app.py

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

# Load the Spider dataset
spider_dataset = load_dataset("HusnaManakkot/haispider", split='train')  # Load a subset of the dataset
# Extract schema information from the Spider dataset
table_names = set()
column_names = set()
for item in spider_dataset:
    for table in item['db_id']:
        table_names.add(table)
    for column in item['question']:
        column_names.add(column)

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")  # Update this to a model fine-tuned on Spider if available
model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")  # Update this to a model fine-tuned on Spider if available

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)

    # Post-process the SQL query to match the dataset's schema
    for table_name in table_names:
        if "TABLE" in sql_query:
            sql_query = sql_query.replace("TABLE", table_name)
            break  # Assuming only one table is referenced in the query
    for column_name in column_names:
        if "COLUMN" in sql_query:
            sql_query = sql_query.replace("COLUMN", column_name, 1)
    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="Generated SQL Query"),
    title="NL to SQL with T5 using Spider Dataset",
    description="This model generates an SQL query for your natural language input based on the Spider dataset."
)

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