Create app.py

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+
+MODEL_NAME = "Chaitanya182004/nl2sql-model"
+tokenizer  = AutoTokenizer.from_pretrained(MODEL_NAME)
+model      = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model  = model.to(device)
+
+def generate_sql(question, context):
+    input_text = f"{question} | {context}"
+    inputs     = tokenizer(input_text, return_tensors='pt',
+                          max_length=512, truncation=True).to(device)
+    outputs    = model.generate(**inputs, max_new_tokens=128,
+                               num_beams=4, early_stopping=True)
+    sql = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return sql
+
+demo = gr.Interface(
+    fn=generate_sql,
+    inputs=[
+        gr.Textbox(label="Question"),
+        gr.Textbox(label="Context")
+    ],
+    outputs=gr.Textbox(label="SQL"),
+    title="NL2SQL API"
+)
+
+demo.launch()