Add image index and pdf parse (#3956)

* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts
This commit is contained in:
Archer
2025-03-03 23:08:29 +08:00
committed by archer
parent 3fadabd28b
commit 139b142293
106 changed files with 2337 additions and 1454 deletions

View File

@@ -23,6 +23,7 @@ weight: 707
"systemEnv": {
"vectorMaxProcess": 15, // 向量处理线程数量
"qaMaxProcess": 15, // 问答拆分线程数量
"vlmMaxProcess": 15, // 图片理解模型最大处理进程
"tokenWorkers": 50, // Token 计算线程保持数,会持续占用内存,不能设置太大。
"pgHNSWEfSearch": 100 // 向量搜索参数。越大搜索越精确但是速度越慢。设置为100有99%+精度。
}