app.py

import gradio as gr
from transformers import T5Tokenizer, T5ForConditionalGeneration, pipeline
from datasets import load_dataset

# Load tokenizer and model
tokenizer = T5Tokenizer.from_pretrained("t5-base")
model = T5ForConditionalGeneration.from_pretrained("t5-base")

# Initialize the pipeline
nl2sql_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)

# Load a part of the Spider dataset
spider_dataset = load_dataset("spider", split='train[:5]')

def generate_sql(query):
    # Format the input for the model
    input_text = f"translate English to SQL: {query}"
    # Run the pipeline
    results = nl2sql_pipeline(input_text, max_length=512, num_return_sequences=1)
    # Extract the SQL query
    sql_query = results[0]['generated_text']
    return sql_query

# Use examples from the Spider dataset
example_questions = [(question['question'],) for question in spider_dataset]

# Create a Gradio interface
interface = gr.Interface(
    fn=generate_sql,
    inputs=gr.Textbox(lines=2, placeholder="Enter your natural language query here..."),
    outputs="text",
    examples=example_questions,
    title="NL to SQL with T5",
    description="This model converts natural language queries into SQL using the Spider dataset. Try one of the example questions or enter your own!"
)

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