Create Collection from Link
Fetch web page content from a specified URL, split it using chunking settings, and create a dataset collection.
Endpoint Overview
- Method :
POST - Path :
/api/core/dataset/collection/create/link - Module : Datasets / Create Collections
- 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/%E9%9B%86%E5%90%88%E5%88%9B%E5%BB%BA/POST/core/dataset/collection/create/link)
Description & Notes
Fetch content from a specified web URL, create a collection, and trigger indexing training.
Request Parameters
Request Body ( application/json )
| Field | Type | Required | Default | Constraints & Description |
|---|---|---|---|---|
trainingType | string (enum) | No | - | Training mode. Allowed values: chunk , qa , imageParse , backup , template , auto |
chunkTriggerType | string (enum) | No | - | Chunk trigger mode. Allowed values: minSize , forceChunk , maxSize |
chunkTriggerMinSize | number | No | - | Minimum size threshold to trigger chunking |
dataEnhanceCollectionName | boolean | No | - | Prepend collection name to chunks |
imageIndex | boolean | No | - | Enable image indexing |
autoIndexes | boolean | No | - | Auto-generate vector indexes |
indexPrefixTitle | boolean | No | - | Prefix title for indexes |
chunkSettingMode | string (enum) | No | - | Chunk setting preset ( auto , custom , or intelligent ). Allowed values: auto , custom , intelligent |
chunkSplitMode | string (enum) | No | - | Chunk splitting mode. Allowed values: paragraph , size , char |
paragraphChunkAIMode | string (enum) | No | - | AI paragraph chunking mode. Allowed values: auto , force , forbid |
paragraphChunkDeep | number | No | - | Paragraph heading split depth |
paragraphChunkMinSize | number | No | - | Minimum paragraph chunk size |
chunkSize | number | No | - | Target chunk size |
chunkSplitter | string | No | - | Custom primary chunk separator |
indexSize | number | No | - | Vector index chunk size |
qaPrompt | string | No | - | Custom prompt for Q&A extraction |
parentId | string | null | No | - | Parent folder ID |
metadata | object | No | - | Metadata |
customPdfParse | boolean | No | - | Custom PDF parser |
datasetId | string | Yes | - | Dataset ID |
tags | string | object[] | No | - | List of collection tags. String items map to legacy default_tag tags; object items { tag, value } resolve by tag name. |
link | string | Yes | - | Source web page URL |
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 POST "https://cloud.fastgpt.io/api/core/dataset/collection/create/link" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
--data-raw '{
"datasetId": "string",
"link": "string"
}'Minimal Valid JSON Body
{
"datasetId": "string",
"link": "string"
}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 collection ID and chunk insertion results
Returns the standard FastGPT success envelope ( { "code": 200, "statusText": "", "message": "", "data": ... } ). The exact data payload schema is not declared in this OpenAPI contract; refer to the status description above or inspect runtime responses.
Last updated