Embeddings

Embeddings convert text into vectors you can use for semantic search, clustering, and retrieval augmented generation (RAG).

API

Use the embeddings endpoint:

curl http://localhost:11434/api/embed \
  -d '{"model":"nomic-embed-text","input":["hello","world"]}'

RAG workflow

1) Embed documents
2) Store vectors in a vector DB
3) Embed the query
4) Retrieve top matches
5) Inject context into chat