Release Notes and Announcements

Release Notes

Product Announcements

Product Introduction

Overview

Features

Strengths

Scenarios

Information Security

Regions and AZs

Product Feature List

Large version lifecycle description

MSSQL Compatible Version

Billing

Billing Overview

Instance Type and Specification

Purchase Methods

Refund

Overdue Payments

Backup Space Billing

Database Audit Billing Overview

Getting Started

Creating TencentDB for PostgreSQL Instance

Connecting to TencentDB for PostgreSQL Instance

Managing TencentDB for PostgreSQL Instance

Importing Data

Migrating Data with DTS

Kernel Version Introduction

Kernel Version Overview

Kernel Version Release Notes

Viewing Kernel Version

Proprietary Kernel Features

Database Audit

Audit Service Description

Activating Audit Service

View Audit Logs

Modify audit services

Audit Performance Description

User Guide

Instance Management

Upgrading Instance

CPU Elastic Scaling

Read-Only Instance

Account Management

Database Management

Parameter Management

Log Management and Analysis

Backup and Restoration

Data Migration

Extension Management

Network Management

Access Management

Data Security

Tenant and Resource Isolation

Security Groups

Monitoring and Alarms

Tag

AI Practice

Using the Tencentdb_ai Plug-In to Call Large Models

Building Ai Applications with the Tencentdb Ai Plug-In

Combining Supabase to Quickly Build Backend Service Based on TencentDB for PostgreSQL

Use Cases

postgres_fdw Extension for Cross-database Access

Automatically Creating Partition in PostgreSQL

Searching in High Numbers of Tags Based on pg_roaringbitmap

Querying People Nearby with One SQL Statement

Configuring TencentDB for PostgreSQL as GitLab's External Data Source

Supporting Tiered Storage Based on cos_fdw Extension

Implement Read/Write Separation via pgpool

Implementing Slow SQL Analysis Using the Auto_explain Plugin

Using pglogical for Logical Replication

Using Debezium to Collect PostgreSQL Data

Set Up a Remote Disaster Recovery Environment for PostgreSQL Locally on CVM

Read-Only Instance and Read-Only Group Practical Tutorial

How to Use SCF for Scheduled Database Operations

Fix Table Bloat

Performance White Paper

Test Methods

Test Results

API Documentation

History

Introduction

API Category

Making API Requests

Instance APIs

Read-Only Instance APIs

Backup and Recovery APIs

Parameter Management APIs

Security Group APIs

Performance Optimization APIs

Account APIs

Specification APIs

Network APIs

Data Types

Error Codes

FAQs

Service Agreement

Service Level Agreement

Glossary

Using the Tencentdb_ai Plug-In to Call Large Models

PDF

포커스 모드

폰트 크기

마지막 업데이트 시간: 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=> 

도움말 및 지원

문제 해결에 도움이 되었나요?

더 자세한 내용은 문의하기 또는 티겟 제출 을 통해 문의할 수 있습니다.

피드백

tencent cloud

TencentDB for PostgreSQL

Using the Tencentdb_ai Plug-In to Call Large Models

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

도움말 및 지원