baai/bge-m3
text embedding model. This model is capable of simultaneously achieving three core functionalities: dense retrieval, multi-vector retrieval, and sparse retrieval. Designed to be compatible with over 100 languages, it supports a variety of input formats, ranging from short sentences to long texts of up to 8,192 tokens.
For detailed usage instructions, please refer to the API documentation: Model-BAAI: BGE-M3
Updated time: March 13, 2025