I'll show you how OpenClaw combines vector and keyword search using a weighted score fusion strategy. By default, vector results get % weight and keyword results get %. The candidateMultiplier setting controls how many candidates each search path retrieves before fusion.
With a candidateMultiplier of and a final result limit of , each path fetches candidates. The fusion step merges both lists and applies weights. It then deduplicates and returns the top . You can tune the weights in your config if your workflow favors exact matches over semantic ones or vice versa.