Update app.py

app.py

@@ -9,18 +9,43 @@ spider_dataset = load_dataset("spider", split='train')  # Load a subset of the d
 tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 
-def generate_sql_from_user_input(query):
+def post_process_sql_query(sql_query, db_schema):
+    # 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']:
+        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']:
+        if "COLUMN" in sql_query:
+            sql_query = sql_query.replace("COLUMN", column_name[1], 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."
+
     # 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, db_schema)
     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"),
+    inputs=[gr.Textbox(label="Enter your natural language query"), gr.Textbox(label="Enter DB ID")],
     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."