Text embedding

Text embedding models are supported with local Hugging Face connections.

In the Text Embedding section of the connection, click Add model from preset to import a preset from the catalog. If the model is not in the catalog, or if you want to configure a compatible Hugging Face model manually, click Add a custom model. Once the model is configured, click Save.

For compatible models and runtime environments, DSS uses vLLM to serve text embedding models. If vLLM cannot be used, DSS falls back to transformers. Compatibility depends on the model architecture, model packaging, quantization format, and runtime environment. For example, Qwen/Qwen3-Embedding-4B can be used as a local text embedding model.

See Setup & prerequisites and Text generation for the shared setup and compatibility considerations.