parentId-chunkId
where parentId is the ID of the document and chunkId
is an integer starting with 0 to the total number of chunksparentId
.chunkCount
to the metadata field of the parentId-0
vector, or you may append them to all chunks if desired. This should be an integer and cardinality will naturally be low.parentId-chunkId
as the ID.parentId
parentId
.parentId
is identified, use the fetch
endpoint to retrieve the chunkCount
from the metadata field by sending the parentId-0
vector ID.
parentId
and chunkCount
.
delete
endpoint using the IDs of the vectors.