Backfill historical documents with documentDate on ingest#
Set documentDate on each document so historical content lands on the date it actually happened instead of the date you uploaded it, which is what makes time-based search work on backfilled data.
Improvements
- A new guide walks through backfilling dated documents through the batch ingestion API, with TypeScript and Python examples.
- Company Brain admins can now change the company domain, and re-running research updates its findings in place instead of stacking duplicates.
Fixes
- Fixed an issue where SDK responses dropped fields the API returned, across 15 endpoints.
- MCP now shows the API's real reason for refusing a request instead of reporting that your account may be restricted or blocked. A read-only key now says so.
Send up to 600 documents per request to POST /v3/documents/batch, sorted oldest to newest:
{
"documents": [
{
"id": "msg-2019-04-02-118",
"content": "Decided to move the billing cutover to Q3.",
"documentDate": "2019-04-02T09:15:00Z"
}
]
}
Without documentDate a backfilled document is dated the day you uploaded it, so a question like "what did we decide in 2019" will not find it.