描述：進行文本切分和切塊向量化
請求文法
POST /v3/openapi/apps/{app_group_identity}/actions/knowledge-split注：app_group_identity表示應用程式名稱。
請求參數
SplitDoc | |||
參數名 | 參數類型 | 描述 | 備忘 |
title | String | 資料標題 | 選填 |
content | String | 處理資料內容 | 必填 |
use_embedding | Boolean | 是否需要向量化：
| 不填則為false |
model | String | 需要使用的向量化模型 | 無 |
請求體樣本
{
"title":"測試標題",
"content":"測試文本",
"use_embedding":true,
}返回參數
響應名 | 響應類型 | 描述 |
chunks | List<ChunkContext> | 切片後的文本資料對象 |
ChunkContext | ||
響應名 | 響應類型 | 描述 |
chunk_id | String | 切片id |
chunk | String | 切片後的文本資料 |
embedding | String | 向量化後的向量 |
type | String | 文本類型： 文本類型：text，圖片類型：image |
img_url | String | 若是圖片類型資料，需要有圖片的url |
響應體樣本
{
"request_id":"111111111",
"status":"OK";
"errors":[],
"result":[
{
"chunk_id":"1",
"chunk":"測試切片文本1",
"embedding":"-0.010441,-0.002826,-0.022911,0.000847,0.025610,0.019213,-0.019912,0.008210,0.011974,-0.010120,-0.003866,-0.008091,-0.006889,-0.034774,...-0.012572,0.009668,0.010963,-0.005273,-0.005072,-0.002190,-0.001554,-0.000058",
"type":"text"
},
{
"chunk_id":"2",
"chunk":"測試切片文本2",
"embedding":"-0.010441,-0.002826,-0.022911,0.000847,0.025610,0.019213,-0.019912,0.008210,0.011974,-0.010120,-0.003866,-0.008091,-0.006889,-0.034774,...-0.012572,0.009668,0.010963,-0.005273,-0.005072,-0.002190,-0.001554,-0.000058",
"type":"image",
"img_url":"http://127.0.0.1"
},
{
"chunk_id":"3",
"chunk":"測試切片文本3",
"type":"text"
}
]
}說明
文本切片向量化後的向量維度為1536維。