app.py

from huggingface_hub import InferenceClient
import gradio as gr
import streamlit as st
import requests

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

def search_url(search_query):
    API_KEY = st.secrets['AIzaSyDseKKQCAUBmPidu_QapnpJCGLueDWYJbE']
    SEARCH_ENGINE_ID = st.secrets['001ae9bf840514e61']
    
    url = 'https://customsearch.googleapis.com/customsearch/v1'

    params = {
        'q': search_query,
        'key': API_KEY,
        'cx': SEARCH_ENGINE_ID,
    }

    response = requests.get(url, params=params)

    results = response.json()

    # print(results)

    if 'items' in results:
        for i in range(min(5, len(results['items']))):
            print(f"Link {i + 1}: {results['items'][i]['link']}")
        return results['items'][:5]
    else:
        print("No search results found.")
        return None
        
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:
        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 = search_url(prompt)
    # output = ""

    # for response in stream:
    #     output += response.token.text
    #     yield output
    return stream
    
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=generateS, 
                        chatbot=mychatbot,
                        additional_inputs=additional_inputs,
                        title="Kamran's Mixtral 8x7b Chat",
                        retry_btn=None,
                        undo_btn=None
                       )

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