Skip to main content
GET
/
v1
/
projects
/
{projectId}
/
knowledgebases
/
{knowledgebaseId}
/
datasets
/
{datasetId}
/
chunks
Preview Chunks
curl --request GET \
  --url https://api.pathors.com/v1/projects/{projectId}/knowledgebases/{knowledgebaseId}/datasets/{datasetId}/chunks \
  --header 'Authorization: <authorization>'
{
  "id": "<string>",
  "content": "<string>",
  "contentLength": 123,
  "isEnabled": true
}

Documentation Index

Fetch the complete documentation index at: https://docs.pathors.com/llms.txt

Use this file to discover all available pages before exploring further.

Returns the chunks produced when the dataset was processed. Useful for previewing how a document was split, debugging unexpected search results, or auditing chunk content.

​
Request

GET https://api.pathors.com/v1/projects/{projectId}/knowledgebases/{knowledgebaseId}/datasets/{datasetId}/chunks

​
Path Parameters

​
projectId
string
required
The project ID
​
knowledgebaseId
string
required
The knowledgebase containing the dataset
​
datasetId
string
required
The dataset to preview

​
Headers

​
Authorization
string
required
Bearer token using your developer key

​
Response

Returns chunks in their original document order.
​
id
string
Unique identifier for the chunk
​
content
string
Chunk text content (post-processing, not raw file content)
​
contentLength
number
Length of the chunk content in characters
​
isEnabled
boolean
Whether the chunk participates in search. Disabled chunks are excluded from query results.

​
Example

curl https://api.pathors.com/v1/projects/{projectId}/knowledgebases/kb_abc123/datasets/dataset_xyz789/chunks \
  -H "Authorization: Bearer dk_your_key"

[
  {
    "id": "chunk_abc123",
    "content": "This is the first chunk of text extracted from the document...",
    "contentLength": 127,
    "isEnabled": true
  }
]
The dataset must belong to the specified knowledgebase — cross-knowledgebase access returns 403.