Skip to main content

OpenAI Compatible Embedding

Connect any embeddings endpoint that implements the OpenAI Embeddings API — self-hosted servers (vLLM, LiteLLM), managed gateways, or third-party providers exposing an OpenAI-compatible interface.

Getting started​

You need:

  • The base URL of the OpenAI-compatible embeddings endpoint (for example https://gateway.example.com/v1).
  • An API key, if the endpoint requires one.
  • The embedding model name your endpoint expects (for example text-embedding-3-small, BAAI/bge-m3, nomic-embed-text).

Setting up in Unstract​

  • Sign in to the Unstract Platform.
  • From the side navigation menu, choose Settings 🞂 Embedding.
  • Click on the New Embedding Profile button.
  • From the list of Embeddings, choose OpenAI Compatible.
  • Name — a unique name for this adapter instance.
  • API Base — the base URL of your endpoint. Required.
  • API Key — the endpoint's API key. Leave empty if it does not require one.
  • Model — the embedding model name your endpoint expects.
  • Leave Max Retries and Timeout at their defaults.
  • Click on Test Connection and ensure it succeeds, then click Submit.