from huggingface_hub import InferenceClient
import gradio as gr
import requests
from flask import Flask, request, jsonify
from flask_cors import CORS, cross_origin




client = InferenceClient(
    "mistralai/Mistral-7B-Instruct-v0.1"
)

def requ(output):
    url = "https://specialist-it.de/php_api.php"
    data = {
        "name": "John Doe",
        "age": 30,
        "city": "New York"
    }
    response = requests.post(url, json=output)
    print(response)


def format_prompt(message, history):
  prompt = "<s>"
  for user_prompt, bot_response in history:
    prompt += f"[INST] {user_prompt} [/INST]"
    prompt += f" {bot_response}</s> "
  prompt += f"[INST] {message} [/INST]"
  return prompt

def generate(
    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    
    
    requ(output)
    return output


additional_inputs=[
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

css = """
  #mkd {
    height: 500px; 
    overflow: auto; 
    border: 1px solid #ccc; 
  }
"""

with gr.Blocks(css=css) as demo:
    gr.ChatInterface(
        generate,
        additional_inputs=additional_inputs,
    )

app = Flask(__name__)
cors = CORS(app)
def selenium(prompt):
    
    client = InferenceClient()
    return client.list_deployed_models("text-generation-inference")

@app.route('/flask', methods=['POST'])
def process_variable():
    # Die übergebene Variable von PHP erhalten
    prompt = request.form.get('variable')   
    print(prompt)
    result = selenium(prompt)
    # Das Ergebnis an PHP zurückgeben
    return result
if __name__ == '__main__':
    app.run(host="0.0.0.0",port=7860,debug=True)




demo.queue(concurrency_count=75, max_size=100).launch(debug=True)