Skip to main content
Embeddings turn the text of each record into a numeric vector so that semantically similar content sits close together in vector space. @ooneex/rag generates embeddings with OpenAI models — you pick the model in your vector database, and embedding happens automatically on add() and search().

​
Choosing a model

Declare the provider and model in getEmbeddingModel(): 
public getEmbeddingModel = (): {
  provider: EmbeddingProviderType;
  model: EmbeddingModelType["model"];
} => ({ provider: "openai", model: "text-embedding-3-small" });
The provider is openai. The available models:
ModelDimensionsNotes
text-embedding-3-small1536Best price/performance — a strong default.
text-embedding-3-large3072Highest quality; larger vectors, higher cost.
text-embedding-ada-0021536Previous-generation model, kept for compatibility.
Start with text-embedding-3-small. Move to text-embedding-3-large only if retrieval quality on your data measurably improves — the larger vectors cost more to store and search.

​
Configuration

Embeddings are generated through OpenAI, so set your API key in the environment: 
OPENAI_API_KEY=sk-...
The key is read when embeddings are generated, so a missing or invalid key surfaces when you first add() or search(), not at construction time.

​
How embedding works

You never compute or pass vectors yourself. When a table is created, the schema wires the embedding model into two roles:
  • The source field is text — the column that gets embedded.
  • The vector field is vector — where the generated embedding is stored and indexed.
From there:
  1. On add(), the text of each record is sent to the embedding model and the resulting vector is stored on the row.
  2. On search(), your query string is embedded with the same model and compared against stored vectors.
Because the same model embeds both stored text and queries, the model is fixed for the life of a table.
The embedding model is part of a table’s schema. Changing getEmbeddingModel() after a table already exists does not re-embed existing rows — embed new data into a fresh table instead, then switch over.

​
Where embeddings fit

Embeddings power the vector half of retrieval. At query time they are combined with a full-text search over the same text and merged with an RRF reranker — see Search for how the two halves come together.