import gradio as gr
from datasets import load_dataset
from difflib import get_close_matches

# Load the WikiSQL dataset
wikisql_dataset = load_dataset("wikisql", split='train[:100]')

# Create a mapping between natural language queries and SQL queries
query_sql_mapping = {item['question']: item['sql']['human_readable'] for item in wikisql_dataset}

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."

    # Retrieve the corresponding SQL query from the dataset
    sql_query = query_sql_mapping.get(matched_query, "SQL query not found.")
    return sql_query

# 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="SQL Query from Dataset"),
    title="NL to SQL using WikiSQL Dataset",
    description="Enter a natural language query and get the corresponding SQL query from the WikiSQL dataset."
)

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