Ask HN: Best Embedding Models?

18 points by devstein 59 days ago | 18 comments

Hey HN, which embedding models are people using? There has been so much development around foundational LLMs, but haven't seen much news about embedding models.

PhilippGille 59 days 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

rapatel0 59 days 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.

stevenfazzio 58 days 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...

emschwartz 59 days 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.

pstorm 58 days ago |

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

devstein 58 days ago | |

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

pstorm 58 days ago | | |

At a minimum, you increase top-k to cast a wider net, then after reranking, take the N you really want. You have to play around with it a bit, but that’s the idea.

sp1982 58 days 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...

LogicCraft678 59 days ago |

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

Alifatisk 58 days ago | |

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

preetsojitra 58 days ago |

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

didgeoridoo 59 days ago |

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

jayshah5696 59 days ago |

embeddings are easy to fine tune. Try modern bert.

mutant 57 days ago |

not a single "of what data" or "in what env"

best in what?

sovenyr 58 days ago |

please check OpenAI embedding models - especially small one

Yogeshshirsath 58 days ago |

E5 (Microsoft)

frederickabrah 59 days ago |

who knows a tool for rug check in crypto

halvorbuilds 59 days ago |

gemma4