I am running a Python script on a Linux VM without CUDA support and a local OLLAMA. When checking OLLAMA on the console with ollama run jina/jina-embeddings-v2-base-de "Hello world" the response is very fast. Takes less than 2 seconds. When starting a script to embed email body the script is very slow. Especially it starts connecting to some host in the US. Please find the logger output below: 18:24:35 DEBUG : connect_tcp.started...
Originally asked by Lars Hinrichsen on Stack Exchange (stackoverflow) (CC BY-SA 4.0).