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')  # Load a subset of the dataset

# 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_user_input(query):
    # Generate SQL for the user's 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

def find_matching_sql(nl_query):
    # Find the matching SQL query from the Spider dataset
    for item in spider_dataset:
        if item['question'].lower() == nl_query.lower():
            return item['query']
    return "No matching SQL query found in the Spider dataset."

# Create a Gradio interface
interface = gr.Interface(
    fn=lambda query: {
        "Generated SQL Query": generate_sql_from_user_input(query),
        "Matching SQL Query from Spider Dataset": find_matching_sql(query)
    },
    inputs=gr.Textbox(label="Enter your natural language query"),
    outputs=[gr.Textbox(label="Generated SQL Query"), gr.Textbox(label="Matching SQL Query from Spider Dataset")],
    title="NL to SQL with T5 using Spider Dataset",
    description="This model generates an SQL query for your natural language input and finds a matching SQL query from the Spider dataset."
)

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