What is the role of embedding dimensionality and model choice in retrieval quality?medium

Type
conceptual
Topic
is-the-role-of-embedding-dimensionality-and-model-choice-i
Frequency
common
Tags
rag, what, the, role, embedding, dimensionality
Answer

Higher dimensionality: more expressive but slower ANN search and more memory.

Explanation

Higher dimensionality: more expressive but slower ANN search and more memory. Common: 768d (BERT), 1536d (OpenAI ada-002), 1024d (Cohere). Model choice matters more than dimensionality: a domain-fine-tuned 768d model often beats a general 1536d model. Benchmark with MTEB or run retrieval evals on your own data. For financial documents, Cohere or fine-tuned models outperform general-purpose embeddings.

Follow-upCan you give a production example?