GitHub Copilot

The Spice AI GitHub Copilot Extension makes it easy to access and chat with external data in GitHub Copilot, enhancing AI-assisted research, Q&A, code, and documentation suggestions for greater accuracy.

Access structured and unstructured data from any Spice data source like GitHub, PostgreSQL, MySQL, Snowflake, Databricks, GraphQL, data lakes (S3, Delta Lake, OneLake), HTTP(s), SharePoint, and even FTP.

Some example prompts:

• @spiceai What documentation is relevant to this file?

• @spiceai Write documentation about the user authentication issue

• @spiceai Who are the top 5 committers to this repository?

• @spiceai What are the latest error logs from my web app?

Installing the Spice.ai for GitHub Copilot Extension

To install the extension, visit the GitHub Marketplace and search for Spice.ai.

Scroll down, and click Install it for free.

Configuring the extension

1. Once installed, open Copilot Chat and type @spiceai. Press enter.

1. A prompt will appear to connect to the Spice.ai Cloud Platform.

1. You will need to authorize the extension. Click Authorize spiceai.

1. To create an account on the Spice.ai Cloud Platform, click Authorize Spice AI Platform.

1. Once your account is created, you can configure the extension. Select from a set of ready-to-use datasets to get started. You can configure other datasets after setup.

1. The extension will take up to 30 seconds to deploy and load the initial dataset.

1. When complete, proceed back to GitHub Copilot Chat.

Chatting with Copilot Chat

Start a new chat

To chat with the Spice.ai for GitHub Copilot extension, prefix the message with @spiceai

Querying which datasets are available

To list the datasets available to Copilot, try @spiceai What datasets do I have access to?

Querying data using SQL

Reset the Copilot instance