app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from datasets import load_dataset

# Load the Spider dataset
spider_dataset = load_dataset("spider", split='train[:1000]')

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")

def generate_sql_from_dataset(index):
    # Ensure the index is within the range of the dataset
    index = int(index)  # Convert to integer in case it's passed as a string
    if index < 0 or index >= len(spider_dataset):
        return "Invalid index. Please enter a number between 0 and {}.".format(len(spider_dataset) - 1), ""

    # Get the natural language query from the dataset
    query = spider_dataset[index]['question']
    input_text = "translate English to SQL: " + query
    inputs = tokenizer(input_text, return_tensors="pt", padding=True)
    outputs = model.generate(**inputs, max_length=512)
    sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return query, sql_query

# Create a Gradio interface
interface = gr.Interface(
    fn=generate_sql_from_dataset,
    inputs=gr.Number(label="Dataset Index (0-4)"),
    outputs=[gr.Textbox(label="Natural Language Query"), gr.Textbox(label="Generated SQL Query")],
    title="NL to SQL with T5 using Spider Dataset",
    description="This model converts natural language queries from the Spider dataset into SQL. Enter the index of the dataset entry (0-4)!"
)

# Launch the app
if __name__ == "__main__":
    interface.launch()