Update app.py

app.py

@@ -5,33 +5,32 @@ 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:
+    for table in item['db']['table_names_original']:
+        db_table_names.add((item['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 post_process_sql_query(sql_query, db_schema):
+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 table_name in db_schema['table_names']:
+    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 db_schema['column_names']:
+    for column_name in column_names:
         if "COLUMN" in sql_query:
-            sql_query = sql_query.replace("COLUMN", column_name[1], 1)
+            sql_query = sql_query.replace("COLUMN", column_name, 1)
     return sql_query
 
-def generate_sql_from_user_input(query, db_id):
-    # Find the corresponding database schema
-    db_schema = None
-    for item in spider_dataset:
-        if item['db_id'] == db_id:
-            db_schema = item
-            break
-    
-    if db_schema is None:
-        return "Database schema not found for the given DB ID."
-
+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)
@@ -39,13 +38,13 @@ def generate_sql_from_user_input(query, db_id):
     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, db_schema)
+    sql_query = post_process_sql_query(sql_query)
     return sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
     fn=generate_sql_from_user_input,
-    inputs=[gr.Textbox(label="Enter your natural language query"), gr.Textbox(label="Enter DB ID")],
+    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."