Skip to content
Why did we open-source our inference engine? Read the post

Migrate to SIE

If you’re already running embedding inference somewhere else, these guides give you the smallest path to running it on SIE. Working before/after code per provider, plus a mapping from every provider concept to its SIE counterpart.

Pick your starting point:

Each guide ships before/after code in the page. Run both legs on a small corpus from your own domain, print the embeddings, and check they look sane. That is a sanity check, not sign-off.

For sign-off, run your own retrieval eval against both legs:

  • Same checkpoint (Fastembed, TEI, Infinity, Modal-with-same-model). Cosine should sit at 0.999 or higher across items. If it doesn’t, the config differs (pooling, normalization, dtype); the guide’s caveats section calls out where.
  • Different model (OpenAI → E5, Cohere → Stella or E5). Absolute cosine carries no signal across spaces. Run recall@k on a labeled set you trust, or a BEIR/MTEB slice that resembles your domain.
Source modelClosest SIE modelRe-embed
text-embedding-3-smallintfloat/e5-base-v2yes
text-embedding-3-largeAlibaba-NLP/gte-Qwen2-1.5B-instructyes
embed-english-v3.0 (Cohere)NovaSearch/stella_en_400M_v5yes
rerank-v3.0 (Cohere)BAAI/bge-reranker-v2-m3n/a
TEI / Infinity / Fastembed bge-*same checkpoint on SIEno
sentence-transformers on Modalsame checkpoint on SIEno

Browse the full model catalog for everything SIE serves out of the box.

Open an issue at superlinked/sie, or send a PR adding a new page to the migrate/ directory in superlinked/sie-web.

Contact us

Tell us about your use case and we'll get back to you shortly.