GitHub Copilot
To use GitHub Copilot as an AI provider in CloudBeaver, configure it as follows:
- As an administrator, sign in to your GitHub account
- Go to the GitHub Copilot page and activate a free trial or subscription
- In CloudBeaver, go to AI Settings -> Profiles, click Create new profile, and choose GitHub Copilot as the engine
- Get your Copilot access token
- Paste the token into the Copilot Access token field
- Choose the model
- Save changes
Model settings¶
| Setting | Description | default |
|---|---|---|
| Copilot Access token | Enter your Copilot access token. | |
| Model | Choose the AI model. | gpt-3.5-turbo |
| 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 |
| Context window size | Choose the context size between 2048 and 32768. 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. |
16384 |
| Authentication URL | The URL used to authenticate with GitHub Copilot. | https://api.github.com |
| Request timeout (sec) | Set the maximum time to wait for a response from the AI provider. | 30 |
| Write AI queries to debug log | Logs your AI requests. These entries go to the server log. | false |