[Feature Request] Support Ollama Embedding

[huaxlin]

Motivation

Ollama has been supported embedding at v0.1.26 - Support for bert and nomic-bert embedding models

I think it's will be more easier ever before when every one get start with privateGPT, without extra setup step(python script/setup)

Usage^1

This model is an embedding model, meaning it can only be used to generate embeddings.

REST API

curl http://localhost:11434/api/embeddings -d '{
  "model": "nomic-embed-text",
  "prompt": "The sky is blue because of Rayleigh scattering"
}'

Python library

ollama.embeddings(model='nomic-embed-text', prompt='The sky is blue because of rayleigh scattering')

[Robinsane]

This can be closed, using Ollama embeddings in my own project as we speak :)

[huaxlin]

supported ollama embedding, refer to settings-ollama.yaml