Ask HN: Best Embedding Models?

15 points | by devstein a day ago ago

15 comments

  • PhilippGille 19 hours ago ago

    Benchmarks only paint part of the picture, but it's still a decent place to start looking into recent models:

    https://huggingface.co/spaces/mteb/leaderboard

  • stevenfazzio 9 hours ago ago

    Cohere's embed-v4.0 is my daily driver as far as a high performance model is concerned. I do a lot of cluster analysis and data visualization and I like that there's an `input_type="clustering"` mode in addition to the standard `input_type="search"` mode.

    For a fast, open, and local model, I've found it hard to beat https://huggingface.co/sentence-transformers/all-MiniLM-L6-v...

  • rapatel0 21 hours ago ago

    I've liked qwen and embeddinggemma for local search. Qwen because 32K is enough to basically fit a whole page into the context window and embeddiggemma because it's crazy efficient.

  • sp1982 8 hours ago ago

    I am using openai small embedding model with custom compression. It is super cheap. You can read more at https://corvi.careers/blog/vector-search-embedding-compressi...

  • pstorm 10 hours ago ago

    Just fyi, for RAG/similarity search, adding a reranker was much bigger pay off than switching embedding models.

    • devstein 5 hours ago ago

      What top K do you use for vector search before passing into the reranker?

  • emschwartz 13 hours ago ago

    I’ve been using MixedBread, which is a pretty old model at this point. Recently, I tried comparing it to some newer models and was disappointed that the results weren’t dramatically and uniformly better.

    You probably can’t go wrong if you pick a recent one that scores decently well on benchmarks and is at the right price point (or memory requirement) for whatever you’re trying to do.

  • LogicCraft678 14 hours ago ago

    Feels like embeddings are underrated compared to LLM's hype, but they doing great.

    • Alifatisk 10 hours ago ago

      Why do you feel like embeddings are underrated? What is it with embeddings that deserves more attention?

  • preetsojitra 9 hours ago ago

    Meta's Perception Encoder Audio-Visual, its CLIP like but has three modality: Audio, Video and Text

  • didgeoridoo 15 hours ago ago

    I’m partial to jina.ai — they have open models for code and prose, all easily runnable locally.

  • jayshah5696 20 hours ago ago

    embeddings are easy to fine tune. Try modern bert.

  • Yogeshshirsath 12 hours ago ago

    E5 (Microsoft)

  • halvorbuilds 13 hours ago ago

    gemma4

  • frederickabrah 14 hours ago ago

    who knows a tool for rug check in crypto