Get Dataset Details
Retrieve full dataset configuration details including embedding, agent, and VLM models, sync state, and caller permissions.
Endpoint Overview
- Method :
GET - Path :
/api/core/dataset/detail - Module : Datasets / Datasets
- Authentication :
Authorization: Bearer <apiKey>—Personal API Key (access scoped by team member permissions) (see API Getting Started ) - Interactive Try-It-Out : Open in Scalar API Explorer (self-hosted instances: replace the origin with
<instance>/apidoc/systemopenapi#tag/%E7%9F%A5%E8%AF%86%E5%BA%93%E7%AE%A1%E7%90%86/GET/core/dataset/detail)
Description & Notes
Retrieve full dataset configuration including model bindings, permissions, and synchronization status.
Request Parameters
Query Parameters
| Field | Type | Required | Default | Constraints & Description |
|---|---|---|---|---|
id | string | Yes | - | Dataset ID. pattern: ^[0-9a-fA-F]{24}$ |
Request Examples
Replace YOUR_API_KEY and placeholder IDs before running. Self-hosted users should replace the base URL with <instance>/api .
cURL Example
curl --fail-with-body -X GET "https://cloud.fastgpt.io/api/core/dataset/detail?id=68ad85a7463006c963799a05" \
-H "Authorization: Bearer YOUR_API_KEY"Response Schema & Examples
Successful /api/* calls return the standard FastGPT envelope { "code": 200, "statusText": "", "message": "", "data": ... } , where data matches the 200 schema below (when a payload schema is declared; otherwise refer to the status description for runtime data semantics).
HTTP 200
Successfully returned dataset details (omits createTime )
Content-Type : application/json
| Field | Type | Required | Default | Constraints & Description |
|---|---|---|---|---|
_id | string | Yes | - | Dataset ID. pattern: ^[0-9a-fA-F]{24}$ |
parentId | string | null | No | - | Parent folder ID |
userId | string | No | - | Deprecated . User ID. pattern: ^[0-9a-fA-F]{24}$ |
teamId | string | Yes | - | Team ID. pattern: ^[0-9a-fA-F]{24}$ |
tmbId | string | Yes | - | Team member ID. pattern: ^[0-9a-fA-F]{24}$ |
updateTime | string | Yes | - | Update time |
inheritPermission | boolean | Yes | - | Whether permissions are inherited from parent |
collectionPermissionEnabled | boolean | No | - | Collection-level permission toggle ( false by default, inheriting dataset readability) |
avatar | string | Yes | "/icon/logo.svg" | Avatar |
name | string | Yes | - | Name |
intro | string | Yes | - | Introduction |
type | string (enum) | Yes | - | Dataset type. Allowed values: folder , dataset , websiteDataset , externalFile , apiDataset , feishu , yuque , dingtalk |
vectorModelId | string | No | - | Embedding model ID |
agentModelId | string | No | - | AI model ID |
vlmModelId | string | No | - | VLM model ID |
websiteConfig | object | No | - | Site sync configuration |
websiteConfig.url | string | Yes | - | Site URL |
websiteConfig.selector | string | Yes | - | CSS selector for site scraping |
chunkSettings | object | No | - | Chunking configuration |
chunkSettings.trainingType | string (enum) | No | - | Training mode. Allowed values: chunk , qa , imageParse , backup , template , auto |
chunkSettings.chunkTriggerType | string (enum) | No | - | Chunk trigger mode. Allowed values: minSize , forceChunk , maxSize |
chunkSettings.chunkTriggerMinSize | number | No | - | Minimum size threshold to trigger chunking |
chunkSettings.dataEnhanceCollectionName | boolean | No | - | Prepend collection name to chunks |
chunkSettings.imageIndex | boolean | No | - | Enable image indexing |
chunkSettings.autoIndexes | boolean | No | - | Auto-generate vector indexes |
chunkSettings.indexPrefixTitle | boolean | No | - | Prefix title for indexes |
chunkSettings.chunkSettingMode | string (enum) | No | - | Chunk setting preset ( auto , custom , or intelligent ). Allowed values: auto , custom , intelligent |
chunkSettings.chunkSplitMode | string (enum) | No | - | Chunk splitting mode. Allowed values: paragraph , size , char |
