Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[编程挑战季] ModelCache检索的Reranker 能力 #55

Open
peng3307165 opened this issue Oct 17, 2024 · 2 comments
Open

[编程挑战季] ModelCache检索的Reranker 能力 #55

peng3307165 opened this issue Oct 17, 2024 · 2 comments
Assignees

Comments

@peng3307165
Copy link
Collaborator

peng3307165 commented Oct 17, 2024

  1. 问题简述
    通过向量数据库检索embedding作为初次召回,仅通过L2或者cosine计算相似度,无法保障召回的query和用户的query完全匹配,希望完善Reranker能力,使用reranker模型进行二次排序,增加Cache的命中的准确性。
  2. 期望产出
    在ModelCache的 adapter_query 模块增加Reranker模块,实现二次排序能力。
  3. 能力要求
    熟悉python代码,了解prompt工程。
@peng3307165 peng3307165 changed the title [ModelCache] Reranker 能力 [编程挑战季] ModelCache检索的Reranker 能力 Nov 13, 2024
@charleschile
Copy link
Contributor

Please assign this to me, I will try to use bge reranker and other open-source models.

@DreamCyc
Copy link

Oh, I'm late. If the previous student is too busy to handle it, I can assist in completing it. Additionally, the BGE embedding model is quite effective in terms of representation capability.

@peng3307165 peng3307165 moved this from Todo to In Progress in CodeFuse编码挑战季 Nov 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: In Progress
Development

No branches or pull requests

3 participants