Skip to main content

​
Migration details

v5 moves document scope into the URL and keeps repeated caller IDs attached to one evolving document.

​
Rename common fields

​
Add or append one document

The response remains an acceptance result with id and status. Its status is the document’s processing state after the request: queued when new work was queued, otherwise the document’s current state (for example done for an unchanged duplicate, or failed for a metadata-only update to a failed document). Possible values: unknown, queued, extracting, chunking, embedding, indexing, done, failed. Repeating the v5 request with id: "conv_1" adds or diffs the new content into that document; it does not silently replace the canonical source.

​
Batch ingestion

Send the v5 body to POST /ns/user_1/document/batch. The array accepts 1–600 document objects. Namespace, taskType, and processing mode apply to the request; document content, ID, context, metadata, grouping, and date stay per item. results lists accepted documents first, in request order, then failed ones; match each result by id, or by url for a failed item with no ID. Inspect count (accepted), failed, and every item in results; each item’s status is a processing state as above, or error when that item failed, and a batch can contain successful and failed items together.

​
File ingestion

Replace POST /v3/documents/file with POST /ns/{namespace}/document/file. Continue using multipart/form-data: The API acknowledges the file after durable acceptance, with status set as for a JSON add. Extraction, indexing, and memory formation continue asynchronously; poll the document rather than assuming the first response means processing is complete.

​
Processing choices

  • taskType=memory extracts long-term memories; taskType=superrag indexes source context without memory generation.
  • dreaming=dynamic (default) groups related documents into coherent memory units.
  • dreaming=instant processes each document independently and bills one extra operation per document.

​
Verification

  • Ingest text, a public URL, and a file, then wait for each document to finish processing.
  • Repeat a caller-defined ID and confirm append/diff behavior instead of replacement.
  • Submit a mixed-success batch and verify each result matches its document by ID, with per-item errors.
  • Confirm metadata and grouping remain filterable after processing.