嵌入模型为何必须开源
论证要点
- 嵌入模型的应用通常涉及计算成千上万甚至数百万个向量并存储,供后续比较使用。
- 若模型为专有,供应商未来可能停止提供该模型;即便有更好的替代,用户仍需付费重新计算已存储的百万级向量。
- 作者引用 OpenAI 2024 年 4 月曾提出承担用户用新模型重新嵌入内容的财务成本,但认为不能指望每个供应商都这样做。
- 作者明确表示不想自己托管模型,更愿意付费使用托管服务,但前提是知道供应商停服后可以自行运行开源权重版本或找其他供应商。
- 因此,作者高度赞赏 EmbeddingGemma 2 采用 Apache 2.0 许可证,认为这对嵌入模型尤其重要。
对实践的启示
对做 AI 应用的人来说,选择嵌入模型时需考虑长期成本与供应商锁定风险。优先选择开源权重模型,即使当前使用托管服务,也能在供应商停服时自主运行或迁移,避免重新计算海量向量的高昂代价。
原文摘引
For embedding models in particular, I don't think it makes sense to use a closed, proprietary, hosted-only model.
If your model is proprietary, the vendor is likely someday going to decide to stop offering that model.
I'd much rather pay a provider for a hosted model while knowing that if they ever stop hosting it I can run the open weights version myself - or find another vendor who can do that for me.
▸ 展开原文全文(11 段,抓取自 Simon Willison)
6th October 2026
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.
(In April 2024 OpenAI offered to "cover the financial cost of users re-embedding content with these new models" - https://openai.com/index/gpt-4-api-general-availability/ - but I don't think that's something we can rely on from every provider.)
Notably, I don't want to host the model myself. I'd much rather pay a provider for a hosted model while knowing that if they ever stop hosting it I can run the open weights version myself - or find another vendor who can do that for me.
Recent articles
- We're going to need default hard budget caps on pretty much everything - 3rd October 2026
- OpenAI DevDay 2026 live blog - 29th September 2026
- 2026 in LLMs (so far) - 27th September 2026