Update app.py

app.py

@@ -1,22 +1,19 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("hrshtsharma2012/NL2SQL-Picard-final")
 model = AutoModelForSeq2SeqLM.from_pretrained("hrshtsharma2012/NL2SQL-Picard-final")
 
-# 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):
-    results = nl2sql_pipeline(query)
-    sql_query = results[0]['generated_text']
-    # Post-process the output to ensure it's a valid SQL query
-    sql_query = sql_query.replace('<pad>', '').replace('</s>', '').strip()
+    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
 
 # Use examples from the Spider dataset