app.py

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

# Load the Spider dataset
wikisql_dataset = load_dataset("wikisql", split='train[:5]')

# 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(query):
    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 sql_query

# Create a Gradio interface
interface = gr.Interface(
    fn=generate_sql,
    inputs=gr.Textbox(lines=2, placeholder="Enter your natural language query here..."),
    outputs="text",
    title="NL to SQL with T5",
    description="This model converts natural language queries into SQL. Enter your query!"
)

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