50 lines
1.6 KiB
Go
50 lines
1.6 KiB
Go
package entity
|
|
|
|
import (
|
|
"rag/consts/document"
|
|
|
|
"gitea.com/red-future/common/beans"
|
|
"github.com/pgvector/pgvector-go"
|
|
)
|
|
|
|
type documentChunkCol struct {
|
|
beans.SQLBaseCol
|
|
Status string
|
|
VectorStatus string
|
|
DatasetId string
|
|
DocumentId string
|
|
Content string
|
|
ContentHash string
|
|
ChunkIndex string
|
|
Vector string
|
|
Metadata string
|
|
}
|
|
|
|
var DocumentChunkCol = documentChunkCol{
|
|
SQLBaseCol: beans.DefSQLBaseCol,
|
|
Status: "status",
|
|
VectorStatus: "vector_status",
|
|
DatasetId: "dataset_id",
|
|
DocumentId: "document_id",
|
|
Content: "content",
|
|
ContentHash: "content_hash",
|
|
ChunkIndex: "chunk_index",
|
|
Vector: "vector",
|
|
Metadata: "metadata",
|
|
}
|
|
|
|
// DocumentChunk 文档切分块实体
|
|
type DocumentChunk struct {
|
|
beans.SQLBaseDO `orm:",inline"`
|
|
|
|
Status document.Status `orm:"status" json:"status" dc:"状态"`
|
|
VectorStatus document.VectorStatus `orm:"vector_status" json:"vectorStatus" dc:"向量状态"`
|
|
DatasetId int64 `orm:"dataset_id" json:"datasetId" dc:"数据集ID"`
|
|
DocumentId int64 `orm:"document_id" json:"documentId" dc:"文件ID"`
|
|
Content string `orm:"content" json:"content" dc:"切分块内容"`
|
|
ContentHash string `orm:"content_hash" json:"contentHash" dc:"切分块内容哈希"`
|
|
ChunkIndex int64 `orm:"chunk_index" json:"chunkIndex" dc:"切分块索引"`
|
|
Vector pgvector.Vector `orm:"vector" json:"vector" dc:"向量"`
|
|
Metadata map[string]interface{} `orm:"metadata" json:"metadata" dc:"元信息"`
|
|
}
|