app.py

from huggingface_hub import InferenceClient
import gradio as gr
import random
import pandas as pd
import csv
import tempfile
import re

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

def extract_text_from_excel(file, column_name):
    df = pd.read_excel(file)
    text = ' '.join(df[column_name].astype(str))
    return text

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

    with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
        fieldnames = ['Original Sentence', 'Generated Sentence']
        writer = csv.DictWriter(tmp, fieldnames=fieldnames)
        writer.writeheader()  

        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, return_full_text=False)
                output = ""
                for response in stream:
                    output += response.text

                generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', output)
                generated_sentences = [s.strip() for s in generated_sentences if s.strip() and s != '.']

                for _ in range(num_similar_sentences):
                    if not generated_sentences:
                        break
                    generated_sentence = generated_sentences.pop(random.randrange(len(generated_sentences)))
                    writer.writerow({'Original Sentence': sentence, 'Generated Sentence': generated_sentence})

            except Exception as e:
                print(f"Error generating data for sentence '{sentence}': {e}")

        tmp_path = tmp.name

    return tmp_path

gr.Interface( 
    fn=generate,
    inputs=[
        gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx"]),
        gr.TextAreaInput(label="Column Name", placeholder="Enter the column name"),
        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"),
        gr.Slider(label="Number of similar sentences", value=10, minimum=1, maximum=20, step=1, interactive=True, info="Number of similar sentences to generate for each original sentence"),
    ],
    outputs=gr.File(label="Synthetic Data "),
    title="SDG",
    description="AYE QABIL.",
    allow_flagging="never",
).launch()