app.py

import json
import gradio as gr
import duckdb

# Load the Parquet dataset path
dataset_path = 'sample_contract_df.parquet'  # Update with your Parquet file path

# Load the dataset schema with DuckDB
def load_dataset_schema():
    con = duckdb.connect()
    con.execute(f"CREATE VIEW contract_data AS SELECT * FROM '{dataset_path}'")
    schema = con.execute("DESCRIBE contract_data").fetchdf()
    con.close()
    return schema.to_dict(orient="records")

# Generate SQL based on schema and user query
def generate_sql_query(features, query):
    # This simple example constructs an SQL condition directly, adapt for complex queries if needed
    sql_query = f"SELECT * FROM contract_data WHERE {query}"
    return sql_query

# Execute the SQL query and display results
def execute_query(sql_query):
    con = duckdb.connect()
    con.execute(f"CREATE VIEW contract_data AS SELECT * FROM '{dataset_path}'")
    result_df = con.execute(sql_query).fetchdf()
    con.close()
    return result_df.to_markdown()  # Display result as markdown

# Gradio app UI
with gr.Blocks() as demo:
    gr.Markdown("""
    # Local Parquet SQL Query App
    Query and explore data in `sample_contract_df.parquet` using DuckDB and SQL queries.
    """)
    
    # Load dataset schema and convert it to JSON for display
    schema = load_dataset_schema()
    schema_json = json.dumps(schema, indent=2)
    features = gr.Code(label="Dataset Schema", value=schema_json, language="json")

    # User input components
    query = gr.Textbox(label="Natural Language Query", placeholder="Enter a condition, e.g., 'amount > 1000'")
    sql_out = gr.Code(label="Generated SQL Query", language="sql")
    results_out = gr.Markdown(label="Query Results")

    # Buttons to generate and execute SQL
    btn_generate = gr.Button("Generate SQL")
    btn_execute = gr.Button("Execute Query")

    # Set up click events with correct inputs and outputs
    btn_generate.click(
        fn=generate_sql_query,
        inputs=[features, query],  # Both are Gradio components now
        outputs=sql_out,
    )
    btn_execute.click(
        fn=execute_query,
        inputs=sql_out,
        outputs=results_out,
    )

# Launch the app
demo.launch()