chunkSettings.paragraphChunkAIMode | string (enum) | No | - | AI paragraph chunking mode. Allowed values: auto , force , forbid |
chunkSettings.paragraphChunkDeep | number | No | - | Paragraph heading split depth |
chunkSettings.paragraphChunkMinSize | number | No | - | Minimum paragraph chunk size |
chunkSettings.chunkSize | number | No | - | Target chunk size |
chunkSettings.chunkSplitter | string | No | - | Custom primary chunk separator |
chunkSettings.indexSize | number | No | - | Vector index chunk size |
chunkSettings.qaPrompt | string | No | - | Custom prompt for Q&A extraction |
sangforFileParseConfig | object | No | - | External PDF parse configuration |
sangforFileParseConfig.keep_header_footer | boolean | No | - | Whether to keep page headers and footers (default false , strips headers/footers) |
sangforFileParseConfig.keep_appendix | boolean | No | - | Whether to keep appendix sections (default true ) |
sangforFileParseConfig.image_analysis | boolean | No | - | Whether to retain OCR/image recognition results including stamps (default false ) |
sangforFileParseConfig.chart_analysis | boolean | No | - | Whether to keep chart-to-table extraction results alongside original images (default false ) |
apiDatasetServer | object | No | - | API dataset server configuration |
apiDatasetServer.apiServer | object | No | - | API dataset server configuration |
apiDatasetServer.apiServer.baseUrl | string | Yes | - | - |
apiDatasetServer.apiServer.authorization | string | No | - | - |
apiDatasetServer.apiServer.basePath | string | No | - | - |
apiDatasetServer.feishuServer | object | No | - | Lark (Feishu) server configuration |
apiDatasetServer.feishuServer.appId | string | Yes | - | - |
apiDatasetServer.feishuServer.appSecret | string | No | - | - |
apiDatasetServer.feishuServer.folderToken | string | Yes | - | - |
apiDatasetServer.yuqueServer | object | No | - | Yuque server configuration |
apiDatasetServer.yuqueServer.userId | string | Yes | - | - |
apiDatasetServer.yuqueServer.token | string | No | - | - |
apiDatasetServer.yuqueServer.basePath | string | No | - | - |
apiDatasetServer.dingtalkServer | object | No | - | DingTalk dataset configuration |
apiDatasetServer.dingtalkServer.appKey | string | Yes | - | - |
apiDatasetServer.dingtalkServer.appSecret | string | No | - | - |
apiDatasetServer.dingtalkServer.userId | string | Yes | - | - |
apiDatasetServer.dingtalkServer.operatorId | string | No | - | - |
apiDatasetServer.dingtalkServer.workspaceId | string | No | - | - |
apiDatasetServer.dingtalkServer.rootNodeId | string | No | - | - |
apiDatasetServer.dingtalkServer.workspaceName | string | No | - | - |
deleteTime | string | null | No | - | Deletion timestamp |
autoSync | boolean | No | - | Auto-sync enabled |
externalReadUrl | string | No | - | Deprecated . External source URL |
defaultPermission | number | No | - | Deprecated . Default permission level |
apiServer | object | No | - | Deprecated . API dataset server configuration |
apiServer.baseUrl | string | Yes | - | - |
apiServer.authorization | string | No | - | - |
apiServer.basePath | string | No | - | - |
feishuServer | object | No | - | Deprecated . Lark (Feishu) server configuration |
feishuServer.appId | string | Yes | - | - |
feishuServer.appSecret | string | No | - | - |
feishuServer.folderToken | string | Yes | - | - |
yuqueServer | object | No | - | Deprecated . Yuque server configuration |
yuqueServer.userId | string | Yes | - | - |
yuqueServer.token | string | No | - | - |
yuqueServer.basePath | string | No | - | - |
dingtalkServer | object | No | - | Deprecated . DingTalk dataset configuration |
dingtalkServer.appKey | string | Yes | - | - |
dingtalkServer.appSecret | string | No | - | - |
dingtalkServer.userId | string | Yes | - | - |
dingtalkServer.operatorId | string | No | - | - |
dingtalkServer.workspaceId | string | No | - | - |
dingtalkServer.rootNodeId | string | No | - | - |
dingtalkServer.workspaceName | string | No | - | - |
status | string (enum) | Yes | - | Synchronization/training status. Allowed values: active , syncing , waiting , error |
