app.py

import gradio as gr
from huggingface_hub import InferenceClient
import google.generativeai as genai
"""
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")


def respond(
    message,
    history: list[tuple[str, str]],
    image,
):
    # 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})
    print (message,image)
    ## for image
    if isinstance(image, np.ndarray):
            img = PIL.Image.fromarray(image)
    else:
        try:
            img = PIL.Image.open(image)
        except (AttributeError, IOError) as e:
            return f"Invalid image provided. Please provide a valid image file. Error: {e}"
    
    # Load model
    model = genai.GenerativeModel("gemini-pro-vision")
    ## for image
    response = model.generate_content([messages, img])
    print (response)
    return response
    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(
    respond,
    additional_inputs=[
        gr.Image(show_label=False)
    ],
    additional_inputs_accordion=gr.Accordion(open=True),
)


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