private-gpt
private-gpt copied to clipboard
How to speed up ingestion
I'm curious about this and how to speed up. Is it Ollama issue? The size of my xxx.csv file is 15M. Ingestion costs 25 minutes.
If you installed Ollama recently you may want to try this: https://github.com/ollama/ollama/issues/3029#issuecomment-1987177366
In the last ollama version (v.2.0), you can select how many concurrent requests and parallel you want. Please check this article :)