Start with install notes or jump straight into the API.

API

Fetch

Fetch is a Layer-only surface. The NVMe cache is checked first; on miss or error the gateway falls through to Turbopuffer and backfills the cache best-effort.

Single fetch

GET /v2/namespaces/products/documents/asin-B08N5WRWNW?include_attributes=title,category
OutcomeStatusHeader
Cached hit200x-layer-cache: hit
Cache miss, upstream hit, cache backfilled200x-layer-cache: miss
Cache unavailable, upstream hit200x-layer-cache: miss-on-error
Missing from both layers404

Batch fetch

POST /v2/namespaces/products/documents
Content-Type: application/json

{
  "ids": ["asin-1", "asin-2", "asin-3"],
  "include_attributes": ["title"]
}
{
  "documents": [
    {"id": "asin-1", "attributes": {"title": "..."}},
    {"id": "asin-3", "attributes": {"title": "..."}}
  ],
  "missing": ["asin-2"]
}

Batch fetch returns found documents and missing ids inline instead of a partial 404. documents preserves request order; ids the gateway could not find anywhere land in missing.

Behavior matrix

Cache stateSingle fetchBatch fetch
Hitcachecache
Miss, upstream presentupstream + backfillupstream + backfill
Miss, upstream absent404inline missing
Cache unavailableupstream, miss-on-errorupstream, miss-on-error