Use cases

Where embedcache fits

Anywhere you embed the same text more than once, or cannot send it to a hosted API, a local content-addressed cache pays off. A few common shapes:

Batch RAG ingestion

Embed a large corpus once, re-run the pipeline as often as you like, and only pay CPU time for the chunks that actually changed.

Generate embeddings entirely on-box for environments where sending text to a third-party API is not an option.

Cut the recurring bill from re-embedding stable inputs by keeping vectors on-box in a cache that survives restarts.

Give every developer and CI job the same fast, offline embedder so tests are deterministic and do not burn API budget.