Skip to content
← All services

AI

Managed Text embeddings on your own cluster

Embeddings and reranking for search and RAG, from any compatible Hugging Face model, behind the OpenAI embeddings API.

Created inside a project, beside the apps that use it. Each project gets its own instance, storage and credentials.

A recent addition. It installs today, and the console marks it as new until it has run on a customer's cluster.

01What it does

Text embeddings, run for you

Hugging Face's Text Embeddings Inference on CPU, on Anyport's own chart.

Name a model from the Hugging Face Hub and the service downloads it before it starts serving, then keeps it on its volume. Embedding models answer the OpenAI embeddings endpoint, so the OpenAI SDK works with one base-URL change; reranker models answer TEI's own rerank endpoint. It pairs with the vector stores in the catalog.

Runs on CPU; a model needs about four bytes per parameter, so the size decides which models fit. The image is built per CPU architecture, and the install form picks the cluster's own. Inference asks for the generated API key, so the service can be published on a domain. Gated and private models are not supported yet.

02Options

What you choose

What the console asks when you create it, in the catalog's own numbers. Anything marked chosen once cannot change without creating a new instance.

Sizes
small 1Gi, medium 4Gi, large 8Gi of memory
Storage
10Gi by default for model files, chosen once
Model
Any compatible Hub model by id; BAAI/bge-small-en-v1.5 by default
Pause
Yes; the models stay on the volume

03Binding

What your app receives

Bind it to an app and these arrive as environment variables. The values are generated once into a secret and reach the app from there, rather than as something you copy.

  • EMBEDDINGS_HOST
  • EMBEDDINGS_PORT
  • EMBEDDINGS_URL
  • EMBEDDINGS_OPENAI_BASE_URL
  • EMBEDDINGS_API_KEY

04Adding it

Add Text embeddings to a project

The same four steps as every service in the catalog.

  1. 01Open a project and go to Services.
  2. 02Pick it from the catalog and choose its options. Only the size is required; everything else has a default.
  3. 03Create it. Anyport installs it into the project's namespace, generates its credentials into a secret there, and tracks its health.
  4. 04Bind it to an app. The connection details arrive as environment variables, and rotating the credential never means editing an app.
Open the console →How services work →

Also under AI