IONOS Cloud Embeddings icon

IONOS Cloud Embeddings

Use IONOS Cloud AI Model Hub to generate text embeddings

IONOS Cloud Embeddings

AI-generated

Summary

Generates embeddings for input text using a selected model from the IONOS AI Model Hub. Exposes an n8n AI Embedding connection for embedding documents in batches or embedding a single query.

Inputs

  • Model (required) — Select an embedding model; the available model IDs are fetched live from the IONOS API.
  • Batch Size — Maximum number of document texts sent per request. Defaults to 512 and is rounded down to at least 1.
  • Strip Newlines — Replace newline characters with spaces before sending text. Defaults to true.
  • Timeout — Maximum wait for each API request, in milliseconds. Defaults to 60000.
  • IONOS Cloud API credentials (required) — Credentials used to authenticate requests to the IONOS embeddings API.

Output shape

An AI Embedding connection that provides document and query embedding methods.

Document embedding returns vectors in input order, split into requests using the configured batch size. Query embedding returns one vector. If the API returns no vector for a query, the operation raises an error.

Links

Discussion