Register AI models|V5.0.1|OceanBase Database|docs|OceanBase Documentations

Last Updated：2026-09-04 11:28:23 Updated

This topic describes how to register AI models and their access endpoints by using the DBMS_AI_SERVICE package, so that you can use AI functions in OceanBase Database.

Notice

You do not need to register a model or endpoint when using the AI_SPLIT_DOCUMENT function.

Prerequisites

You have the required permissions for AI model operations. For details, see Permissions for AI function services.
You have obtained the API key of the third-party model service.

Templates for registering models and endpoints

Use CREATE_AI_MODEL to register a model, and then use CREATE_AI_MODEL_ENDPOINT to register an access endpoint for the model. The following examples register three model keys: ob_complete, ob_embed, and ob_rerank, for text generation (AI_COMPLETE), vector embedding (AI_EMBED), and reranking (AI_RERANK), respectively. Replace access_key with your actual API key.

Note

If you only need to use a specific type of AI function, you can register only the corresponding model and endpoint. For example, if you only use AI_COMPLETE, complete the Register the text generation model and its endpoint step below.

Register an embedding model and endpoint

For AI_EMBED.

Alibaba Cloud

Alibaba Cloud DashScope

SiliconFlow

Tencent Hunyuan

This example shows how to register an embedding model and its endpoint for Alibaba Cloud by using the OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_embed');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_embed_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_embed', '{
    "type": "dense_embedding",
    "model_name": "BAAI/bge-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_embed_endpoint', '{
    "ai_model_name": "ob_embed",
    "url": "https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-openAI"
}');

This example shows how to register an embedding model and its endpoint for Alibaba Cloud DashScope by using the non-OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_embed');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_embed_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_embed', '{
    "type": "dense_embedding",
    "model_name": "BAAI/bge-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_embed_endpoint', '{
    "ai_model_name": "ob_embed",
    "url": "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-dashscope"
}');

This example shows how to register an embedding model and its endpoint for SiliconFlow.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_embed');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_embed_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_embed', '{
    "type": "dense_embedding",
    "model_name": "BAAI/bge-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_embed_endpoint', '{
    "ai_model_name": "ob_embed",
    "url": "https://api.siliconflow.cn/v1/embeddings",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "siliconflow"
}');

This example shows how to register an embedding model and its endpoint for Tencent Hunyuan by using the OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_embed');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_embed_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_embed', '{
    "type": "dense_embedding",
    "model_name": "BAAI/bge-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_embed_endpoint', '{
    "ai_model_name": "ob_embed",
    "url": "https://api.hunyuan.cloud.tencent.com/v1/embeddings",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "hunyuan-openAI"
}');

Register text generation models and endpoints

For AI_COMPLETE and AI_PROMPT.

Alibaba Cloud

Alibaba Cloud DashScope

DeepSeek

SiliconFlow

Tencent Hunyuan

This example shows how to register a text generation model and its endpoint for Alibaba Cloud by using the OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_complete', '{
    "type": "completion",
    "model_name": "THUDM/GLM-4-9B-0414"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_complete_endpoint', '{
    "ai_model_name": "ob_complete",
    "url": "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-openAI"
}');

This example shows how to register a text generation model and its endpoint for Alibaba Cloud DashScope by using the non-OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_complete', '{
    "type": "completion",
    "model_name": "THUDM/GLM-4-9B-0414"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_complete_endpoint', '{
    "ai_model_name": "ob_complete",
    "url": "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-dashscope"
}');

This example shows how to register a text generation model and its endpoint for DeepSeek.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_complete', '{
    "type": "completion",
    "model_name": "THUDM/GLM-4-9B-0414"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_complete_endpoint', '{
    "ai_model_name": "ob_complete",
    "url": "https://api.deepseek.com/chat/completions",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "deepseek"
}');

This example shows how to register a text generation model and its endpoint for SiliconFlow.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_complete', '{
    "type": "completion",
    "model_name": "THUDM/GLM-4-9B-0414"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_complete_endpoint', '{
    "ai_model_name": "ob_complete",
    "url": "https://api.siliconflow.cn/v1/chat/completions",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "siliconflow"
}');

This example shows how to register a text generation model and its endpoint for Tencent Hunyuan by using the OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_complete', '{
    "type": "completion",
    "model_name": "THUDM/GLM-4-9B-0414"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_complete_endpoint', '{
    "ai_model_name": "ob_complete",
    "url": "https://api.hunyuan.cloud.tencent.com/v1/chat/completions",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "hunyuan-openAI"
}');

Register a reranking model and endpoint

For AI_RERANK.