hasTrainingTask | boolean | Yes | - | Whether active training jobs or pending/failed index/synonym rebuild tasks exist |
errorMsg | string | No | - | Error details |
vectorModel | object | No | - | Embedding model details (empty if deleted; inactive models still return display metadata) |
vectorModel.pricing | object | No | - | Credit price per fixed billing unit; omitted if free |
vectorModel.pricing.unitPrice | number | No | - | Composite credit price per million units (tokens/TTS) or per 60 seconds (STT). min: 0 |
vectorModel.provider | string | Yes | - | minLength: 1 |
vectorModel.model | string | Yes | - | minLength: 1 |
vectorModel.name | string | Yes | - | minLength: 1 |
vectorModel.scope | string (enum) | Yes | "system" | Allowed values: system , team |
vectorModel.sortOrder | integer | No | - | Display rank within the same scope (smaller numbers appear first). min: 0; max: 9007199254740991 |
vectorModel.tmbId | string | null | No | - | - |
vectorModel.teamId | string | null | No | - | - |
vectorModel.isActive | boolean | No | - | - |
vectorModel.isUpcomingDeprecation | boolean | No | - | Whether the model is scheduled for deprecation |
vectorModel.requestUrl | string | No | - | - |
vectorModel.requestAuth | string | No | - | - |
vectorModel.testMode | boolean | No | - | - |
vectorModel.type | "embedding" | Yes | - | Fixed: "embedding" |
vectorModel.config | object | Yes | - | - |
vectorModel.config.defaultToken | number | Yes | - | - |
vectorModel.config.maxToken | number | Yes | - | - |
vectorModel.config.weight | number | Yes | 0 | - |
vectorModel.config.hidden | boolean | No | - | - |
vectorModel.config.vision | boolean | No | - | - |
vectorModel.config.normalization | boolean | No | - | - |
vectorModel.config.batchSize | number | No | - | - |
vectorModel.config.defaultConfig | object | No | - | - |
vectorModel.config.dbConfig | object | No | - | - |
vectorModel.config.queryConfig | object | No | - | - |
vectorModel.modelId | string | Yes | - | - |
vectorModel.avatar | string | No | - | - |
agentModel | object | No | - | AI model details (empty if deleted; inactive models still return display metadata) |
agentModel.pricing | object | No | - | Tiered LLM pricing per million tokens; omitted if free |
agentModel.pricing.tiers | object[] | No | - | LLM pricing tier (lower bound derives from the previous tier upper bound). maxItems: 5 |
agentModel.pricing.tiers[].maxInputTokens | number | No | - | Upper input limit for this tier in million tokens; omit for unlimited. min: 0 |
agentModel.pricing.tiers[].inputPrice | number | Yes | - | Credit price per million input tokens. min: 0 |
agentModel.pricing.tiers[].outputPrice | number | Yes | - | Credit price per million output tokens. min: 0 |
agentModel.provider | string | Yes | - | minLength: 1 |
agentModel.model | string | Yes | - | minLength: 1 |
agentModel.name | string | Yes | - | minLength: 1 |
agentModel.scope | string (enum) | Yes | "system" | Allowed values: system , team |
agentModel.sortOrder | integer | No | - | Display rank within the same scope (smaller numbers appear first). min: 0; max: 9007199254740991 |
agentModel.tmbId | string | null | No | - | - |
agentModel.teamId | string | null | No | - | - |
agentModel.isActive | boolean | No | - | - |
agentModel.isUpcomingDeprecation | boolean | No | - | Whether the model is scheduled for deprecation |
agentModel.requestUrl | string | No | - | - |
agentModel.requestAuth | string | No | - | - |
agentModel.testMode | boolean | No | - | - |
agentModel.type | "llm" | Yes | - | Fixed: "llm" |
agentModel.config | object | Yes | - | - |
agentModel.config.maxContext | number | Yes | - | - |
agentModel.config.maxResponse | number | Yes | - | - |
agentModel.config.quoteMaxToken | number | Yes | - | - |
agentModel.config.maxTemperature | number | null | No | - | - |
agentModel.config.showTopP | boolean | No | - | - |
agentModel.config.responseFormatList | string[] | No | - | - |
