Update app.py

app.py

@@ -5,29 +5,49 @@ from datasets import load_dataset
 # Load the Spider dataset
 spider_dataset = load_dataset("spider", split='train')  # Load a subset of the dataset
 
+# Extract schema information from the dataset
+db_table_names = set()
+column_names = set()
+for item in spider_dataset:
+    db_id = item['db_id']
+    for table in item['db']['table_names_original']:
+        db_table_names.add((db_id, table))
+    for column in item['db']['column_names_original']:
+        column_names.add(column[1])
+
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 
-def generate_sql_from_spider_query(index):
-    # Get the natural language query from the Spider dataset
-    if index < 0 or index >= len(spider_dataset):
-        return "Invalid index. Please enter a value between 0 and {}.".format(len(spider_dataset) - 1)
+def post_process_sql_query(sql_query):
+    # Modify the SQL query to match the dataset's schema
+    for db_id, table_name in db_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
 
-    nl_query = spider_dataset[index]['question']
-    input_text = "translate English to SQL: " + nl_query
+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)
-    return {"Natural Language Query": nl_query, "Generated SQL Query": sql_query}
+
+    # Post-process the SQL query to match the dataset's schema
+    sql_query = post_process_sql_query(sql_query)
+    return sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=generate_sql_from_spider_query,
-    inputs=gr.Number(label="Enter the index of the query in the Spider dataset (0 to {})".format(len(spider_dataset) - 1)),
-    outputs=[gr.Textbox(label="Natural Language Query"), gr.Textbox(label="Generated SQL Query")],
-    title="NL to SQL using Spider Dataset",
-    description="This interface generates an SQL query from a natural language query in the Spider dataset."
+    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