Spaces:
Sleeping
Sleeping
File size: 2,588 Bytes
06f01b3 b474ae1 06f01b3 b474ae1 5b4c268 b474ae1 7161a9c 5b4c268 b474ae1 5b4c268 b474ae1 06f01b3 b474ae1 06f01b3 b474ae1 06f01b3 b474ae1 5b4c268 06f01b3 b474ae1 06f01b3 b474ae1 8cb3a33 b474ae1 8cb3a33 b474ae1 5b4c268 06f01b3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
import os
import json
import gradio as gr
import duckdb
# Load the Parquet dataset
dataset_path = 'sample_contract_df.parquet' # Update with your Parquet file's path
# Load the dataset with DuckDB and get schema information
def load_dataset():
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):
messages = [
{
"role": "system",
"content": "You are a SQL query expert assistant that generates DuckDB SQL queries based on the user's natural language query and dataset schema.",
},
{
"role": "user",
"content": f"""table contract_data
# Features
{features}
# Query
{query}
""",
},
]
# Here we use DuckDB directly instead of an external API
sql_query = f"SELECT * FROM contract_data WHERE {query}" # Simple example; adapt for complex queries
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() # Convert result to markdown for display
# Gradio app UI
with gr.Blocks() as demo:
gr.Markdown("""
# Local Parquet SQL Query App
Query and explore the data stored in `sample_contract_df.parquet` using DuckDB and SQL queries.
""")
# Display schema
schema = load_dataset()
features = json.dumps(schema, indent=2)
gr.Markdown(f"### Dataset Schema:\n\n```json\n{features}\n```")
# User inputs for natural language query
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
with gr.Row():
btn_generate = gr.Button("Generate SQL")
btn_execute = gr.Button("Execute Query")
# Generate SQL on button click
btn_generate.click(
fn=generate_sql_query,
inputs=[features, query],
outputs=sql_out,
)
# Execute SQL on button click
btn_execute.click(
fn=execute_query,
inputs=sql_out,
outputs=results_out,
)
# Launch the app
demo.launch()
|