Skip to content

OpenAI Embeddings Provider

This provider turns text into numeric vectors for semantic search. Connect its embedder output to the Vector Store Orchestrator and Retriever Provider so documents and search queries use the same embedding model.

  • Category: Embedding
  • Purpose: Converts text into vectors, which is what makes semantic search possible
  • Inputs: None (configured through fields)
  • Outputs: embedder - Embedding instance, connected to both Vector Store and Retriever
  • Configuration:
  • Embedding Model: text-embedding-3-small (1536 dimensions, inexpensive), text-embedding-3-large (3072 dimensions, more accurate), text-embedding-ada-002 (previous generation). Default is 3-small
  • Select Credential: OpenAI API key (required)
  • Organization (Optional): Billing organisation for enterprise accounts
  • Batch Size: 1–100, default 100. Number of texts embedded per request
  • Max Retries: 0–10, default 3
  • Request Timeout (seconds): 10–300, default 30
  • Dimensions: Default 1536. Calculated automatically from the selected model — do not edit
  • Usage: Once a collection has been populated with one model, the model cannot be changed. The dimensions and representation would no longer match and search would fail, requiring every document to be reprocessed.