Embeddings
Configure embedding models for retrieval and vector search.
Embedding models convert text into vectors. In Anvia, they are separate from completion models so retrieval code can swap providers without changing agent logic.
import { OpenAIClient } from "@anvia/openai";
const openai = new OpenAIClient({ apiKey });
const embeddings = openai.embeddingModel("text-embedding-3-small");
const result = await embeddings.embed(["Anvia carries structured context."]);Provider Support
| Provider package | Embedding support |
|---|---|
@anvia/openai | OpenAI and OpenAI-compatible embedding endpoints |
@anvia/gemini | Gemini embedding models |
@anvia/transformers | Local Transformers embeddings |
Use embeddings with Vector Stores for retrieval workflows.