Spaces:
Sleeping
Sleeping
File size: 2,102 Bytes
6c6d2f7 f38ba4d 6c6d2f7 887c95b f1efe67 0c5ce5c b2ea7cc 0c5ce5c b2ea7cc 0c5ce5c f38ba4d 514fc02 4b8f9d6 0c5ce5c 769f777 f38ba4d 7cbc7f5 0c5ce5c 4f13759 6c6d2f7 0c5ce5c 769f777 0c5ce5c 6c6d2f7 db1852e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from datasets import load_dataset
# Load the Spider dataset
spider_dataset = load_dataset("spider", split='train') # Load a subset of the dataset
# Extract schema information from the dataset
db_table_names = set()
column_names = set()
for item in spider_dataset:
db_id = item['db_id']
for table in item['table_names']:
db_table_names.add((db_id, table))
for column in item['column_names']:
column_names.add(column[1])
# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-wikiSQL")
def post_process_sql_query(sql_query):
# Modify the SQL query to match the dataset's schema
for db_id, table_name in db_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 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_from_user_input,
inputs=gr.Textbox(label="Enter your natural language query"),
outputs=gr.Textbox(label="Generated SQL Query"),
title="NL to SQL using Spider Dataset",
description="This interface generates an SQL query from your natural language input based on the Spider dataset."
)
# Launch the app
if __name__ == "__main__":
interface.launch()
|