EmbeddingGemma 2 采用 Apache 2.0 开源许可，适合长期向量化存储场景
EmbeddingGemma 2
Google 把 EmbeddingGemma 2 用 Apache 2.0 开源了，做 RAG 存几百万条向量的朋友值得看看这篇讲为什么别用闭源 embedding 的分析。
EmbeddingGemma 2 以 Apache 2.0 许可发布，允许自由托管与商用。作者认为 embedding 模型尤其不适合用闭源托管服务，因为应用往往要预先计算并存储数百万条向量，供应商一旦下线旧模型就得付费重算。OpenAI 在 2024 年 4 月 GPT-4 API 发布时曾承诺承担用户迁移到新 embedding 模型的重算费用，但这并非所有供应商都能保证。开源权重的好处是可以先付费托管，供应商停服后自行运行或换一家供应商接手。
EmbeddingGemma 2
My comment on EmbeddingGemma 2 — Hacker News. 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. Tags: google , ai , generative-ai , embeddings , gemma
