jeecgboot / jeecgboot/JeecgBoot

AI对话功能调用同样的本地模型比本地ollama客户端慢太多

Open
#9,715 2 comments 0 reactions 0 assignees View on GitHub
bug
Dominant language
Java
Stars
47.8k
Forks
16.2k
PR merge metrics
No merged PRs in 30d

Description

##### 版本号:3.9.2

##### 分支:master

##### 问题描述:AI对话功能使用本地ollama部署的gemma4:26b模型,在同一个电脑中jeecg网页端的回复等待时间远大于在ollama客户端的回复时间,集成进jeecg后回复的等待时间更长更慢了,麻烦看一下。

##### 错误截图:
如图为本地ollama客户端的思考等待时间:
Image

下面是集成进jeecg的截图,我计时大概思考等待时间大概在35秒左右,是本地客户端思考时间的3倍多,问其他问题也是同样问题,jeecg的思考等待时间远大于在客户端的时间。

Image

Image

#### 友情提示:
- 未按格式要求发帖、描述过于简单的,会被直接删掉;
- 描述问题请图文并茂,方便我们理解并快速定位问题;
- 如果使用的不是master,请说明你使用的分支;

Contributor guide

No contributing guide indexed for this repository

Research direction

No source file or test is named in the report. Start by reproducing the same gemma4:26b request through the Jeecg web interface and the local Ollama client on the reported 3.9.2 master setup, then trace the AI chat integration path to compare their waiting times. Done means identifying and correcting the integration-specific delay, with comparable response timing confirmed.

Written by the indexing model from the issue text.

Assessment

Tech stack
java, ollama
Domain
ai, backend, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.