-
Notifications
You must be signed in to change notification settings - Fork 44
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
检索效果问题 #49
Comments
您测试的是什么数据集啊?能看看您测试了哪些query吗? |
我在NeurIPS中选择了一篇论文PDF 用VisRAG-master/scripts/demo/visrag_pipeline/build_index.py这个代码建立了索引,针对PDF的其中一页中的文本,提一个问题,而且我刚刚发现一个bug,对多篇论文PDF进行建立索引(即一个index文件夹下生成多个npy文件时候)检索到的页面相当不准。但是当我提前手动把几个PDF论文合并成一个PDF,然后再建立索引(即一个index文件夹下生成一个npy文件),检索的效果就会很准确。请您能给我解答一下吗? |
提的都是一些英文问题,例如How can investigators adjust for the impact on statistical inference when stopping an experiment in only one region? What does Figure 2 illustrate about CLASH's performance when the minority group is harmed compared to other methods? 应该和问题没关系 也有检索准确的时候。 关键的问题是 |
您好,我主要关注的是您VisRAG-Ret检索方面的性能,我发现了一个问题,我在您的训练集中选择了一篇进行测试,当我的index中只有这一篇PDF时候,检索的效果(关注检索到的页面是否准确)还是不错的,但是当我把index扩充到三篇PDF,问了同样的问题(测试了多个问题),检索的效果很差,您能给我解答一下吗?
The text was updated successfully, but these errors were encountered: