app.py

from huggingface_hub import InferenceClient
import gradio as gr
import requests
import json

client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

def google_search(query, **kwargs):
    api_key = 'AIzaSyDseKKQCAUBmPidu_QapnpJCGLueDWYJbE'
    cse_id = '001ae9bf840514e61'
    
    service_url = 'https://www.googleapis.com/customsearch/v1'
    params = {
        'key': api_key,
        'cx': cse_id,
        'q': query,
        **kwargs
    }
    response = requests.get(service_url, params=params)
    if response.status_code == 200:
        return json.loads(response.text)['items']
    else:
        print(f'Error: {response.status_code}')
        return []
        
def tokenize(text):
    return text
    # return tok.encode(text, add_special_tokens=False)
    
def format_prompt(message, history):
    prompt = ""
    for user_prompt, bot_response in history:
        prompt += "<s>" + tokenize("[INST]") + tokenize(user_prompt) + tokenize("[/INST]")
        prompt += tokenize(bot_response) + "</s> "
    prompt += tokenize("[INST]") + tokenize(message) + tokenize("[/INST]")
    return prompt

def generate(prompt, history, system_prompt, temperature=0.2, max_new_tokens=512, 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(f"{system_prompt}, {prompt}", history)

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

    for response in stream:
        print(response.token.text + "/n")
        output += response.token.text
        yield output
    return output

def generateS(prompt, history, system_prompt, temperature=0.2, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0):
    
    stream = google_search(prompt)
    output = ""

    for response in stream:
        output += json.dumps(response)
        yield output
    return output
    
additional_inputs=[
    gr.Textbox(
        label="System Prompt",
        max_lines=1,
        interactive=True,
    ),
    gr.Slider(
        label="Temperature",
        value=0.2,
        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=512,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.95,
        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,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

mychatbot = gr.Chatbot(
    avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=False)

demo = gr.ChatInterface(fn=generate, 
                        chatbot=mychatbot,
                        additional_inputs=additional_inputs,
                        title="Kamran's Mixtral 8x7b Chat",
                        retry_btn=None,
                        undo_btn=None
                       )

demo.queue().launch(show_api=False)