app.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
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("AuriLab/gpt-bi-instruct-cesar")


def respond(
    message,
    history: list[tuple[str, str]],
):
    messages = [{"role": "system", "content": "Gpt-Bi zara, AuriLabsek sortutako assitente digitala."}]

    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=60,
        stream=True,
        temperature=0.7,
        top_p=0.85,
    ):
        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(
    respond,
    title="GPT-BI Instruct",
)


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