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