Hacker News Reader

How do you weight results between vector search and bm25? Do you fall back to bm25 when vector similarity is below a threshold, or maybe you tweak the weights by hand for each data set?

View on HN

The algorithm I use to get a final ranking from multiple rankings is called "reciprocal ranked fusion". I use the implementation described here: https://docs.llamaindex.ai/en/stable/examples/low_level/fusi...

Which is the implementation from the original paper.

Thanks, much appreciated!

Reply on news.ycombinator.com