Comment by drittich
7 months ago
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?
7 months ago
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?
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!