Caching

Skip the vector DB for repeated or similar queries.

Attach a cache and repeated queries are served without hitting S3 Vectors. Three backends:

from dynavec import Dynavec, SemanticCache, DynamoDBCache, RedisCache

# 1) in-process semantic cache — also serves near-duplicate queries
db = Dynavec(cfg, embedder=emb, cache=SemanticCache(threshold=0.97))

# 2) durable, shared cache in your own DynamoDB table (TTL expiry)
db = Dynavec(cfg, embedder=emb, cache=DynamoDBCache(cfg, ttl_seconds=3600))

# 3) sub-millisecond shared cache on Redis / AWS ElastiCache
db = Dynavec(cfg, embedder=emb, cache=RedisCache("redis://my-elasticache:6379/0"))

Backend	Best for
`SemanticCache`	single process; tolerant of near-duplicate hits; zero infra
`DynamoDBCache`	durable, shared, no extra service; exact-match with TTL
`RedisCache`	many workers/hosts; lowest latency; AWS ElastiCache

Force a fresh search per call with db.search(..., use_cache=False).

PreviousStreaming NextKnowledge graph