Note
This view is available starting with V4.4.1.
Purpose
This view displays the AI model access information of the current tenant.
Columns
| Column | Type | Nullable | Description |
|---|---|---|---|
| ENDPOINT_ID | int(20) | NO | The unique ID of the model access information. |
| ENDPOINT_NAME | varchar(128) | NO | The unique name of the model access information. |
| AI_MODEL_NAME | varchar(128) | NO | The name of the AI model to which the access information belongs. |
| SCOPE | varchar(128) | NO | A reserved field. The default value is all. This field will be used in the future to configure model access information across regions and zones. |
| URL | varchar(2048) | NO | The URL of the model. The URL supports HTTP and HTTPS. Example: https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings. |
| ACCESS_KEY | varchar(2048) | NO | The API key used to call the model. |
| PROVIDER | varchar(128) | NO | The provider of the AI model. For example, openai, aliyun, deepseek, or ollama. This field is used to adapt the API message format in the database. If this field is empty, you must provide a UDF function. Otherwise, an error will be returned. |
| REQUEST_MODEL_NAME | varchar(128) | YES | The name of the AI model specified in the request message body. For example, bge-m3-custom. |
| PARAMETERS | varchar(2048) | YES | A reserved field. Optional parameters used to configure additional parameters for model calls, such as context_window and max_output_tokens, to support batch operations. Example: {"context_window": 128000,"max_output_tokens": 8000}. |
| REQUEST_TRANSFORM_FN | varchar(64) | YES | A reserved field. Used to construct the request data sent to the AI model. If this field is empty, the system will use the default message format based on the PROVIDER and the model type (embedding, rerank, or completion) to send the request. |
| RESPONSE_TRANSFORM_FN | varchar(64) | YES | A reserved field. Used to parse the data returned by the AI model. If this field is empty, the system will use the default response format based on the PROVIDER and the model type (embedding, rerank, or completion) to process the data. |
Sample query
Query the AI model access information of the current tenant.
obclient [oceanbase]> SELECT * FROM oceanbase.DBA_OB_AI_MODEL_ENDPOINTS;
The query result is as follows:
+-------------+--------------------+---------------+-------+-------------------+------------------------------------------------------------------+----------+--------------------+------------+----------------------+-----------------------+
| ENDPOINT_ID | ENDPOINT_NAME | AI_MODEL_NAME | SCOPE | URL | ACCESS_KEY | PROVIDER | REQUEST_MODEL_NAME | PARAMETERS | REQUEST_TRANSFORM_FN | RESPONSE_TRANSFORM_FN |
+-------------+--------------------+---------------+-------+-------------------+------------------------------------------------------------------+----------+--------------------+------------+----------------------+-----------------------+
| 1 | my_model_endpoint1 | my_ai_model_1 | ALL | your ai model url | EAF8BD8998A38C94B9EA596257E8D05CE4B8309E7134F81A78CCB59D60C39846 | openai | text-embedding-v2 | NULL | NULL | NULL |
+-------------+--------------------+---------------+-------+-------------------+------------------------------------------------------------------+----------+--------------------+------------+----------------------+-----------------------+
1 row in set