Update app.py

app.py

@@ -1,38 +1,37 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
+from difflib import get_close_matches
 
 # Load the WikiSQL dataset
-dataset = load_dataset("wikisql", split='train[:1000]')
+wikisql_dataset = load_dataset("wikisql", split='train[:100]')
 
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("t5-base")
-model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
+# Create a mapping between natural language queries and SQL queries
+query_sql_mapping = {item['question']: item['sql']['human_readable'] for item in wikisql_dataset}
 
-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 find_closest_match(query, dataset):
+    questions = [item['question'] for item in dataset]
+    matches = get_close_matches(query, questions, n=1)
+    return matches[0] if matches else None
 
-def generate_sql(query):
-    # Preprocess the input query
-    input_text = "translate English to SQL: " + query
-    inputs = tokenizer(input_text, return_tensors="pt", padding=True)
+def generate_sql_from_user_input(query):
+    # Find the closest match in the dataset
+    matched_query = find_closest_match(query, wikisql_dataset)
+    if not matched_query:
+        return "No close match found in the dataset."
 
-    # Generate SQL query using the model
-    outputs = model.generate(**inputs, max_length=512)
-    sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # Retrieve the corresponding SQL query from the dataset
+    sql_query = query_sql_mapping.get(matched_query, "SQL query not found.")
     return sql_query
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=generate_sql,
+    fn=generate_sql_from_user_input,
     inputs=gr.Textbox(label="Enter your natural language query"),
-    outputs=gr.Textbox(label="Generated SQL Query"),
-    title="Natural Language to SQL Prototype",
-    description="Enter a natural language query and get the corresponding SQL query."
+    outputs=gr.Textbox(label="SQL Query from Dataset"),
+    title="NL to SQL using WikiSQL Dataset",
+    description="Enter a natural language query and get the corresponding SQL query from the WikiSQL dataset."
 )
 
 # Launch the app
-interface.launch()
+if __name__ == "__main__":
+    interface.launch()