Replace document with file
Replace an existing document with a new file while keeping its stable document ID. Content and caller metadata are overwritten, then the document is reprocessed asynchronously.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
The isolated namespace. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope documents.
100^[a-zA-Z0-9_:-]+$"user_alex"
The public document ID
1 - 255"my-doc-123"
Body
File contents to upload
Context used to guide memory extraction within this namespace. Max 1500 characters.
1500"Focus on product decisions, dates, and owners."
JSON-encoded metadata to attach to the document and its derived memories
JSON-encoded metadata used to keep related context isolated during processing and recall
When the source content is from, in ISO 8601 format
"2026-01-15"
Processing pipeline. "memory" builds durable learned context; "superrag" optimizes the document for retrieval without generating memories.
memory, superrag Processing mode. "dynamic" (default) groups related documents so memories form from coherent context. "instant" processes each document independently right away and bills one extra operation per document.
dynamic, instant Explicit source type used when automatic inference is insufficient
text, pdf, image, video, audio Explicit MIME type used when upload metadata is insufficient
^[^\s/]+\/[^\s/]+$Response
Replacement accepted for processing
Document identifier to poll or retrieve
1The document's processing state after this request. queued when new work was queued; otherwise its current state, e.g. done for an unchanged duplicate or failed for a metadata-only update to a failed document.
unknown, queued, extracting, chunking, embedding, indexing, done, failed