The BGE-EN-ICL embedding model is a state-of-the-art solution for embedding-based tasks, ranking highly on the MTEB leaderboard due to its exceptional capabilities. It excels in in-context learning, leveraging few-shot examples provided within the query to adapt to new tasks effectively. This dynamic adaptability enables it to outperform competitors, achieving SOTA performance on both the BEIR and AIR-Bench benchmarks. With its robust architecture and versatility, BGE-EN-ICL sets a new standard for embedding models in diverse application scenarios.

For instructions on accessing this model or initializing it via API, please refer to our docs.