Update app.py

app.py

@@ -1,35 +1,52 @@
 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")
+# Load the WikiSQL dataset
+wikisql_dataset = load_dataset("wikisql", split='train[:100]')  # Load a subset of the dataset
 
-# Initialize the pipeline
-nl2sql_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+# 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)
 
-# Load a part of the WikiSQL dataset
-wikisql_dataset = load_dataset("wikisql", split='train[:5]')
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
+model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
 
-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()
+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
 
-# Use examples from the WikiSQL dataset
-example_questions = [(question['question'],) for question in wikisql_dataset]
+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)
+
+    # 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,
-    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 WikiSQL dataset. Try one of the example questions or enter your own!"
+    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 WikiSQL Dataset",
+    description="This model generates an SQL query for your natural language input based on the WikiSQL dataset."
 )
 
 # Launch the app