Use case
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.
The problem
RAG ingestion re-embeds the same documents on every pipeline run. Against a hosted API that means repeated per-token charges and rate-limited backfills that stretch into days.
How embedcache helps
- 1
Point your ingestion job at the embedcache /v1/embed or /v1/process endpoint instead of a hosted embedder.
- 2
Each chunk is keyed by its content hash and model, so unchanged chunks are cache reads on subsequent runs.
- 3
Re-run the pipeline freely: only genuinely new or edited chunks trigger inference.
- 4
Hand the resulting vectors to your vector database (Qdrant, pgvector, LanceDB) for indexing and search.