Update app.py

app.py

@@ -5,35 +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['table_names']:
+        db_table_names.add((db_id, 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
+    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
+
 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 sql_query
 
-def find_matching_sql(nl_query):
-    # Find the matching SQL query from the Spider dataset
-    for item in spider_dataset:
-        if item['question'].lower() == nl_query.lower():
-            return item['query']
-    return "No matching SQL query found in the Spider dataset."
+    # 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=lambda query: {
-        "Generated SQL Query": generate_sql_from_user_input(query),
-        "Matching SQL Query from Spider Dataset": find_matching_sql(query)
-    },
+    fn=generate_sql_from_user_input,
     inputs=gr.Textbox(label="Enter your natural language query"),
-    outputs=[gr.Textbox(label="Generated SQL Query"), gr.Textbox(label="Matching SQL Query from Spider Dataset")],
-    title="NL to SQL with T5 using Spider Dataset",
-    description="This model generates an SQL query for your natural language input and finds a matching SQL query from the Spider dataset."
+    outputs=gr.Textbox(label="Generated SQL Query"),
+    title="NL to SQL using Spider Dataset",
+    description="This interface generates an SQL query from your natural language input based on the Spider dataset."
 )
 
 # Launch the app