BCEmbedding: Bilingual and Crosslingual Embedding for RAG 最新、最详细bce reranker base v1相关信息，请移步（The latest "Updates" should be checked in）： GitHub 主要特点(Key Features)： 中英日韩四个语种，以及中英日韩四个语种的跨语种能力(Multilingual and Crosslingual capability in English, Chinese, Japanese and Korean)； RAG优化，适配更多真实业务场景(RAG adaptation for more domains, including Education, Law, Finance, Medical, Literature, FAQ, Textbook, Wikipedia, etc.)； BCEmbedding 适配长文本做rerank(Handle long passages reranking more than 512 limit in BCEmbedding )； RerankerModel可以提供 “绝对”分数 ，低质量passage过滤阈值推荐0.35或0.4。（RerankerModel provides "meaningful" (for filtering bad passages with a threshold of 0.35 or 0.4) similarity score ） 最佳实践（Best practice） ：embedding召回top50 100片段，reranker对这50 100片段精排，最后取top5 10片段。（1. Get top 50 100 passages with bce embedding base v1 for " recall "； 2. Rerank passages with bce reranker base v1 and get top 5 10 for " precision " finally. ） News: BCEmbedding 技术博客（ Technical Blog ）: 为RAG而生 BCEmbedding技术报告 Related link for EmbeddingModel : bce embedding base v1 Third party Examples: RAG applications: QAnything, ragflow, HuixiangDou, ChatPDF. Efficient inference framework: ChatLLM.cpp, Xinference, mindnlp (Huawei GPU, 华为GPU…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy