Update app.py
Browse files
app.py
CHANGED
@@ -1,21 +1,15 @@
|
|
1 |
-
from dotenv import load_dotenv
|
2 |
import streamlit as st
|
3 |
import os
|
4 |
import sqlite3
|
5 |
import google.generativeai as genai
|
6 |
|
7 |
-
# Load environment variables
|
8 |
load_dotenv()
|
9 |
|
10 |
-
# # Retrieve the API key securely from Streamlit secrets
|
11 |
-
# GOOGLE_API_KEY = st.secrets["gemini"]["GOOGLE_API_KEY"]
|
12 |
-
|
13 |
# Configure Gemini API
|
14 |
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
|
15 |
|
16 |
-
# Configure Gemini API with the API Key from secrets
|
17 |
-
# genai.configure(api_key=API_KEY)
|
18 |
-
|
19 |
# Function to load Gemini model and generate SQL query
|
20 |
def get_gemini_response(question, prompt):
|
21 |
model = genai.GenerativeModel('gemini-pro')
|
@@ -36,7 +30,7 @@ def read_sql_query(sql, db):
|
|
36 |
except Exception as e:
|
37 |
return [("Error:", str(e))] # Return error message if query fails
|
38 |
|
39 |
-
# Define prompt
|
40 |
prompt = """
|
41 |
You are an expert in SQL query generation. Your task is to convert natural language questions into valid SQL queries based on the given database schema.
|
42 |
|
@@ -59,23 +53,17 @@ Input: "Show the names of students in Data Science Section."
|
|
59 |
Output: SELECT NAME FROM STUDENT_INFO WHERE SECTION = 'Data Science';
|
60 |
"""
|
61 |
|
62 |
-
# Streamlit App
|
63 |
st.set_page_config(page_title="SQL Query Generator")
|
64 |
st.header("Gemini App To Retrieve SQL Data")
|
65 |
|
66 |
-
# Input for user's question
|
67 |
question = st.text_input("Enter your question:", key="input")
|
68 |
submit = st.button("Generate SQL Query")
|
69 |
|
70 |
-
# If submit is clicked
|
71 |
if submit:
|
72 |
sql_query = get_gemini_response(question, prompt)
|
73 |
st.subheader("Generated SQL Query")
|
74 |
st.code(sql_query, language="sql") # Show SQL query
|
75 |
|
76 |
-
# Execute the SQL query and retrieve results
|
77 |
response = read_sql_query(sql_query, "student.db")
|
78 |
-
|
79 |
-
# Show the query results
|
80 |
-
st.subheader("Query Results")
|
81 |
-
st.write(response)
|
|
|
1 |
+
from dotenv import load_dotenv
|
2 |
import streamlit as st
|
3 |
import os
|
4 |
import sqlite3
|
5 |
import google.generativeai as genai
|
6 |
|
7 |
+
# Load environment variables
|
8 |
load_dotenv()
|
9 |
|
|
|
|
|
|
|
10 |
# Configure Gemini API
|
11 |
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
|
12 |
|
|
|
|
|
|
|
13 |
# Function to load Gemini model and generate SQL query
|
14 |
def get_gemini_response(question, prompt):
|
15 |
model = genai.GenerativeModel('gemini-pro')
|
|
|
30 |
except Exception as e:
|
31 |
return [("Error:", str(e))] # Return error message if query fails
|
32 |
|
33 |
+
# Define prompt
|
34 |
prompt = """
|
35 |
You are an expert in SQL query generation. Your task is to convert natural language questions into valid SQL queries based on the given database schema.
|
36 |
|
|
|
53 |
Output: SELECT NAME FROM STUDENT_INFO WHERE SECTION = 'Data Science';
|
54 |
"""
|
55 |
|
56 |
+
# Streamlit App
|
57 |
st.set_page_config(page_title="SQL Query Generator")
|
58 |
st.header("Gemini App To Retrieve SQL Data")
|
59 |
|
|
|
60 |
question = st.text_input("Enter your question:", key="input")
|
61 |
submit = st.button("Generate SQL Query")
|
62 |
|
63 |
+
# If submit is clicked
|
64 |
if submit:
|
65 |
sql_query = get_gemini_response(question, prompt)
|
66 |
st.subheader("Generated SQL Query")
|
67 |
st.code(sql_query, language="sql") # Show SQL query
|
68 |
|
|
|
69 |
response = read_sql_query(sql_query, "student.db")
|
|
|
|
|
|
|
|