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

# Load the WikiSQL dataset (only the table schemas are needed for validation)
wikisql_dataset = load_dataset("wikisql", split='train')

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")

def validate_sql_against_schema(sql_query, schema):
    # This is a placeholder function. You need to implement the logic to validate
    # the SQL query against the table schema. The validation can be as simple or as
    # complex as you need, depending on the requirements.
    return True  # Assume the query is valid for now

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)

    # Validate the generated SQL query against the schemas in the dataset
    for item in wikisql_dataset:
        if validate_sql_against_schema(sql_query, item['sql']):
            return query, sql_query

    return query, "Generated SQL query is not consistent with the 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="Your Query"), gr.Textbox(label="Generated SQL Query")],
    title="NL to SQL with T5 using WikiSQL Dataset",
    description="This model generates an SQL query for your natural language input and validates it against the WikiSQL dataset."
)

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