Skip to content

Commit

Permalink
Update RAG框架中的Rerank算法评估.md
Browse files Browse the repository at this point in the history
  • Loading branch information
kuozo authored Aug 22, 2024
1 parent dc5c279 commit 92a880b
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions docs/RAG框架中的Rerank算法评估.md
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ class QuerySuite(BaseModel):
top_k: int = 1


@ app.post('/bge_base_rerank')
@app.post('/bge_base_rerank')
def rerank(query_suite: QuerySuite):
scores = reranker.compute_score([[query_suite.query, passage] for passage in query_suite.passages])
if isinstance(scores, list):
Expand Down Expand Up @@ -118,4 +118,4 @@ curl --location 'http://localhost:50072/bge_base_rerank' \

本文详细介绍了RAG框架中的两种Rerank模型的评估实验:bge-reranker和Cohere Rerank,算是在之前Retrieve算法评估实验上的延续工作,后续将会有更多工作持续更新。

本文的所有过程及指标结果已开源至Github,网址为:[https://github.com/percent4/embedding_rerank_retrieval](https://github.com/percent4/embedding_rerank_retrieval) .
本文的所有过程及指标结果已开源至Github,网址为:[https://github.com/percent4/embedding_rerank_retrieval](https://github.com/percent4/embedding_rerank_retrieval) .

0 comments on commit 92a880b

Please sign in to comment.