app.py

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

# Load the WikiSQL dataset
wikisql_dataset = load_dataset("wikisql", split='train[:100]')  # 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 find_closest_match(query, dataset):
    questions = [item['question'] for item in dataset]
    matches = get_close_matches(query, questions, n=1)
    return matches[0] if matches else None

def generate_sql_from_user_input(query):
    # Find the closest match in the dataset
    matched_query = find_closest_match(query, wikisql_dataset)
    if not matched_query:
        return "No close match found in the dataset.", ""

    # Find the corresponding SQL query in the dataset
    for item in wikisql_dataset:
        if item['question'] == matched_query:
            return matched_query, item['sql']['human_readable']

    return "Match found, but corresponding SQL query not found in dataset.", ""

# Create a Gradio interface
interface = gr.Interface(
    fn=generate_sql_from_user_input,
    inputs=gr.Textbox(label="Enter your natural language query"),
    outputs=[gr.Textbox(label="Matched Query from Dataset"), gr.Textbox(label="Corresponding SQL Query from Dataset")],
    title="NL to SQL with T5 using WikiSQL Dataset",
    description="This model finds the closest match in the WikiSQL dataset for your query and returns the corresponding SQL query from the dataset."
)

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