kolkata - GCCD 2024",
    theme=gr.themes.Soft(),
    concurrency_limit=20,
).launch(show_api=False)