Give Feedback

Available Embeddings and Reranking Models for DigitalOcean Knowledge Bases

Validated on 23 Apr 2026 • Last edited on 27 Apr 2026

DigitalOcean Knowledge Bases let you store, index, and retrieve data from private files, websites, Spaces buckets, and other sources to power retrieval-augmented generation with your own content.

Copy page as Markdown View page as Markdown

The following embeddings and reranking models are available for Knowledge Bases.

Note

For pricing information, see the pricing page.

Embeddings Models

An embedding model converts data into vector embeddings. DigitalOcean stores vector embeddings in an OpenSearch database cluster for use with agent knowledge bases. The following embeddings models are available on the platform, along with their token windows and recommended chunking ranges.

Alibaba Models

Model	Parameters	Token Window	Chunk Size Range	Parent Chunk Range	Child Chunk Range
GTE Large (v1.5)	Not available	8192 tokens	0-750	500-1000	300-500
Qwen3 Embedding 0.6B (Multilingual) (in Public Preview)	600 million	8000 tokens	0-750	500-1000	300-500

BAAI Models

Model	Parameters	Token Window	Chunk Size Range	Parent Chunk Range	Child Chunk Range
BGE M3	568M	8192 tokens	0-8192	Not Specified	Not Specified

Microsoft Models

Model	Parameters	Token Window	Chunk Size Range	Parent Chunk Range	Child Chunk Range
E5 Large (v2)	Not available	512 tokens	0-512	Not Specified	Not Specified

UKP Lab (Technical University of Darmstadt) Models

Model	Parameters	Token Window	Chunk Size Range	Parent Chunk Range	Child Chunk Range
All-MiniLM-L6-v2	22 million	256 tokens	0-256	100-256	100-200
Multi-QA-mpnet-base-dot-v1	109 million	512 tokens	0-512	100-512	100-500

Reranking Models

Reranking models reorder retrieved results to improve relevance after the initial retrieval step. DigitalOcean supports the following reranking model for knowledge base retrieval:

BAAI Models

Model	Parameters	Usage Notes
BGE Reranker (v2) M3	Not available	Can be enabled at knowledge base creation, updated after creation.

Available Embeddings and Reranking Models for DigitalOcean Knowledge Bases

Embeddings Models

Reranking Models

We can't find any results for your search.