from omegaconf import OmegaConf
from query import VectaraQuery
import os

from PIL import Image
import gradio as gr
from huggingface_hub import InferenceClient

import logging
logging.basicConfig(level=logging.DEBUG)


# """
# 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]], system_message, max_tokens, temperature, top_p):
#     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})

#     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

def isTrue(x) -> bool:
    if isinstance(x, bool):
        return x
    return x.strip().lower() == 'true'

corpus_ids = str(os.environ['corpus_ids']).split(',')
cfg = OmegaConf.create({
    'customer_id': str(os.environ['customer_id']),
    'corpus_ids': corpus_ids,
    'api_key': str(os.environ['api_key']),
    'title': os.environ['title'],
    'description': os.environ['description'],
    'source_data_desc': os.environ['source_data_desc'],
    'streaming': isTrue(os.environ.get('streaming', False)),
    'prompt_name': os.environ.get('prompt_name', None)
})

cfg.description = f'''
                    <h4 style="text-align: center;">{cfg.description}</h4>
                  '''

vq = VectaraQuery(cfg.api_key, cfg.customer_id, cfg.corpus_ids, cfg.prompt_name)


def respond(message, history):
    if cfg.streaming:
        # Call stream response and stream output
        stream = vq.submit_query_streaming(message)

        outputs = ""
        for output in stream:
            outputs += output
            yield outputs
    else:
        logging.debug(f"Calling normal query with message: {message}")
        # Call non-stream response and return message output
        response = vq.submit_query(message)
        logging.debug(f"Chat response: {response}")
        return response

def random_fun(message, history):
    return message + '!'


demo = gr.ChatInterface(respond, title = cfg.title, description = cfg.description)

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
# demo = gr.ChatInterface(respond)


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