Create app.py

app.py

@@ -0,0 +1,54 @@
+import streamlit as st
+from transformers import pipeline 
+import sqlite3
+import numpy as np
+import pandas as pd
+
+translator = pipeline(model= "saikiranmaddukuri/chat_to_sql0.17", max_new_tokens= 100)
+
+## Function to read SQL data
+def read_sql_query(sql, db):
+    conn = sqlite3.connect(db)
+    cur = conn.cursor()
+    cur.execute(sql)
+    rows = cur.fetchall()
+    for row in rows:
+        print(row)
+    conn.close()
+
+
+def process_text(input_text):
+    # Backend function to process the input text (replace with your actual processing logic)
+    processed_text = f"You entered: {input_text}"
+    return processed_text
+
+# Streamlit app
+def main():
+    st.title("Conversational AI: Text-2-SQL")
+    
+    
+    create_table_statement= "CREATE TABLE  car_sales (Manufacturer text, Model text, Sales_in_thousands float, __year_resale_value float, Vehicle_type text, Price_in_thousands float, Engine_size float, Horsepower float, Wheelbase float, Width float, Length float, Curb_weight float, Fuel_capacity float, Fuel_efficiency float, Latest_Launch text, Power_perf_factor float)"
+
+    # Step 1: User input
+    user_query = st.text_input("Ask question and press Enter:")
+
+    # Step 2: Backend processing on Enter
+    if  user_query:
+        text='question:{}. table:{}'.format(user_query,create_table_statement.replace("text", 'VARCHAR') )
+        generated_sql= translator([text])
+        generated_sql= generated_sql[0]['generated_text']
+        
+        
+        i_gen_query = st.text_area("AI Generated SQL", generated_sql)
+
+        
+
+        # Step 4: Process edited text on Enter
+        if st.button("Enter") and i_gen_query:
+            final_output= read_sql_query(i_gen_query, "Cars_db.sqlite")
+
+            # Step 5: Display final output
+            st.write("Final Output:", final_output)
+
+if __name__ == "__main__":
+    main()