Integrate Slack with Genie natively using Databricks Apps in 30mins!

Integrate Slack with Genie natively using Databricks Apps in 30min!

A Slack bot that integrates with Databricks Genie using conversational APIs, allowing users to query and interact with their data directly from Slack.

Features

• 🤖 Conversational AI: Ask questions about your data in natural language

• 💬 Threaded Conversations: Maintain context across multiple messages in Slack threads

• 📊 Rich Responses: Get query results and reasoning directly in Slack

• 🔄 Real-time Updates: Socket mode for instant message handling

• 🔐 Secure: Natively developed within the Databricks ecosystem and governed with Unity Catalog

Architecture

Prerequisites

1. Databricks Workspace

   • Active Databricks workspace

   • Genie space ID

2. Slack App

   • Slack workspace with admin access

   • Slack app created with socket mode enabled

Setup Instructions

1. Slack App Setup

1. Go to Slack API Apps

2. Click Create New App → From scratch

3. Name your app (e.g., “Databricks Genie Bot”) and select your workspace

Configure OAuth & Permissions

Under OAuth & Permissions, add these bot token scopes:

• app_mentions:read

• chat:write

• im:history

• im:read

• im:write

Enable Socket Mode

1. Go to Socket Mode in your app settings

2. Enable Socket Mode

3. Name Token (e.g., “Databricks Genie Bot Token”) and generate an app-level token with connections:write scope

4. Save the token (starts with xapp-)

Subscribe to Events

Under Event Subscriptions:

1. Enable Events

2. Subscribe to bot events:

   • app_mention

   • message.im

Install App to Workspace

1. Go to Install App

2. Click Install to Workspace

3. Authorize the app

4. Save the Bot User OAuth Token (starts with xoxb-)

Note Slack Signing Secret

To find your Slack signing secret:

1. Go to your Slack app settings

2. Navigate to Basic Information

3. Find Signing Secret under App Credentials

2. Databricks Application Setup

Create a new Databricks App

1. Go to Databricks console, Compute, and create a new App using Create custom app

2. Name Databricks App (e.g., “databricks-genie-bot-app”)

3. Wait for the App to be ready and note the service principal from the Authorization tab, App authorization

Note Genie Space ID

Navigate to the specific Genie space within your Databricks workspace. The space ID can also be found and copied from the Settings tab of that Genie space.

Prepare Application Code

Download the application code and make the necessary updates to the config values in app.yaml. Download all files from repo: https://github.com/adgitdemo/ad_databricks/tree/main/genie-slack-app

Grant Permissions to Service Principal

Note that the Service Principal is created automatically for the Databricks app from the above step, and the following grants are performed.

1. Grant Genie Access with “Can Run” permissions

2. Grant Warehouse access with “Can Use” permissions

3. Grant access to Unity Catalog tables/views used in Genie Space via Unity Catalog or SQL

Deploy Application to Databricks Apps

You can create or select an existing folder in the workspace where you want to upload application code and application files.

Go to the Databricks App and deploy the application from the folder where all the application code is stored.

Wait for the deployment to finish, and once you see the application is running, it's time to talk to Genie from Slack!

Usage

In Slack

1. Direct Messages:

   • Send a DM to your bot

   • Ask questions like: “Show me sales data for last month”

2. Channel Mentions:

   • Invite the bot to a channel: /invite @YourBotName

   • Mention the bot: @YourBotName what are the top 10 customers?

3. Threaded Conversations:

   • Continue asking questions in a thread

   • The bot maintains conversation context within threads

Demo Time

Start chatting with Databricks Genie Bot

It will respond in a thread,

Let’s ask a real question,

You should give feedback to Genie Bot, and it will get recorded in Databricks Genie, so that the author of Genie Space will review it!