Custom OpenAI-Compatible Model Configuration
This section explains how to configure a custom model that uses an OpenAI-compatible API in AskSenseOps.
Prerequisites
Before configuring the model, ensure that the provider or service exposes an OpenAI-compatible API endpoint and that you have the required API credentials.
Adding a Custom Model
- Open AskSenseOps.
- Navigate to the model configuration section.
- Click Add Model.
- Enter the required configuration details.
- Test the configuration and save the model.
Basic Info
| Field | Description | Required |
|---|---|---|
| Display Name | Enter a name to identify the model in AskSenseOps. | Yes |
| Provider | Select Custom (OpenAI-Compatible). | Yes |
Credentials
| Field | Description | Required |
|---|---|---|
| API Key | Enter the API key required to authenticate with the custom endpoint. | Yes |
Model Configuration
| Field | Description | Required |
|---|---|---|
| Model Name / ID | Enter the model identifier expected by the endpoint. | Yes |
| Endpoint URL | Enter the URL of the OpenAI-compatible API endpoint. | Yes |
Use Fetch models, when available, to retrieve the models exposed by the configured endpoint.
Custom Headers
Custom headers are optional and can be used when the endpoint or gateway requires additional headers.
- Under Custom Headers (Optional), click + Add.
- Enter the required header name and value.
- Add additional headers if needed.
Examples shown in the interface include x-openai-token, x-fabrix-client, and x-llm-model-id.
If a custom header carries the authentication token, the API Key field can be left empty.
Testing and Saving the Model
After entering the configuration details:
- Review the display name, provider, API key, model identifier, and endpoint URL.
- Click Test to verify the configuration.
- If the test succeeds, click Save Model to save the configuration.
If the test fails, verify the API key, model identifier, endpoint URL, and any custom headers required by the endpoint.