import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread
def generate_prompt(example: dict) -> str:
    """Generates a standardized message to prompt the model with an instruction, optional input and a
    'response' field."""

    if example["input"]:
        return (
            "Below is an instruction that describes a task, paired with an input that provides further context. "
            "Write a response that appropriately completes the request.\n\n"
            f"### Instruction:\n{example['instruction']}\n\n### Input:\n{example['input']}\n\n### Response:"
        )
    return (
        "Below is an instruction that describes a task. "
        "Write a response that appropriately completes the request.\n\n"
        f"### Instruction:\n{example['instruction']}\n\n### Response:"
    )
tokenizer = AutoTokenizer.from_pretrained("mehrdad-es/legalLLM-hf")
model = AutoModelForCausalLM.from_pretrained("mehrdad-es/legalLLM-hf", torch_dtype=torch.float16)
model = model.to('cuda:0')

class StopOnTokens(StoppingCriteria):
    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
        stop_ids = [30, 0]
        for stop_id in stop_ids:
            if input_ids[0][-1] == stop_id:
                return True
        return False

def predict(message, history):
    prompt,userInput = message.split('!!')
    message=generate_prompt({"instruction": prompt, "input": userInput})
    history_transformer_format = history + [[message, ""]]
    stop = StopOnTokens()

    messages = "".join(["".join(["\n<USER>:"+item[0], "\n<ASSISTANT>:"+item[1]])  #curr_system_message +
                for item in history_transformer_format])

    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
    generate_kwargs = dict(
        model_inputs,
        streamer=streamer,
        max_new_tokens=400,
        do_sample=True,
        top_p=0.85,
        top_k=500,
        temperature=0.1,
        num_beams=1,
        stopping_criteria=StoppingCriteriaList([stop])
        )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    partial_message  = ""
    for new_token in streamer:
        if new_token != '<':
            partial_message += new_token
            yield partial_message


gr.ChatInterface(predict).queue().launch()