Search Moments
Search collection content (semantic / keyword / image)
https://api.memories.ai/datalake/v1
Auth: Authorization: sk-mai-...semantic (vector), keyword (BM25), and hybrid (RRF) modes, plus text-to-frame and image-to-frame. Each result’s ref can be fed straight into Get Moment.
Response Fields
ref, score, snippet, thumbnail_url.Notes
Rate limit: 5 QPS/user.Authorizations
Send Authorization: sk-mai-...
Body
Target collection (fixes vector model + data scope).
Non-empty search targets.
caption, transcription, summary, title, frame_embedding, event Natural-language query (non-English is auto-translated). One of query / query_images required.
1–10 http(s) image URLs; averaged with query when both given.
Advanced: bring-your-own vector; must be 3072-dim (OmniRetriever).
semantic (default) | keyword | hybrid.
semantic, keyword, hybrid Page size, default 20, max 200.
Next-page cursor; all other fields must match the first page exactly.
Filter DSL (and/or/not + leaves: video_ids, tags, time, captured_at, location, speaker_id, event_type).
Cross-encoder rerank of the current page (text query only). Billed ×3 when actually run.
moment (default) | video.
moment, video Response
Success
