Embedders
Embedding models convert text into high-dimensional vectors that power semantic search. TypeGraph uses the Vercel AI SDK format, so any provider that implements it works out of the box. The dimensions value must match your chosen model and stay consistent across deploys - changing dimensions after data has been ingested requires re-embedding everything.
@ai-sdk/openai
@ai-sdk/openai@ai-sdk/google
@ai-sdk/google@ai-sdk/cohere
@ai-sdk/cohereAI Gateway (OpenAI)
@ai-sdk/gatewayAI Gateway (Cohere)
@ai-sdk/gatewayUsage in Config
Pass the embedding model and its dimensions to the TypeGraph config:
Provider Options
Some providers accept extra configuration via providerOptions. This is part of the AISDKEmbeddingInput type that TypeGraph uses for embedding configuration:
Asymmetric Embeddings
You can use separate embedding models (or the same model with different providerOptions) for ingestion vs query via the embedding and searchEmbedding config fields. This is useful for providers like Voyage that distinguish between document and query input types: