GitHub Copilot
To use GitHub Copilot as an AI provider in DBeaver, configure it as follows:
- Sign in to your GitHub account
- Go to the GitHub Copilot page and activate a free trial or subscription
- In DBeaver, go to Window -> Preferences -> Model configurations
- Click + and choose GitHub Copilot as the engine to create a profile
- If you use GitHub Enterprise, enter your GHE hostname in Authentication Provider before authorizing
- Click Authorize to get your OAuth code
- Click Copy and Open - this opens the GitHub authorization page
- Paste the code, confirm access, and authorize the GitHub Copilot plugin
-
After completing the OAuth flow, the access token will be filled in automatically in DBeaver
Important
The token is visible only once. After you save the changes, it’ll be masked for security.
-
Choose the model
- Click Test connection to verify that the key and model work correctly
- Apply the changes
Engine settings¶
| Setting | Description | Default |
|---|---|---|
| Access token | Input your secret key from the provider platform. Can also be acquired by signing in via OAuth using the Authorize button. | |
| Authentication URL | Your GitHub Enterprise Cloud hostname (for example your-org.ghe.com) to authenticate against, instead of the public github.com. Leave empty to use github.com. |
|
| Model | Choose the AI model. Models are loaded dynamically and can be refreshed using the Refresh models button next to the field. | |
| Context window size | A larger number allows the AI to use more data for better answers but may slow down response time. Choose based on your balance of accuracy and speed. | |
| Temperature | Control AI's creativity from 0.0 (more precise) to 0.9 (more diverse). Note that higher temperature can lead to less predictable results. |
0.0 |
| Request timeout (sec) | Maximum time DBeaver waits for a response from the AI engine before the request fails. | 30 |
| Write AI queries to debug log | Logs your AI requests. For more details on logging, see Log Viewer. | disabled |