Skip to content

Text Embeddings

Models

DS1 currently provides two embedding models with the following specifications:

Model NameDimensionContext LengthTokenizerDescription
DS1-EN-V1512 (L2 normalized)512 tokens30k WordPieceHigh-performance English text retrieval model
DS1-MULTILINGUAL-V1256 (L2 normalized)200,000 max tokens/requestMultilingual tokenizerMultilingual retrieval model for cross-language semantic search

Tokenization

Tokenizer configuration differs by model:

Model NameVocabulary SizeTokenizer ConfigSpecial Tokens
DS1-EN-V130,000model_max_length: 512[PAD], [UNK], [CLS]
DS1-MULTILINGUAL-V1250,002model_max_length: 200KBOS, CLS, EOS, MASK, PAD, SEP, UNK

Modality

DS1 is a text-only embedding model family optimized for semantic search and retrieval.

Runtime Request Limits

The following limits are runtime API/container limits and are not intrinsic model capabilities.

  • Use up to 32 texts per request.
  • Keep payloads compact to avoid endpoint memory pressure on smaller instances.
  • For large corpora, process in chunks of 16 to 32 texts and retry failed chunks.

Want to know about additional models? Check out our FAQ.