Post details of a given document that will enrich the chunk and be added to the context or just for filtering. If Just for filtering, start with ”_” in the key.
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Datastore ID of the datastore from which to retrieve the document
Document ID of the document to retrieve details for
Metadata request in JSON format. custom_metadata
is a flat dictionary containing one or more key-value pairs, where each value must be a primitive type (str
, bool
, float
, or int
). The strings with date format must stay in date format or be avoided if not in date format.The custom_metadata.url
field is automatically included in returned attributions during query time, if provided.
The default maximum metadata fields that can be used is 15, contact support if more is needed.The combined size of the metadata must not exceed 2 KB when encoded as JSON.
metadata_config
is an optional dictionary that defines how each metadata field should be used — e.g., whether it's included in chunk reranking (in_chunks
, default=False), included in the API response (returned_in_response
, default=False), or enabled for filtering (filterable
, default=True).
Example Request Body:
{
"custom_metadata": {
"topic": "science",
"difficulty": 3
},
"metadata_config": {
"topic": {
"in_chunks": true,
"returned_in_response": false,
"filterable": true
},
"difficulty": {
"filterable": true
}
}
}
Successful Response
Document description