New dpcs structure and dataset i18n (#551)

* perf: check balance

* md

* lock way

* i18n

* docs

* doc

* i18n

* update doc

* feat: one link sync

* feat: one link sync

* feat: one link sync

* feat: one link sync

* feat: one link sync

* feat: one link sync

* feat: one link sync
This commit is contained in:
Archer
2023-12-04 21:37:07 +08:00
committed by GitHub
parent c3ae38df8b
commit 62e87551ac
141 changed files with 961 additions and 469 deletions

View File

@@ -0,0 +1,24 @@
---
title: '升级到 V4.2.1'
description: 'FastGPT 从旧版本升级到 V4.2.1 操作指南'
icon: 'upgrade'
draft: false
toc: true
weight: 847
---
私有部署,如果添加了配置文件,需要在配置文件中修改 `VectorModels` 字段。增加 defaultToken 和 maxToken分别对应直接分段时的默认 token 数量和该模型支持的 token 上限 (通常不建议超过 3000)
```json
"VectorModels": [
{
"model": "text-embedding-ada-002",
"name": "Embedding-2",
"price": 0,
"defaultToken": 500,
"maxToken": 3000
}
]
```
改动目的是,我们认为不需要留有选择余地,选择一个最合适的模型去进行任务即可。