Skip to main content
GET
/
namespaces
/
{namespace_name}
/
documents
/
fetch-text-data
curl -X GET "http://localhost:8080/namespaces/my-documents/documents/fetch-text-data?limit=100"

{
  "status": "<string>",
  "message": "<string>",
  "namespace": "<string>",
  "statistics": {},
  "statistics.total_items": 123,
  "statistics.total_text_chunks": 123,
  "statistics.total_summary_chunks": 123,
  "statistics.created_at_min": {},
  "statistics.created_at_max": {},
  "statistics.source_counts": {},
  "items": [
    {}
  ],
  "items[].id": "<string>",
  "items[].text": "<string>",
  "items[].metadata": {},
  "items[].created_at": "<string>",
  "items[].is_summary": true,
  "pagination.limit": 123,
  "pagination.has_more": true,
  "pagination.next_token": {},
  "execution_time": 123
}

​
Overview

Get text chunks from a text-type namespace. Use this to list stored text and summary chunks for display, export, or bulk RAG context loading. Results are returned one page at a time. Each page returns up to 100 items. When more data exists, the response includes pagination.has_more and pagination.next_token — pass that token on the next request to fetch the following page.
Only namespaces with type === "text" are supported. Vector-only namespaces are not supported.

​
Path parameters

​
namespace_name
string
required
Name of the text namespace (e.g. my-documents)

​
Query parameters

​
limit
integer
Maximum number of items to return in this page. Default: 100. Maximum: 100.
​
next_token
string
Opaque cursor from the previous response’s pagination.next_token. Omit on the first request.
next_token is tied to the requested namespace. Do not reuse a token from a different namespace.

​
Pagination

1

First request

GET .../fetch-text-data?limit=100 (or omit limit for the default of 100).
2

Check pagination

If pagination.has_more is true, more chunks exist in the namespace.
3

Next page

Call again with next_token from the previous response: GET .../fetch-text-data?limit=100&next_token=<token>
4

Stop

Repeat until pagination.has_more is false or next_token is null.
curl -X GET "http://localhost:8080/namespaces/my-documents/documents/fetch-text-data?limit=100"

​
Response fields

​
status
string
"success" for 200 responses.
​
message
string
Human-readable summary for this page (e.g. “Fetched N text items from namespace ’…’”).
​
namespace
string
The requested namespace name.
​
statistics
object
Aggregated counts and timestamps for items in this page only (not the full namespace total).
​
statistics.total_items
number
Number of items in items on this page.
​
statistics.total_text_chunks
number
Count of non-summary chunks on this page.
​
statistics.total_summary_chunks
number
Count of summary chunks on this page.
​
statistics.created_at_min
string | null
Earliest item timestamp on this page as ISO 8601. null when the page is empty.
​
statistics.created_at_max
string | null
Latest item timestamp on this page as ISO 8601. null when the page is empty.
​
statistics.source_counts
object
Map of source name → count on this page.
​
items
array
Text chunks for this page (length ≤ limit, max 100).
​
items[].id
string
Item/chunk identifier.
​
items[].text
string
Text content of the chunk.
​
items[].metadata
object
Arbitrary metadata (e.g. source, heading, chunk_index).
​
items[].created_at
string
Creation time as ISO 8601.
​
items[].is_summary
boolean
true for summary chunks, false for regular text chunks.
​
pagination.limit
number
Page size used for this request (≤ 100).
​
pagination.has_more
boolean
true if additional pages exist after this one.
​
pagination.next_token
string | null
Pass as query param next_token to fetch the next page. null when has_more is false.
​
execution_time
number
Request processing time in seconds.

​
Example response

{
  "status": "success",
  "message": "Fetched 2 text items from namespace 'my-documents'.",
  "namespace": "my-documents",
  "statistics": {
    "total_items": 2,
    "total_text_chunks": 2,
    "total_summary_chunks": 0,
    "created_at_min": "2025-12-19T18:18:57.370Z",
    "created_at_max": "2025-12-19T18:20:01.120Z",
    "source_counts": {
      "document.pdf": 2
    }
  },
  "items": [
    {
      "id": "abc123_chunk_0",
      "text": "Overview section content...",
      "metadata": {
        "chunk_index": 0,
        "source": "document.pdf"
      },
      "created_at": "2025-12-19T18:18:57.700Z",
      "is_summary": false
    }
  ],
  "pagination": {
    "limit": 100,
    "has_more": false,
    "next_token": null
  },
  "execution_time": 0.012
}

​
Errors

StatusMessage (examples)
400Bad Request: Namespace '...' is not a text-based namespace.
400Invalid limit: must be a positive integer.
400Invalid next_token: token does not match requested namespace.
404Namespace '...' not found.
500Internal Server Error during namespace validation.