Update app.py

app.py

@@ -5,30 +5,18 @@ 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()
+# Extract schema information from the Spider dataset
+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])
+    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")
-model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
-
-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
+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
@@ -38,7 +26,13 @@ def generate_sql_from_user_input(query):
     sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
     # Post-process the SQL query to match the dataset's schema
-    sql_query = post_process_sql_query(sql_query)
+    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