Upload 3 files

README.md

@@ -1,13 +1,27 @@
----
-title: NLP SQL
-emoji: 📚
-colorFrom: green
-colorTo: purple
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🧠 Natural Language → SQL Generator App
+
+This app converts **natural language questions** into **SQL queries** and runs them directly on your uploaded CSV data.
+
+## 🚀 Features
+- Upload any CSV file
+- Ask questions in plain English
+- Auto-generates SQL queries
+- Executes SQL and shows the result instantly
+- Runs 100% on Hugging Face — **no API keys required**
+
+## 🧩 Tech Stack
+- Python 🐍
+- Transformers (Hugging Face)
+- Gradio (UI)
+- SQLite + Pandas
+
+## 🧠 Model Used
+[`mrm8488/t5-base-finetuned-wikiSQL`](https://huggingface.co/mrm8488/t5-base-finetuned-wikiSQL)
+
+## 🪄 Example
+**Input:**  
+> Show employees older than 25
+
+**Output SQL:**  
+```sql
+SELECT * FROM data_table WHERE age > 25;

app.py

@@ -0,0 +1,56 @@
+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()

requirements.txt

@@ -0,0 +1,5 @@
+transformers==4.41.2
+torch
+gradio
+pandas
+sqlite3-binary