Skip to main content
When vault search returns a truncated text_preview, use chunk retrieval to fetch the full chunk text and nearby chunks from the document manifest stored in Vault.

​
Endpoint

Endpoint
GET /vault/:id/objects/:objectId/chunks

​
When to use it

Search is optimized for relevance and compact responses. That means results often contain only a preview of the matched chunk. If the match lands inside a table, exhibit list, or a passage that spans several chunks, call read-chunks to recover the surrounding text. Example workflow:
  1. Search returns chunk 13 with a partial exhibit table.
  2. Request start=12&end=14.
  3. Read the full text of chunks 12, 13, and 14 together.
Ranges are inclusive and capped at 10 chunks per request.

​
Parameters

ParameterTypeRequiredDescription
idstringYesVault ID
objectIdstringYesProcessed object ID
startintegerNoFirst chunk index to return. Defaults to 0.
endintegerNoLast chunk index to return, inclusive. If omitted, only the start chunk is returned.

​
Example

curl "https://api.case.dev/vault/$VAULT_ID/objects/$OBJECT_ID/chunks?start=12&end=14" \
  -H "Authorization: Bearer $CASEDEV_API_KEY"
Response
{
  "object_id": "obj_abc123",
  "vault_id": "vault_def456",
  "chunks": [
    {
      "index": 12,
      "text": "full text of chunk 12...",
      "page_start": 5,
      "page_end": 5,
      "word_start_index": 5544,
      "word_end_index": 6055
    },
    {
      "index": 13,
      "text": "full text of chunk 13...",
      "page_start": 5,
      "page_end": 6,
      "word_start_index": 6056,
      "word_end_index": 6532
    },
    {
      "index": 14,
      "text": "full text of chunk 14...",
      "page_start": 6,
      "page_end": 6,
      "word_start_index": 6533,
      "word_end_index": 6881
    }
  ],
  "total_chunks": 42
}

​
Response fields

FieldDescription
object_idObject that owns the returned chunks
vault_idVault containing the object
chunksFull chunk entries for the requested range
total_chunksTotal stored chunk count for the object
Each chunk includes:
FieldDescription
indexChunk index within the document
textFull text of the chunk
page_start, page_endPDF page span when available
word_start_index, word_end_indexOCR word range when available

​
Notes

  • end is clamped to the document’s final chunk if you request past the end.
  • Requests where start is out of range return an error.
  • Objects without stored chunks return total_chunks: 0 and an empty chunks array.