Resume Matcher is an open source, free tool to improve your resume. It works by using language models to compare and rank resumes with job descriptions.
Hi,
very interesting work!
when I look into it, it shows score simply represents a given data in code. And it does not compute my resume. so where is the score actually computed?
Hi @ZeruiW
Yes, in order to computer similarity scores locally, the requirements are:
PyTorch
CUDA
Nvidia GPU (which supports CUDA)
Sentence Transformers
Enough RAM
So that's why I have used precomputed metrics. I ran the qdrant script in colab and got the scores out. At this point, there are ways like OpenAI embeddings or Cohere's embed API that can help get the embeddings easily without requiring heavy GPU loads. It's in pipeline, and I will get it on main as soon as possible, within this week.
Hi, very interesting work! when I look into it, it shows score simply represents a given data in code. And it does not compute my resume. so where is the score actually computed?