The semantic index rebuilds incrementally on startup and as files change. If results seem stale, let it finish indexing (the status bar shows index state). If your local index hits a problem, V3Code falls back to the cloud index for free so search keeps working.
If you’re using Ollama and a call errors out, it usually means Ollama is powered off — start it and retry. For built-in local inference, make sure the model finished downloading.