OpenAI
To use OpenAI as an AI provider in Team Edition, configure it as follows:
- As an administrator, sign up on the OpenAI platform.
- Navigate to the API Keys section and generate a new secret key.
- Insert this key into Team Edition's Engine Settings.
- Choose the model.
- Save changes.
Note
OpenAI services are available in specific countries. Consult the supported countries list to verify availability in your location.
Engine settings¶
| Setting | Description | Default |
|---|---|---|
| API token | Input your secret key from the OpenAI platform. | |
| Endpoint | The address where requests to the AI service are sent. Normally this is filled automatically for the selected provider. Change it only if you use a custom endpoint. | https://api.openai.com/v1/ |
| Model | Choose the AI model. | gpt-4o |
| 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 |
| Write AI queries to debug log | Logs your AI requests. These entries go to the server log. | false |
| 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. |
12800 |
| Use legacy API | Use the legacy OpenAI chat API (/v1/chat/completions). May be useful if you’re using an OpenAI-compatible engine that doesn’t support the newer /v1/responses endpoint. |
false |