bge is short for BAAI general embedding. [1]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly.
Introduction
bge is short for BAAI general embedding. [1]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, no instruction needs to be added to passages. [2]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models. For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results.
Key Features
- In all cases, no instruction needs to be added to passages. [2]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding.
- To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.
- For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results.
