GET
/
api
/
corpora
/
{corpus_id}
/
sources
/
{source_id}
/
documents
/
{document_id}
cURL
curl --request GET \
  --url https://api.ultravox.ai/api/corpora/{corpus_id}/sources/{source_id}/documents/{document_id} \
  --header 'X-API-Key: <api-key>'
{
  "corpusId": "<string>",
  "sourceId": "<string>",
  "documentId": "<string>",
  "created": "2023-11-07T05:31:56Z",
  "mimeType": "<string>",
  "metadata": {
    "publicUrl": "<string>",
    "language": "<string>",
    "title": "<string>",
    "description": "<string>",
    "published": "2023-11-07T05:31:56Z"
  },
  "sizeBytes": "<string>"
}

Authorizations

​
X-API-Key
string
header
required

API key

Path Parameters

​
corpus_id
string<uuid>
required
​
document_id
string<uuid>
required
​
source_id
string<uuid>
required

Response

200 - application/json

A single complete source of information included in a corpus. In the most straight-forward case, this could be an uploaded PDF or a single webpage. However, documents can also be created from other documents during processing, for example turning an HTML page into a markdown document.

​
corpusId
string

The id of the corpus in which this document is included.

​
sourceId
string

The id of the source that provides this document.

​
documentId
string

The unique ID of this document.

​
created
string<date-time>

When this document was created.

​
mimeType
string

The MIME type of the document. https://developer.mozilla.org/en-US/docs/Web/HTTP/MIME_types

​
metadata
object

Metadata about the document. Metadata about a document. This is typically not included in the document's chunks, but can be used for filtering or citations. Derived documents inherit metadata from their source documents in general.

​
sizeBytes
string

The size of the document contents, in bytes.