import gradio as gr
from huggingface_hub import InferenceClient
import os
#from transformers import AutoTokenizer, AutoModelForCausalLM
import requests

# ACCESS_TOKEN = os.getenv('ACCESS_TOKEN')
"""
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("meta-llama/Meta-Llama-3-8B-Instruct")



# tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b-storywriter", trust_remote_code=True)
# model = AutoModelForCausalLM.from_pretrained("mosaicml/mpt-7b-storywriter", trust_remote_code=True)


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

    ### doesn't work
    # input_ids = tokenizer.encode(message, return_tensors = 'pt')
    # for output in model.generate(input_ids, stream=True):
    #     output_text = tokenizer.decode(output, skip_special_tokens=True)
    #     yield output_text
    
    # API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
    # headers = {"Authorization": "Bearer "+os.environ['hf_token']}
    # response = requests.post(API_URL, headers=headers, json={"inputs":message})
    # data  = response.json()
    # returnval = ""
    # for item in data:
    #     returnval = returnval + item['generated_text']
    #     yield returnval



"""
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.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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