Using the Tencentdb_ai Plug-In to Call Large Models

Last updated: 2025-11-07 17:27:28
Using the Tencentdb_ai Plug-In to Call Large Models
Last updated: 2025-11-07 17:27:28
Currently, both basic large models and AI application development are advancing rapidly. TencentDB for PostgreSQL provides the tencentdb_ai plug-in, enabling easy API calls to accessible large models over the network within TencentDB for PostgreSQL instances, supporting application development in various scenarios. This plug-in supports instances running PostgreSQL 17.
Note:
Using tencentdb_ai is the premise for an instance of PostgreSQL 17 already created.
Creating the tencentdb_ai plug-in will associate the creation of the pgcrypto plug-in. Please be informed.
TencentDB AI Plug-In Function Description
Adding a Model
add_model function defined as follows:
tencentdb_ai.add_model(
    model_name NAME,
    version TEXT,
    region TEXT,
    json_path JSONPATH
);
The parameters are explained as follows:
model_name: model name, such as hunyuan-lite, deepseek-r1
version: common parameter of this model version. Leave it blank if version is not required.
region: common parameter of this model region. Leave it blank if region is not required.
json_path: specifies how to extract the JSON response from this model during a call. It is equivalent to performing the jsonb_path_query_first function on the model output. If this parameter is not set, the original response of the model is output by default.
Viewing Registered Models
list_models function defined as follows:
tencentdb_ai.list_models(void);
Updating a Model
update_model_attr function defined as follows:
tencentdb_ai.update_model_attr(
    model_name NAME,
    attr_name text,
    attr_value text
);
The parameters are explained as follows:
model_name: model name.
attr_name: model attribute to be updated. Updatable model attributes include version, region, json_path, SecretId, SecretKey.
attr_value: attribute's value to be updated.
For specific SecretId and SecretKey, check Cloud Access Management.
Deleting a Model
delete_model function defined as follows:
tencentdb_ai.delete_model(
    model_name NAME
);
The parameters are explained as follows:
model_name: model name.
Model Invocation
The call_model function is defined as follows:
tencentdb_ai.call_model(
    model_name NAME,
    common_params TEXT[],
    api_params TEXT[]
);
The parameters are explained as follows:
model_name: model name.
common_params: common parameters required to invoke the model, such as ARRAY['Action: ChatCompletions', 'Version: 2023-09-01']
api_params: proprietary parameters required to invoke the model, such as ARRAY['"Stream": false', '"Model": "hunyuan-lite"', '"Messages": [{"Role": "user", "Content": "Hello"}]']
In addition to using the call_model function for model invocation, you can also use the following APIs for model invocation in specific scenarios.
Fixed Scenario API
Dialogue
chat_completions function definition is as follows:
tencentdb_ai.chat_completions(
    model_name  NAME,
    content TEXT,
    args TEXT[] default NULL
);
The parameters are explained as follows:
model_name: model name.
content: conversation content.
args: other parameters to invoke the model, defaults to NULL.
Sample call:
SELECT tencentdb_ai.chat_completions('hunyuan-lite', 'Hello');
                                                                                                                                                                                          
