Update app.py

app.py

@@ -9,22 +9,24 @@ spider_dataset = load_dataset("spider", split='train[:5]')
 tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 
-def generate_sql(query):
+def generate_sql_from_dataset(index):
+    # Get the natural language query from the dataset
+    query = spider_dataset[index]['question']
     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
+    return query, sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=generate_sql,
-    inputs=gr.Textbox(lines=2, placeholder="Enter your natural language query here..."),
-    outputs="text",
-    title="NL to SQL with T5",
-    description="This model converts natural language queries into SQL. Enter your query!"
+    fn=generate_sql_from_dataset,
+    inputs=gr.Number(label="Dataset Index (0-4)", default=0),
+    outputs=[gr.Textbox(label="Natural Language Query"), gr.Textbox(label="Generated SQL Query")],
+    title="NL to SQL with T5 using Spider Dataset",
+    description="This model converts natural language queries from the Spider dataset into SQL. Enter the index of the dataset entry (0-4)!"
 )
 
 # Launch the app
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()