Skip to main content
GET
Get a document's extracted text

Authorizations

Authorization
string
header
required

Workspace credential issued from the automation console at /automation. Send it as Authorization: Bearer vq_ws_.... This is NOT a Data API key: a vq_key_ credential is refused here and names the other product in the error.

Path Parameters

matterId
string
required

mat_ identifier of the matter to work inside. Everything in this API hangs off a matter, and the matter in the path is what the authorization boundary is checked against. Take it from GET /v1/matters.

documentId
string
required

doc_ identifier of the document. Take it from the matter's document list, or from the operation that completed its upload.

Response

Successful Response

The reassembled text of a document.

Reassembled from the ingested chunks rather than re-extracted from the original, so what a customer reads here is exactly what retrieval, drafting and review saw. Re-extracting would be a second implementation that could silently disagree with the one the product actually uses.

documentId
string
required

doc_ identifier of the document this text came from.

Example:

"doc_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6"

text
string
required

The document's full text, reassembled from the ingested chunks. This is exactly what retrieval, drafting and review saw, not a fresh extraction.

Example:

"Neither party shall be liable for indirect or consequential damages."

chunkCount
integer
required

How many chunks were reassembled. Compare against the document's chunkCount to tell a partial read from a complete one.

Example:

37

truncated
boolean
default:false

True when the text was cut at the published ceiling. Always check it before quoting the text as complete.

Example:

false

Last modified on August 23, 2026