app.py

from huggingface_hub import InferenceClient
import gradio as gr
import PyPDF2
import random
import pandas as pd
from io import BytesIO 
import csv
import os
import io
import tempfile
# Initialize the inference client with your chosen model
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

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 save_to_csv(sentence, output, filename="synthetic_data.csv"):
    with open(filename, mode='a', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        writer.writerow([sentence, output])


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

    # CSV dosyası için başlık
    if not os.path.exists("synthetic_data.csv"):
        with open("synthetic_data.csv", mode='w', newline='', encoding='utf-8') as file:
            writer = csv.writer(file)
            writer.writerow(["Original Sentence", "Synthetic Data"])

    for sentence in sentences:
        sentence = sentence.strip()
        if not sentence:
            continue

        generate_kwargs = {
            "temperature": temperature,
            "max_new_tokens": max_new_tokens,
            "top_p": top_p,
            "repetition_penalty": repetition_penalty,
            "do_sample": True,
            "seed": 42,
        }

        try:
            stream = client.text_generation(sentence, **generate_kwargs, stream=True, details=True, return_full_text=False)
            output = ""
            for response in stream:
                output += response.token.text
            save_to_csv(sentence, output)
        except Exception as e:
            print(f"Error generating data for sentence '{sentence}': {e}")
            save_to_csv(sentence, f"Error: {e}")

    # CSV dosyasını okuyup byte olarak döndür
    with open("synthetic_data.csv", "r", encoding="utf-8") as file:
        csv_content = file.read()
    csv_bytes = csv_content.encode()

    # Geçici dosya oluştur ve içeriği yaz
    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp:
        tmp.write(csv_bytes)
        tmp_path = tmp.name

    return tmp_path
gr.Interface( 
    fn=generate,
    inputs=[
        gr.File(label="Upload PDF File", file_count="single", file_types=[".pdf"]),
        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=0.95, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),
        gr.Slider(label="Repetition penalty", value=1.0, minimum=1.0, maximum=2.0, step=0.1, interactive=True, info="Penalize repeated tokens"),
    ],
    outputs=gr.File(label="Synthetic Data CSV"),
    title="Synthetic Data Generation",
    description="This tool generates synthetic data from the sentences in your PDF and saves it to a CSV file.",
    allow_flagging="never",
).launch()