Alibaba Cloud DashScope

SiliconFlow

This example shows how to register a reranking model and its endpoint for Alibaba Cloud DashScope by using the non-OpenAI-compatible format.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_rerank');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_rerank_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_rerank', '{
    "type": "rerank",
    "model_name": "BAAI/bge-reranker-v2-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_rerank_endpoint', '{
    "ai_model_name": "ob_rerank",
    "url": "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-dashscope"
}');

This example shows how to register a reranking model and its endpoint for SiliconFlow.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_rerank');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_rerank_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_rerank', '{
    "type": "rerank",
    "model_name": "BAAI/bge-reranker-v2-m3"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_rerank_endpoint', '{
    "ai_model_name": "ob_rerank",
    "url": "https://api.siliconflow.cn/v1/rerank",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "siliconflow"
}');

Register a multimodal image model

Notice

Image embedding and image understanding are supported starting from V5.0.1.

As with a text model, first use CREATE_AI_MODEL to register the model, and then use CREATE_AI_MODEL_ENDPOINT to register its endpoint. The following example uses Alibaba Cloud DashScope in the OpenAI-compatible format. Replace access_key with your actual API key.

Register an image embedding model and its endpoint

For AI_EMBED image embedding.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_vl_embed');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_vl_embed_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_vl_embed', '{
    "type": "dense_embedding",
    "model_name": "qwen2.5-vl-embedding"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_vl_embed_endpoint', '{
    "ai_model_name": "ob_vl_embed",
    "url": "https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-openAI"
}');

The following examples use an image URL and Base64-encoded binary image data:

-- Replace the image URL with the actual image URL.
SET @img_url = 'https://example.com/image.jpg';
-- Embed an image URL.
SELECT AI_EMBED('ob_vl_embed', @img_url, '{"type":"image"}');

-- Use Base64-encoded binary image data.
SET @img_base64 = 'xxxxxxxxxxxxxxxxxxxxxxxxxxx';
-- Embed binary image data.
SELECT AI_EMBED('ob_vl_embed', FROM_BASE64(@img_base64), '{"type":"image"}');

Register an image understanding model and its endpoint

For AI_COMPLETE and AI_PROMPT image understanding.

CALL DBMS_AI_SERVICE.DROP_AI_MODEL ('ob_vl_complete');
CALL DBMS_AI_SERVICE.DROP_AI_MODEL_ENDPOINT ('ob_vl_complete_endpoint');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL(
'ob_vl_complete', '{
    "type": "completion",
    "model_name": "qwen3.5-plus"
}');

CALL DBMS_AI_SERVICE.CREATE_AI_MODEL_ENDPOINT (
'ob_vl_complete_endpoint', '{
    "ai_model_name": "ob_vl_complete",
    "url": "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
    -- To be replaced with the actual access_key
    "access_key": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "provider": "aliyun-openAI"
}');

Example calls are as follows:

-- Understand a single image from an image URL.
SELECT AI_COMPLETE(
  'ob_vl_complete',
  AI_PROMPT('Please describe this image {img_0}', @img_url)
);

-- Understand a single image from Base64-encoded data.
SELECT AI_COMPLETE(
  'ob_vl_complete',
  AI_PROMPT('Please describe this image {img_0}', FROM_BASE64(@img_base64))
);

References

Quick start with AI function service: Steps to run the first example after registration.
Use AI function service and examples: Syntax and more examples for each AI function.
DBMS_AI_SERVICE package: Complete parameter description for AI models and endpoints.

OceanBase

Customer Stories

Documentation

Register AI models

Notice

Prerequisites

Templates for registering models and endpoints

Note

Register an embedding model and endpoint

Register text generation models and endpoints

Register a reranking model and endpoint

Register a multimodal image model

Notice

Register an image embedding model and its endpoint

Register an image understanding model and its endpoint

References