Interview: choose a sentence embedding model for a startup RAG.
mediumAnswer
- Constraints: quality vs cost vs latency vs vector dimension.
- (1) OpenAI text-embedding-3-small: cheap ($0.02/1M), 1536 dim, hosted.
- (2) Cohere embed-v3: multilingual, 1024 dim.
- (3) Open-source: bge-small-en-v1.5 (384 dim, fast, high MTEB score), E5-large-v2 (1024 dim, top-tier).
- (4) DIY fine-tuning: contrastive on domain pairs.
- Rule: start with bge-small / OpenAI-3-small for speed; benchmark on your data (MTEB score alone is misleading).
Check yourself — multiple choice
- Random
- OpenAI text-embed-3-small (cheap, hosted) / Cohere v3 (multilingual) / bge-small or E5 (OSS top) / DIY fine-tune; start with bge-small or OpenAI-3-small + benchmark on YOUR data
- Only proprietary
- Not real
Startup RAG embeddings: OpenAI-3-small / bge-small; benchmark on your data.
#interview#applications#nlp
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- Interview: users complain search returns irrelevant results — how do you fix?
- Interview: 'you have 1M support tickets — how do you categorize them?'
- Interview: 'you're asked to segment 10M customers — how?'
- Interview: 'design an unsupervised fraud detection system'.
- BM25 — why is it still competitive with modern retrievers?
- Vector search / approximate nearest neighbors — main algorithms.