Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,7 @@ language:
|
|
| 39 |
- 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.)；
|
| 40 |
- <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>适配长文本做rerank(Handle long passages reranking more than 512 limit in <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>)；
|
| 41 |
- RerankerModel可以提供可靠的 **相关性分数**，用于过滤低质量passage（RerankerModel provides **meaningful similarity score**, which help you figure out how relavent the query and passages are!）
|
|
|
|
| 42 |
|
| 43 |
## News:
|
| 44 |
- `BCEmbedding`技术博客（ **Technical Blog** ）: [为RAG而生-BCEmbedding技术报告](https://zhuanlan.zhihu.com/p/681370855)
|
|
|
|
| 39 |
- 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.)；
|
| 40 |
- <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>适配长文本做rerank(Handle long passages reranking more than 512 limit in <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>)；
|
| 41 |
- RerankerModel可以提供可靠的 **相关性分数**，用于过滤低质量passage（RerankerModel provides **meaningful similarity score**, which help you figure out how relavent the query and passages are!）
|
| 42 |
+
- *** 最佳实践（Best practice） *** ：embedding召回top50～100，reranker对这50～100精排，最后取top5～10。（1. Get top 50~100 passages with [bce-embedding-base_v1](https://huggingface.co/maidalun1020/bce-embedding-base_v1) for `recall`. 2. Rerank passages with [bce-reranker-base_v1](https://huggingface.co/maidalun1020/bce-reranker-base_v1) and get top 5~10 for `precision` finally. ）
|
| 43 |
|
| 44 |
## News:
|
| 45 |
- `BCEmbedding`技术博客（ **Technical Blog** ）: [为RAG而生-BCEmbedding技术报告](https://zhuanlan.zhihu.com/p/681370855)
|