app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")

# <img src="/file=val_speaking_transparent.gif" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  ">
PLACEHOLDER = """
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
   
   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Hi Jennifer, welcome to DTF</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything about working at here...</p>
</div>. 
"""


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,
    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(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


# additional_inputs = [
#     gr.Slider(
#         label="Temperature",
#         value=0.9,
#         minimum=0.0,
#         maximum=1.0,
#         step=0.05,
#         interactive=True,
#         info="Higher values produce more diverse outputs",
#     ),
#     gr.Slider(
#         label="Max new tokens",
#         value=256,
#         minimum=0,
#         maximum=1048,
#         step=64,
#         interactive=True,
#         info="The maximum numbers of new tokens",
#     ),
#     gr.Slider(
#         label="Top-p (nucleus sampling)",
#         value=0.90,
#         minimum=0.0,
#         maximum=1,
#         step=0.05,
#         interactive=True,
#         info="Higher values sample more low-probability tokens",
#     ),
#     gr.Slider(
#         label="Repetition penalty",
#         value=1.2,
#         minimum=1.0,
#         maximum=2.0,
#         step=0.05,
#         interactive=True,
#         info="Penalize repeated tokens",
#     ),
# ]

with gr.Blocks(fill_height=True) as demo:

    gr.Image("/file=val_speaking_transparent.gif")
    gr.Markdown("Hi I'm Val the Voyager, welcome onboard!")
    gr.ChatInterface(
        fn=generate,
        chatbot=gr.Chatbot(
            show_label=False,
            show_share_button=False,
            show_copy_button=True,
            likeable=True,
            layout="panel",
            placeholder=PLACEHOLDER,
        ),
        # additional_inputs=additional_inputs,
        examples=[
            ["Ask me what an acronym stands for"],
            ["How can I check my leave allowance?"],
            ["Where can I find a floor map of 1 Macarthur?"],
            ["How can I find out about DTF's Disability network?"],
        ],
        cache_examples=False,
        title="""Voyager Val""",
    )

if __name__ == "__main__":
    demo.launch()