Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from datasets import load_dataset
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("hrshtsharma2012/NL2SQL-Picard-final")
@@ -8,21 +9,16 @@ model = AutoModelForSeq2SeqLM.from_pretrained("hrshtsharma2012/NL2SQL-Picard-fin
 # Initialize the pipeline
 nl2sql_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
 
+# Load a part of the Spider dataset
+spider_dataset = load_dataset("spider", split='train[:5]')
+
 def generate_sql(query):
-    # Use the model to generate SQL from the natural language query
     results = nl2sql_pipeline(query)
-    # Extract the first result (highest likelihood)
     sql_query = results[0]['generated_text']
     return sql_query
 
-# Example questions from the Spider dataset
-example_questions = [
-    ("How many heads of the departments are older than 56 ?",),
-    ("List the name, born state and age of the heads of departments ordered by age.",),
-    ("List the creation year, name and budget of each department.",),
-    ("What are the maximum and minimum budget of the departments?",),
-    ("In which year were most departments established?.",)
-]
+# Use examples from the Spider dataset
+example_questions = [(question['question'],) for question in spider_dataset]
 
 # Create a Gradio interface
 interface = gr.Interface(
@@ -31,7 +27,7 @@ interface = gr.Interface(
     outputs="text",
     examples=example_questions,
     title="NL to SQL with Picard",
-    description="This model converts natural language queries into SQL. It's based on the Spider dataset. Try one of the example questions or enter your own!"
+    description="This model converts natural language queries into SQL using the Spider dataset. Try one of the example questions or enter your own!"
 )
 
 # Launch the app