获取知识库文件的分段与清洗规则

开发中

GET

/ai-portal/proxy/console/api/datasets/process-rule

请求参数

Query 参数

Header 参数

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request GET 'http://172.20.238.8:48806/ai-portal/proxy/console/api/datasets/process-rule?document_id=921c2266-3588-46ae-a098-b7208ca84578' \
--header 'Pragma: no-cache' \
--header 'authorization: debug userId=19645' \
--header 'tenantId: 0' \
--header 'content-type: application/json' \
--data-raw ''

返回响应

🟢200成功

application/json

Body

示例

{"mode": "automatic", "rules": {"pre_processing_rules": [{"id": "remove_extra_spaces", "enabled": true}, {"id": "remove_urls_emails", "enabled": false}], "segmentation": {"delimiter": "\n", "max_tokens": 500, "chunk_overlap": 50}}}

修改于 2024-08-14 09:02:56

获取分段与清洗规则

保存文档的分段信息