krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-09 21:08:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

added multimodal models

Browse Source
This commit is contained in:
Manas Chopra
2026-07-30 04:38:46 +05:30
parent 78d79e043a
commit 4236b507ce
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/articles/fastembed.md
+5 -4
View File
@@ -130,10 +130,11 @@ This is intentional. FastEmbed is engineered to deliver optimal performance righ
FastEmbed has grown well beyond dense text embeddings. Today it supports: FastEmbed has grown well beyond dense text embeddings. Today it supports:
- **Dense embeddings** – the default `TextEmbedding` model used throughout this article - **Dense embeddings** – the default `TextEmbedding` model used throughout this article (e.g. `BAAI/bge-small-en-v1.5`, multilingual-e5, nomic-embed-text-v2-moe)
- **Sparse embeddings** – SPLADE and miniCOIL, for exact keyword-style retrieval - **Sparse embeddings** – `SparseTextEmbedding` models including BM25, SPLADE, and miniCOIL for exact keyword-style retrieval
- **Multi-vector embeddings** – ColBERT, ideal for rescoring and small-scale retrieval - **Multi-vector embeddings** – `LateInteractionTextEmbedding` models including ColBERT, ideal for rescoring and small-scale retrieval
- **Rerankers** – cross-encoders to re-rank top-K results - **Image embeddings** – `ImageEmbedding` models including CLIP variants for visual and multimodal search
- **Rerankers** – `TextCrossEncoder` cross-encoders to re-rank top-K results (e.g. ms-marco-MiniLM)
- **Postprocessing** – MUVERA, for compressing multi-vector embeddings into single fixed-size vectors for fast first-stage search - **Postprocessing** – MUVERA, for compressing multi-vector embeddings into single fixed-size vectors for fast first-stage search
Most of the models we support are [quantized](https://pytorch.org/docs/stable/quantization.html) to enable even faster computation! Most of the models we support are [quantized](https://pytorch.org/docs/stable/quantization.html) to enable even faster computation!