Embedding model vendor lock-in and high re-embedding cost
Problem
Users face vendor lock-in risk when using proprietary embedding models, requiring costly re-embedding of millions of stored vectors when switching models. Additionally, the lack of moderate-size multimodal embedding models hinders development of local/fast embedding tooling.
Pain points
- Proprietary embedding models cause vendor lock-in, requiring costly re-embedding of stored vectors when switching models.
- Lack of moderate-size multimodal embedding models hinders development of local/fast embedding tools.
Questions to verify
- Are you using an embedding model that requires long-term vector storage? Do you face cost when switching models and recomputing?
- Do you need a moderate-size multimodal embedding model for local deployment?
Evidence
quote · @Anonymous
I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license. For embedding models in particular, I don't think it makes sense to use a closed, proprietary, hosted-only model. Most applications of embedding models involve calculating thousands or even millions of embedding vectors and storing them for later comparison. If your model is proprietary, the vendor is likely someday going to decide to stop offering that model. They'll have a better model to replace it, but you still need to pay to re-calculate those millions of stored existing vectors.
quote · @Anonymous
Finally. I was getting annoyed that there's been an inflection point in how LLMs/agents work but there hasn't been a good moderate-size embeddings model, and this one is multimodal too! 270M for text only is great compared to older embedding models, and a total 440M for text + vision is also fair. I also may or may not have a tool for much faster local embedding creation that I calibrated for EmbeddingGemma but didn't want to release until a better embedding model came along.
Disclaimer: this card is distilled by AI from community discussions as “pain point evidence”. It is a starting point for need analysis and validation, not a “validated market need”. AI has analytical limits; please open the original discussion above to manually verify before key decisions.