Update app.py

app.py

@@ -1,52 +1,35 @@
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, Trainer, TrainingArguments
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 from datasets import load_dataset
 
-# Load the model and tokenizer
-model_name = "hrshtsharma2012/NL2SQL-Picard-final"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("hrshtsharma2012/NL2SQL-Picard-final")
+model = AutoModelForSeq2SeqLM.from_pretrained("hrshtsharma2012/NL2SQL-Picard-final")
 
-# Load the Spider dataset
-dataset = load_dataset("spider")
+# Initialize the pipeline
+nl2sql_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
 
-# Preprocess the dataset
-def tokenize_function(examples):
-    inputs = tokenizer(examples["question"], padding="max_length", truncation=True, max_length=512)
-    outputs = tokenizer(examples["query"], padding="max_length", truncation=True, max_length=512)
-    return {"input_ids": inputs.input_ids, "attention_mask": inputs.attention_mask, "labels": outputs.input_ids}
+# Load a part of the Spider dataset
+spider_dataset = load_dataset("spider", split='train[:5]')
 
-tokenized_dataset = dataset.map(tokenize_function, batched=True)
-
-# Fine-tune the model
-training_args = TrainingArguments(
-    output_dir="./results",
-    num_train_epochs=3,
-    per_device_train_batch_size=4,
-    per_device_eval_batch_size=4,
-    warmup_steps=500,
-    weight_decay=0.01,
-    logging_dir="./logs",
-)
+def generate_sql(query):
+    results = nl2sql_pipeline(query)
+    sql_query = results[0]['generated_text']
+    return sql_query
 
-trainer = Trainer(
-    model=model,
-    args=training_args,
-    train_dataset=tokenized_dataset["train"],
-    eval_dataset=tokenized_dataset["validation"],
+# Use examples from the Spider dataset
+example_questions = [(question['question'],) for question in spider_dataset]
+
+# Create a Gradio interface
+interface = gr.Interface(
+    fn=generate_sql,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your natural language query here..."),
+    outputs="text",
+    examples=example_questions,
+    title="NL to SQL with Picard",
+    description="This model converts natural language queries into SQL using the Spider dataset. Try one of the example questions or enter your own!"
 )
 
-trainer.train()
-
-# Evaluate the model
-results = trainer.evaluate()
-print(results)
-
-# Use the model for inference
-def generate_sql(question):
-    inputs = tokenizer(question, 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
-
-sample_question = "What are the names of the students?"
-print(generate_sql(sample_question))
+# Launch the app
+if __name__ == "__main__":
+    interface.launch()