         chat_completions                                                                                                                                                                 
                                  
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
----------------------------------
 {"Response":{"RequestId":"*******-****-****-****-***********","Note":"The above content is AI generation and does not mean the developer standpoint, do not delete or modify this tag","Choices":[{"Index":0,"Message":{"Role":"assistant","Co
Hello. Glad to chat with you. What would you like to share today?
nTokens":17,"TotalTokens":20}}}
(1 row)
Text to Vector
get_embedding function definition as follows:
tencentdb_ai.get_embedding(
    model_name NAME, 
    content TEXT[]
);
The parameters are explained as follows:
model_name: model name.
content: conversion content.
Sample call:
damoxing1=> SELECT tencentdb_ai.get_embedding('hunyuan-embedding',ARRAY['Hello', 'PostgreSQL']);
Text Sorting
run_rerank function defined as follows:
tencentdb_ai.run_rerank(
    model_name NAME, 
    query TEXT, 
    documents TEXT[], 
    args TEXT[] DEFAULT NULL
);
The parameters are explained as follows:
model_name: model name.
query: text sorting issue.
documents: content to be sorted.
args: specified parameters for a specific model.
damoxing1=> SELECT COUNT(*) FROM tencentdb_ai.run_rerank('lke-reranker-base', 'knowledge engine large model', ARRAY['HunYuan Large Model', 'Tencent knowledge engine']);
 count 
-------
     2
(1 row)
Generating Text From Images
The function definition of image_to_text is as follows:
tencentdb_ai.image_to_text
(
    model_name NAME, 
    query TEXT, 
    image TEXT, 
    args TEXT[] DEFAULT NULL
);
The parameters are explained as follows:
model_name: model name
query: image-to-text problem
image: image address
args: specific model parameters
Plugin Usage Example
The plugin use process is described as follows:
1. Create plugin
damoxing=> CREATE EXTENSION tencentdb_ai CASCADE;
NOTICE:  installing required extension "pgcrypto"
CREATE EXTENSION
Check plugin creation completed
damoxing=> SELECT * FROM pg_extension;
  oid  |   extname    | extowner | extnamespace | extrelocatable | extversion | extconfig | extcondition 
-------+--------------+----------+--------------+----------------+------------+-----------+--------------
 14275 | plpgsql      |       10 |           11 | f              | 1.0        |           | 
 16440 | pgcrypto     |    16437 |         2200 | t              | 1.3        |           | 
 16477 | tencentdb_ai |    16437 |         2200 | t              | 1.0        | {16479}   | {""}
(3 rows)
2. Adding a large model
damoxing=> SELECT tencentdb_ai.add_model('hunyuan-lite','2023-09-01', NULL, NULL);
 add_model 
-----------
 
(1 row)
3. Add SecretId and SecretKey for large model API calls
For specific SecretId and SecretKey, check Cloud Access Management.
damoxing=> SELECT tencentdb_ai.update_model_attr('hunyuan-lite', 'SecretId', 'AKID***************');
 update_model_attr 
-------------------
 
(1 row)
damoxing=> SELECT tencentdb_ai.update_model_attr('hunyuan-lite', 'SecretKey', '********************');
 update_model_attr 
-------------------
 
(1 row)
4. View the current added model list
damoxing=> SELECT * FROM tencentdb_ai.list_models();
-[ RECORD 1 ]--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
model_name | hunyuan-lite
json_path  | 
secretid   | ***************************
secretkey  | ***************************
version    | 
region     | 
id_random  | 516234453022
key_random | 134577899689
5. Call a large model
In a chat scenario, you can use the call_model API.
damoxing=> SELECT tencentdb_ai.call_model('hunyuan-lite',
                            ARRAY['Action: ChatCompletions', 'Version: 2023-09-01'],
                            ARRAY['"Stream": false', '"Model": "hunyuan-lite"', '"Messages": [{"Role": "user", "Content": "Hello"}]']); 
                                                                                                                                      
                                                                                                  call_model                          
                                                                                                                                      
                                                                        
--------------------------------------------------------------------------------------------------------------------------------------
--------------------------------------------------------------------------------------------------------------------------------------
--------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------
 {"Response":{"RequestId":"*******-****-****-****-***********","Note":"The above content is AI generation and does not mean the developer standpoint, do not delete or modify this tag","Ch
choices":[{"Index":0,"Message":{"Role":"assistant","Content":"Hello! I'm happy to chat with you. What can I help you with? Whether it's about life, work, or learning."}}]}
study or other issues, I'll do my best to offer help."},"FinishReason":"stop"}],"Created":1739793838,"Id":"*******-****-****-****-***********
","Usage":{"PromptTokens":3,"CompletionTokens":33,"TotalTokens":36}}}
(1 row)
﻿
damoxing=> 
Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
Feedback
tencent cloud

TencentDB AI Plug-In Function Description

Adding a Model

Viewing Registered Models

Updating a Model

Deleting a Model

Model Invocation

Fixed Scenario API

Dialogue

Text to Vector

Text Sorting

Generating Text From Images

Plugin Usage Example
