app.py

from huggingface_hub import InferenceClient
import gradio as gr
import PyPDF2
import random
import pandas as pd
from io import StringIO

# Initialize the inference client with your chosen model
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

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 extract_text_from_pdf(file):
    pdf_reader = PyPDF2.PdfReader(file)
    text = ""
    for page in range(len(pdf_reader.pages)):
        text += pdf_reader.pages[page].extract_text()
    return text

def generate_synthetic_data(sentences, generate_kwargs):
    synthetic_data = []
    for sentence in sentences:
        formatted_prompt = format_prompt(sentence, [])
        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
        synthetic_data.append(output)
    return synthetic_data

def generate(file, system_prompt, temperature, max_new_tokens, top_p, repetition_penalty):
    # Extract text and split into sentences
    text = extract_text_from_pdf(file)
    sentences = text.split('.')
    random.shuffle(sentences)  # Shuffle sentences

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

    synthetic_data = generate_synthetic_data(sentences, generate_kwargs)

    # Convert synthetic data to CSV
    df = pd.DataFrame(synthetic_data, columns=["Synthetic Data"])
    csv_buffer = StringIO()
    df.to_csv(csv_buffer, index=False)
    return gr.File(value=csv_buffer.getvalue(), file_name="synthetic_data.csv")

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=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"),
    gr.File(label="Upload PDF File", file_count="single", file_types=[".pdf"]),
]

gr.Interface(
    fn=generate,
    inputs=[gr.File(label="Upload PDF File", file_count="single", file_types=[".pdf"]), "state", "number", "number", "number", "number"],
    outputs="file",
    additional_inputs=additional_inputs,
    title="Synthetic Data Generation",
    description="This tool generates synthetic data from the sentences in your PDF.",
    allow_flagging="never",
).launch()