app.py

from huggingface_hub import InferenceClient
import gradio as gr
import pandas as pd

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

# Function to format the prompt
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

# Function to generate text based on prompt and history
def generate(prompt, history, system_prompt, 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,
    )

    # Format the prompt
    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)

    # Generate text using InferenceClient
    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

# Additional input components for Gradio interface
additional_inputs=[
    gr.File(label="Upload CSV or Document", type="binary"),  # Max file size is 2 GB
    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=5120, 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")
]

# Function to read uploaded CSV or Document
def read_file(file):
    if file is None:
        return None
    elif file.name.endswith('.csv'):
        return pd.read_csv(file)
    elif file.name.endswith('.txt'):
        with open(file.name, 'r') as f:
            return f.read()

# Gradio Chat Interface
gr.ChatInterface(
    fn=generate,
    inputs=[
        gr.Textbox(label="Prompt"),
        gr.Textbox(label="History", placeholder="User1: Hello\nBot: Hi there!\nUser1: How are you?"),
        gr.Textbox(label="System Prompt"),
        gr.File(label="Upload CSV or Document", type="binary"),  # Max file size is 2 GB
    ],
    outputs=gr.Textbox(label="Response"),
    title="Synthetic-data-generation-aze",
    additional_inputs=additional_inputs,
    examples=[
        ["What is the capital of France?", "Paris", "Ask me anything"],
        ["How are you?", "I'm good, thank you!", "User"],
    ],
    allow_flagging=False,
    allow_upvoting=False,
    allow_duplicate_of_same_input=False,
    flagging_options=["Inappropriate", "Incorrect", "Offensive"],
    thumbs=None,
).launch()