Embedder Configuration
Embedding models are specific types of models that turn text into vectors, which can be stored and searched in a vector database—the foundation of Retrieval Augmented Generation (RAG).
Tip: Embedding models are set system-wide and cannot be configured per workspace like LLMs can.
Supported Embedding Model Providers
HEADS UP!
Once you select your embedding model provider and begin uploading and embedding documents it is best to not change it.
While you can change embedders, doing so means you must delete your uploaded documents and re-embed them with the new provider.
RealTimeX supports many embedding model providers out of the box, often with zero configuration.
You can change your embedding provider and model at any time—but doing so can result in broken queries and will require you to re-embed all uploaded/stored documents.
Local Embedding Model Providers
