Create high-accuracy 1024-dimensional multilingual embeddings for semantic search, RAG, similarity, clustering, and classification across Southeast Asia. SEA-LION E5 Embedding 600M is developed by AI Singapore. Adjust the available settings to shape the result for your task.
Model
aisingapore/SEA-LION-E5-Embedding-600M
Documentation
Use this reference to understand how every field in the playground changes the request sent to aisingapore/SEA-LION-E5-Embedding-600M.
Required
Type: Text
Provides one text string or a JSON list of texts to convert into embedding vectors. Each input produces a semantic vector for retrieval, clustering, or similarity comparison; use consistent task prefixes when the model documentation recommends them.
Optional
Type: Boolean
Default: On
Allows the tokenizer to discard tokens when an input is longer than the configured maximum or model context. Turning it off surfaces an error instead of silently losing content, which is safer when every part of the input matters.
Optional
Type: JSON object
Default: None
Provides advanced keyword arguments to the tokenizer before embeddings are computed. Use it to control padding, truncation, or maximum length; truncating too aggressively can remove text that is important to semantic similarity.
Optional
Type: Boolean
Default: Off
Returns numeric generated token IDs as tensors rather than ordinary readable text. This is useful for downstream model processing or custom decoding, but most applications should leave it off.