How do you pick an embedding model for a new RAG project?

medium

Answer

$Criteria: (1) MTEB leaderboard score for your task type (retrieval, STS, classification); (2) language coverage — E5, BGE, Cohere multilingual for non-English; (3) max input length — most cap at 512 tokens; longer models (Jina, Nomic, BGE-M3) go 8k+; (4) dimension — 768/1024 typical; 3072 for OpenAI text-embedding-3-large; (5) cost + license.$
$Modern strong choices: BGE-M3, E5-mistral, Nomic v1.5, Cohere v3, OpenAI text-embedding-3.$
$Always validate on your own retrieval eval set — MTEB is not your domain.$

Check yourself — multiple choice

Pick the highest MTEB
MTEB score + language + length + dim + cost — then validate on your own retrieval eval set (MTEB is not your domain)
Random choice
Only OpenAI's model

Embedding choice: MTEB / language / length / cost + always validate on your data.

#embeddings#retrieval

214 interview questions in this topic.