Update app.py

app.py

@@ -5,46 +5,16 @@ 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_ids = set()
-table_names = set()
-column_names = set()
-for item in spider_dataset:
-    db_ids.add(item['db_id'])
-    for table in item['table_names']:
-        table_names.add(table)
-    for column in item['column_names']:
-        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 post_process_sql_query(sql_query):
-    # Modify the SQL query to match the dataset's schema
-    # This is just an example and might need to be adapted based on the dataset and model output
-    for db_id in db_ids:
-        if "DB_ID" in sql_query:
-            sql_query = sql_query.replace("DB_ID", db_id)
-            break  # Assuming only one database is referenced in the 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
-
 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)
-
-    # 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