agentModel.config.showStopSign | boolean | No | - | - |
agentModel.config.censor | boolean | No | - | - |
agentModel.config.vision | boolean | No | - | - |
agentModel.config.audio | boolean | No | - | - |
agentModel.config.video | boolean | No | - | - |
agentModel.config.reasoning | boolean | No | - | - |
agentModel.config.reasoningEffort | boolean | No | - | - |
agentModel.config.functionCall | boolean | No | - | - |
agentModel.config.toolChoice | boolean | No | - | - |
agentModel.config.defaultSystemChatPrompt | string | No | - | - |
agentModel.config.defaultConfig | object | No | - | - |
agentModel.config.fieldMap | object | No | - | - |
agentModel.modelId | string | Yes | - | - |
agentModel.avatar | string | No | - | - |
vlmModel | object | No | - | Vision-Language Model (VLM) |
vlmModel.pricing | object | No | - | Tiered LLM pricing per million tokens; omitted if free |
vlmModel.pricing.tiers | object[] | No | - | LLM pricing tier (lower bound derives from the previous tier upper bound). maxItems: 5 |
vlmModel.pricing.tiers[].maxInputTokens | number | No | - | Upper input limit for this tier in million tokens; omit for unlimited. min: 0 |
vlmModel.pricing.tiers[].inputPrice | number | Yes | - | Credit price per million input tokens. min: 0 |
vlmModel.pricing.tiers[].outputPrice | number | Yes | - | Credit price per million output tokens. min: 0 |
vlmModel.provider | string | Yes | - | minLength: 1 |
vlmModel.model | string | Yes | - | minLength: 1 |
vlmModel.name | string | Yes | - | minLength: 1 |
vlmModel.scope | string (enum) | Yes | "system" | Allowed values: system , team |
vlmModel.sortOrder | integer | No | - | Display rank within the same scope (smaller numbers appear first). min: 0; max: 9007199254740991 |
vlmModel.tmbId | string | null | No | - | - |
vlmModel.teamId | string | null | No | - | - |
vlmModel.isActive | boolean | No | - | - |
vlmModel.isUpcomingDeprecation | boolean | No | - | Whether the model is scheduled for deprecation |
vlmModel.requestUrl | string | No | - | - |
vlmModel.requestAuth | string | No | - | - |
vlmModel.testMode | boolean | No | - | - |
vlmModel.type | "llm" | Yes | - | Fixed: "llm" |
vlmModel.config | object | Yes | - | - |
vlmModel.config.maxContext | number | Yes | - | - |
vlmModel.config.maxResponse | number | Yes | - | - |
vlmModel.config.quoteMaxToken | number | Yes | - | - |
vlmModel.config.maxTemperature | number | null | No | - | - |
vlmModel.config.showTopP | boolean | No | - | - |
vlmModel.config.responseFormatList | string[] | No | - | - |
vlmModel.config.showStopSign | boolean | No | - | - |
vlmModel.config.censor | boolean | No | - | - |
vlmModel.config.vision | boolean | No | - | - |
vlmModel.config.audio | boolean | No | - | - |
vlmModel.config.video | boolean | No | - | - |
vlmModel.config.reasoning | boolean | No | - | - |
vlmModel.config.reasoningEffort | boolean | No | - | - |
vlmModel.config.functionCall | boolean | No | - | - |
vlmModel.config.toolChoice | boolean | No | - | - |
vlmModel.config.defaultSystemChatPrompt | string | No | - | - |
vlmModel.config.defaultConfig | object | No | - | - |
vlmModel.config.fieldMap | object | No | - | - |
vlmModel.modelId | string | Yes | - | - |
vlmModel.avatar | string | No | - | - |
permission | object | Yes | - | Serialized permission object JSON structure |
permission.role | integer | Yes | - | Permission role bitmask value. min: -9007199254740991; max: 9007199254740991 |
permission.isOwner | boolean | Yes | - | Whether the caller has owner permission |
permission.hasManagePer | boolean | Yes | - | Whether the caller has manage permission |
permission.hasWritePer | boolean | Yes | - | Whether the caller has write permission |
permission.hasReadPer | boolean | Yes | - | Whether the caller has read permission |
permission.hasManageRole | boolean | Yes | - | Whether manage role bit is set |
permission.hasWriteRole | boolean | Yes | - | Whether write role bit is set |
permission.hasReadRole | boolean | Yes | - | Whether read role bit is set |
Last updated