File size: 1,914 Bytes
a22c47e |
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 57 |
import gradio as gr
import pandas as pd
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import sqlite3
# Load model and tokenizer
model_name = "mrm8488/t5-base-finetuned-wikiSQL"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
def generate_sql_query(natural_language, data):
# Load uploaded CSV
df = pd.read_csv(data.name)
# Create in-memory SQLite DB
conn = sqlite3.connect(":memory:")
df.to_sql("data_table", conn, index=False, if_exists="replace")
# Create schema description
schema = ", ".join([f"{col}" for col in df.columns])
# Combine user query and schema
input_text = f"translate English to SQL: {natural_language} | table columns: {schema}"
# Generate SQL query
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=256)
sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
try:
# Execute the generated SQL query
result_df = pd.read_sql_query(sql_query, conn)
except Exception as e:
result_df = pd.DataFrame({"Error": [str(e)]})
conn.close()
return sql_query, result_df.head()
# Gradio UI
iface = gr.Interface(
fn=generate_sql_query,
inputs=[
gr.Textbox(label="Enter your question (Natural Language)", placeholder="e.g., Show customers with age > 30"),
gr.File(label="Upload CSV dataset")
],
outputs=[
gr.Textbox(label="Generated SQL Query"),
gr.Dataframe(label="Query Result")
],
title="🧠 Natural Language to SQL Generator",
description="Upload a CSV file and ask questions in plain English. The app converts them into SQL and shows the result.",
allow_flagging="never"
)
if __name__ == "__main__":
iface.launch()
|