Local OSS
embeddings
Run the local OpenAI-compatible embedding daemon.
emend embeddings
Info
Local OSS only. The embedding daemon serves embeddings from a local model on your machine.
The daemon hosts a single active local embedding model (default local/nomic-embed-text-v1.5) behind an OpenAI-compatible API. services start launches it automatically when local embedding mode is selected (EMEND_EMBEDDING_PROVIDER=local_service or CLAUDE_SMART_USE_LOCAL_EMBEDDING=1); run it directly only when you want the embedding service on its own.
Command: emend embeddings serve
Serves the embedding daemon with uvicorn and blocks until you interrupt with Ctrl-C.
emend embeddings serve [OPTIONS]Options
| Prop | Type |
|---|---|
--host | str |
--port | int |
Endpoints
GET /health— liveness check; reports the currently active model.POST /v1/embeddings— OpenAI-compatible embedding endpoint. Themodelfield is required and must match the daemon's single active model; requests for a different model are rejected.
Examples
# Serve on the default port (EMBEDDING_PORT or 8072)emend embeddings serve # Serve on a custom portemend embeddings serve --port 9072 # Check the daemon and its active modelcurl -H "User-Agent: my-agent-emend" http://localhost:8072/healthSee services for starting the embedding daemon alongside the backend, and Configuration for embedding provider settings.