Update app.py

app.py

@@ -3,8 +3,8 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
 from difflib import get_close_matches
 
-# Load the WikiSQL dataset
-wikisql_dataset = load_dataset("wikisql", split='train')  # Increase the number of examples for better matching
+# Load the Spider dataset
+spider_dataset = load_dataset("spider", split='train[:100]')  # Increase the number of examples for better matching
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
@@ -17,7 +17,7 @@ def find_closest_match(query, dataset):
 
 def generate_sql_from_user_input(query):
     # Find the closest match in the dataset
-    matched_query = find_closest_match(query, wikisql_dataset)
+    matched_query = find_closest_match(query, spider_dataset)
     if not matched_query:
         return "No close match found in the dataset.", ""
 
@@ -33,8 +33,8 @@ interface = gr.Interface(
     fn=generate_sql_from_user_input,
     inputs=gr.Textbox(label="Enter your natural language query"),
     outputs=[gr.Textbox(label="Matched Query from Dataset"), gr.Textbox(label="Generated SQL Query")],
-    title="NL to SQL with T5 using WikiSQL Dataset",
-    description="This model finds the closest match in the WikiSQL dataset for your query and generates the corresponding SQL."
+    title="NL to SQL with T5 using Spider Dataset",
+    description="This model finds the closest match in the Spider dataset for your query and generates the corresponding SQL."
 )
 
 # Launch the app