Go: add cli command, list dataset documents (#14948)

### What problem does this PR solve?
```
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
| created_at          | id                               | meta_fields | name            | size    | status | type |
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
| 2026-05-08 19:35:08 | f6aa38bb4ad111f1ba6338a74640adcc | map[]       |  abc.pdf        | 3387987 | 1      | pdf  |
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
```

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2026-05-15 14:00:45 +08:00
committed by GitHub
parent 1a25191b13
commit 335dd5a263
12 changed files with 225 additions and 67 deletions

View File

@@ -30,7 +30,7 @@ import (
// DatasetsHandler handles the RESTful dataset endpoints.
type DatasetsHandler struct {
datasetsService *service.DatasetsService
datasetsService *service.DatasetService
}
type listDatasetsExt struct {
@@ -40,7 +40,7 @@ type listDatasetsExt struct {
}
// NewDatasetsHandler creates a new datasets handler.
func NewDatasetsHandler(datasetsService *service.DatasetsService) *DatasetsHandler {
func NewDatasetsHandler(datasetsService *service.DatasetService) *DatasetsHandler {
return &DatasetsHandler{datasetsService: datasetsService}
}

View File

@@ -32,12 +32,14 @@ import (
// DocumentHandler document handler
type DocumentHandler struct {
documentService *service.DocumentService
datasetService *service.DatasetService
}
// NewDocumentHandler create document handler
func NewDocumentHandler(documentService *service.DocumentService) *DocumentHandler {
func NewDocumentHandler(documentService *service.DocumentService, datasetService *service.DatasetService) *DocumentHandler {
return &DocumentHandler{
documentService: documentService,
datasetService: datasetService,
}
}
@@ -198,35 +200,22 @@ func (h *DocumentHandler) DeleteDocument(c *gin.Context) {
}
// ListDocuments document list
// @Summary Document List
// @Description Get paginated document list
// @Tags documents
// @Accept json
// @Produce json
// @Param page query int false "page number" default(1)
// @Param page_size query int false "items per page" default(10)
// @Success 200 {object} map[string]interface{}
// @Router /api/v1/document/list [post]
func (h *DocumentHandler) ListDocuments(c *gin.Context) {
_, errorCode, errorMessage := GetUser(c)
if errorCode != common.CodeSuccess {
jsonError(c, errorCode, errorMessage)
datasetID := c.Param("dataset_id")
pageStr := c.Query("page")
pageSizeStr := c.Query("page_size")
page, _ := strconv.Atoi(pageStr)
pageSize, _ := strconv.Atoi(pageSizeStr)
userID := c.GetString("user_id")
if !h.datasetService.Accessible(datasetID, userID) {
jsonError(c, common.CodeAuthenticationError, "No authorization.")
return
}
kbID := c.Query("kb_id")
if kbID == "" {
c.JSON(http.StatusOK, gin.H{
"code": 1,
"message": "Lack of KB ID",
"data": false,
})
return
}
page, _ := strconv.Atoi(c.DefaultQuery("page", "1"))
pageSize, _ := strconv.Atoi(c.DefaultQuery("page_size", "10"))
if page < 1 {
page = 1
}
@@ -235,7 +224,7 @@ func (h *DocumentHandler) ListDocuments(c *gin.Context) {
}
// Use kbID to filter documents
documents, total, err := h.documentService.ListDocumentsByKBID(kbID, page, pageSize)
documents, total, err := h.documentService.ListDocumentsByDatasetID(datasetID, page, pageSize)
if err != nil {
c.JSON(http.StatusOK, gin.H{
"code": 1,
@@ -482,4 +471,37 @@ func (h *DocumentHandler) SetMeta(c *gin.Context) {
"message": "success",
"data": true,
})
}
}
type ParseDocumentRequest struct {
Documents []string `json:"documents" binding:"required"`
DatasetID string `json:"dataset_id" binding:"required"`
}
func (h *DocumentHandler) ParseDocuments(c *gin.Context) {
var req ParseDocumentRequest
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusOK, gin.H{
"code": common.CodeBadRequest,
"message": err.Error(),
})
return
}
userID := c.GetString("user_id")
if !h.datasetService.Accessible(req.DatasetID, userID) {
jsonError(c, common.CodeAuthenticationError, "No authorization to access the dataset.")
return
}
err := h.documentService.ParseDocuments(req.DatasetID, userID, req.Documents)
if err != nil {
jsonError(c, common.CodeExceptionError, err.Error())
return
}
c.JSON(http.StatusOK, gin.H{
"code": 0,
"message": "success",
})
}