Update app.py

app.py

@@ -13,51 +13,95 @@ def load_dataset_schema():
     con.close()
     return schema.to_dict(orient="records")
 
+# Simple parser to convert natural language to SQL syntax
+def parse_query(nl_query):
+    # Replace common phrases with SQL syntax
+    replacements = {
+        'equal to': '=',
+        'equals to': '=',
+        'equals': '=',
+        'equal': '=',
+        'not equal to': '!=',
+        'not equal': '!=',
+        'greater than or equal to': '>=',
+        'less than or equal to': '<=',
+        'greater than': '>',
+        'less than': '<',
+        'between': 'BETWEEN',
+        ' and ': ' AND ',
+        ' or ': ' OR ',
+    }
+    sql_query = nl_query.lower()
+    for k, v in replacements.items():
+        sql_query = sql_query.replace(k, v)
+    return sql_query
+
 # 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}"
+    condition = parse_query(query)
+    sql_query = f"SELECT * FROM contract_data WHERE {condition}"
     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
+    try:
+        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, ""
+    except Exception as e:
+        con.close()
+        return None, f"Error executing query: {e}"
+
+# Load dataset schema and convert it to JSON for display
+schema = load_dataset_schema()
+schema_json = json.dumps(schema, indent=2)
 
 # 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.
+
+    ## Instructions
+
+    - Enter a natural language query describing the data you want to retrieve.
+    - Click "Generate SQL" to see the SQL query that will be executed.
+    - Click "Execute Query" to run the query and see the results.
+    - You can view the dataset schema in the "Dataset Schema" tab.
     """)
-    
-    # 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")
+    with gr.Tabs():
+        with gr.TabItem("Query Data"):
+            with gr.Row():
+                with gr.Column(scale=1):
+                    query = gr.Textbox(
+                        label="Natural Language Query",
+                        placeholder="e.g., 'amount greater than 1000 and status equal to \"approved\"'"
+                    )
+                    btn_generate = gr.Button("Generate SQL")
+                    sql_out = gr.Code(label="Generated SQL Query", language="sql")
+                    btn_execute = gr.Button("Execute Query")
+                    error_out = gr.Markdown("", visible=False)
+                with gr.Column(scale=2):
+                    results_out = gr.Dataframe(label="Query Results")
 
-    # Buttons to generate and execute SQL
-    btn_generate = gr.Button("Generate SQL")
-    btn_execute = gr.Button("Execute Query")
+        with gr.TabItem("Dataset Schema"):
+            gr.Markdown("### Dataset Schema")
+            features = gr.Code(label="Dataset Schema", value=schema_json, language="json")
 
-    # Set up click events with correct inputs and outputs
+    # Set up click events
     btn_generate.click(
         fn=generate_sql_query,
-        inputs=[features, query],  # Both are Gradio components now
+        inputs=[features, query],
         outputs=sql_out,
     )
     btn_execute.click(
         fn=execute_query,
         inputs=sql_out,
-        outputs=results_out,
+        outputs=[results_out, error_out],
     )
 
 # Launch the app