Update app.py

app.py

@@ -3,33 +3,45 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
 
 # Load the Spider dataset
-spider_dataset = load_dataset("spider", split='train[:1000]')
+spider_dataset = load_dataset("spider", split='train')  # Load a subset of the dataset
 
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
-model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
+# Extract schema information from the Spider dataset
+table_names = set()
+column_names = set()
+for item in spider_dataset:
+    for table in item['db']['table_names_original']:
+        table_names.add(table)
+    for column in item['db']['column_names_original']:
+        column_names.add(column[1])
 
-def generate_sql_from_dataset(index):
-    # Ensure the index is within the range of the dataset
-    index = int(index)  # Convert to integer in case it's passed as a string
-    if index < 0 or index >= len(spider_dataset):
-        return "Invalid index. Please enter a number between 0 and {}.".format(len(spider_dataset) - 1), ""
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")  # Update this to a model fine-tuned on Spider if available
+model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")  # Update this to a model fine-tuned on Spider if available
 
-    # Get the natural language query from the dataset
-    query = spider_dataset[index]['question']
+def generate_sql_from_user_input(query):
+    # Generate SQL for the user's query
     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 query, sql_query
+
+    # Post-process the SQL query to match the dataset's schema
+    for table_name in table_names:
+        if "TABLE" in sql_query:
+            sql_query = sql_query.replace("TABLE", table_name)
+            break  # Assuming only one table is referenced in the query
+    for column_name in column_names:
+        if "COLUMN" in sql_query:
+            sql_query = sql_query.replace("COLUMN", column_name, 1)
+    return sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=generate_sql_from_dataset,
-    inputs=gr.Number(label="Dataset Index (0-4)"),
-    outputs=[gr.Textbox(label="Natural Language Query"), gr.Textbox(label="Generated SQL Query")],
+    fn=generate_sql_from_user_input,
+    inputs=gr.Textbox(label="Enter your natural language query"),
+    outputs=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)!"
+    description="This model generates an SQL query for your natural language input based on the Spider dataset."
 )
 
 # Launch the app