DownloadBAAI/bge-large-en-v1.5 is a powerful English sentence embedding model designed by the Beijing Academy of Artificial Intelligence to enhance retrieval-augmented language model systems. It uses a BERT-based architecture fine-tuned to produce high-quality dense vector representations optimized for sentence similarity, search, and retrieval. This model is part of the BGE (BAAI General Embedding) family and delivers improved similarity distribution and state-of-the-art results on the MTEB benchmark. It is recommended for use in document retrieval tasks, semantic search, and passage reranking, particularly when paired with a reranker like BGE-Reranker. The model supports inference through multiple frameworks, including FlagEmbedding, Sentence-Transformers, LangChain, and Hugging Face Transformers. It accepts English text as input and returns normalized 1024-dimensional embeddings suitable for cosine similarity comparisons.
Features
- Pretrained and fine-tuned for dense text embedding
- Outputs 1024-dimensional sentence vectors
- Optimized for semantic similarity and retrieval tasks
- Achieves state-of-the-art results on MTEB leaderboard
- Compatible with Hugging Face, FlagEmbedding, and LangChain
- Suitable for reranking with BGE-Reranker
- Efficient batching and GPU usage support
- Licensed under MIT for commercial and research use
Project Samples
