I have this below code that works well when I connect to OpenAI. I am trying to do the same using llama2 but I am having trouble using the right embedding technique.. In the below code I use OpenAIEmbeddings, want some help to find how can this be tweaked to run well using llama2 model

I have set up the ollama docker image on docker compose locally and on a vps.
Same image (ollama/ollama:latest), same ollama configurations (no env variables), same model (llama3:8b).