Update app.py

app.py

@@ -3,52 +3,36 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
 
 # Load the WikiSQL dataset
-wikisql_dataset = load_dataset("wikisql", split='train[:100]')  # Load a subset of the dataset
-
-# Extract schema information from the dataset
-table_names = set()
-column_names = set()
-for item in wikisql_dataset:
-    table_names.add(item['table']['name'])
-    for column in item['table']['header']:
-        column_names.add(column)
+dataset = load_dataset("wikisql", split='train[:1000]')
 
 # Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
-model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
+tokenizer = AutoTokenizer.from_pretrained("t5-base")
+model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
 
-def post_process_sql_query(sql_query):
-    # Modify the SQL query to match the dataset's schema
-    # This is just an example and might need to be adapted based on the dataset and model output
-    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
+def preprocess_data(dataset):
+    # Tokenize the questions and SQL queries
+    tokenized_questions = tokenizer(dataset['question'], padding=True, truncation=True, return_tensors="pt")
+    tokenized_sql = tokenizer(dataset['sql']['human_readable'], padding=True, truncation=True, return_tensors="pt")
+    return tokenized_questions, tokenized_sql
 
-def generate_sql_from_user_input(query):
-    # Generate SQL for the user's query
+def generate_sql(query):
+    # Preprocess the input query
     input_text = "translate English to SQL: " + query
     inputs = tokenizer(input_text, return_tensors="pt", padding=True)
+
+    # Generate SQL query using the model
     outputs = model.generate(**inputs, max_length=512)
     sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # Post-process the SQL query to match the dataset's schema
-    sql_query = post_process_sql_query(sql_query)
     return sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=generate_sql_from_user_input,
+    fn=generate_sql,
     inputs=gr.Textbox(label="Enter your natural language query"),
     outputs=gr.Textbox(label="Generated SQL Query"),
-    title="NL to SQL with T5 using WikiSQL Dataset",
-    description="This model generates an SQL query for your natural language input based on the WikiSQL dataset."
+    title="Natural Language to SQL Prototype",
+    description="Enter a natural language query and get the corresponding SQL query."
 )
 
 # Launch the app
-if __name__ == "__main__":
-    interface.launch()
+interface.launch()