embedding dimensions
The number of values in each embedding vector, fixed by the model, which drives storage size and search cost.
In more detail
More dimensions can hold finer distinctions but cost more memory and time per comparison. Some models are trained so their vectors can be truncated to fewer dimensions with little loss; others lose badly when cut.
Related terms
- embedding vector — A list of numbers that represents a piece of text, or an image, so that items with similar meaning lie close together.
- Matryoshka embeddings — Embeddings trained so that the first part of each vector is itself a useful smaller embedding, allowing safe truncation.
- embedding quantization — Storing embedding values in fewer bits, such as one byte (int8) or one bit (binary) per dimension, to save memory and speed up search.
Taught in
- Embedding Models — AI Engineering: LLM Apps, RAG & Agents
- Vector Indexes And Databases — AI Engineering: LLM Apps, RAG & Agents
- Model-Graded Evals — AI Engineering: LLM Apps, RAG & Agents
References
- OpenAI: Vector embeddings guide (dimensions parameter)
- Kusupati et al.: Matryoshka Representation Learning (arXiv 2205.13147)