From 35ba9de4713119c44717bfd9b7880c6bb066f395 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ozan=20Arma=C4=9Fan?= <70442658+ozanarmagan@users.noreply.github.com> Date: Sun, 30 Nov 2025 11:00:28 +0000 Subject: [PATCH] Add table of officially supported models for vector search Added a table listing officially supported models for vector search, including their embedding dimensions, languages, and parameters. --- docs-site/content/30.0/api/vector-search.md | 27 ++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/docs-site/content/30.0/api/vector-search.md b/docs-site/content/30.0/api/vector-search.md index 560d1d21..d019ab18 100644 --- a/docs-site/content/30.0/api/vector-search.md +++ b/docs-site/content/30.0/api/vector-search.md @@ -935,7 +935,32 @@ curl 'http://localhost:8108/collections' \ When you create a collection with the schema above, the `all-MiniLM-L12-v2` model will be downloaded and your documents will be automatically embedded by this model and will be stored in the `embedding` field. -See our [Hugging Face repo](https://huggingface.co/typesense/models/tree/main) for all officially supported models. +#### Officially Supported Models + +| Model | Embedding Dimensions | Languages | Parameters | +|---|---|---|---| +| `all-MiniLM-L12-v2` | 384 | English | 33.4M | +| `distilbert-base-uncased` | 768 | English | 66M | +| `distiluse-base-multilingual-cased-v2` | 512 | 50+ | 135M | +| `e5-large-v2` | 1024 | English | 335M | +| `e5-large` | 1024 | English | 335M | +| `e5-small-v2` | 384 | English | 33.4M | +| `e5-small` | 384 | English | 33.4M | +| `finbert` | 768 | English | 110M | +| `GATE-AraBert-v1` | 768 | Arabic | 110M | +| `gte-large` | 1024 | English | 335M | +| `gte-small` | 384 | English | 34M | +| `jina-embeddings-v2-base-en` | 768 | English | 137M | +| `multilingual-e5-base` | 768 | 100+ | 278M | +| `multilingual-e5-large` | 1024 | 100+ | 560M | +| `multilingual-e5-small` | 384 | 100+ | 118M | +| `nomic-embed-text-v1.5` | 768 | English | 137M | +| `paraphrase-MiniLM-L6-v2` | 384 | English | 22.7M | +| `paraphrase-multilingual-mpnet-base-v2` | 768 | 50+ | 278M | +| `snowflake-arctic-embed-m` | 768 | English | 110M | + + +See our [Hugging Face repo](https://huggingface.co/typesense/models/tree/main) for more details about the officially supported models. If you need support for additional publicly-available models, feel free to convert the model to ONNX format and send a PR to our [Hugging Face models repo](https://huggingface.co/typesense/models/tree/main). ### Using a GPU (optional)