Add Support for Ollama - Githubissues

timescale / pgai

Bring AI models closer to your PostgreSQL data

PostgreSQL License

318 stars 11 forks source link

Closed jgpruitt closed 2 weeks ago

jgpruitt commented 2 weeks ago

Adds support for interacting with LLMs running in Ollama.

jgpruitt commented 2 weeks ago

@jonatas is Ollama running on your host machine and pgai running in docker? If so, you need to use http://host.docker.internal:11434

jgpruitt commented 2 weeks ago

If that fixes it, I guess I should improve the docs with this info

jonatas commented 2 weeks ago

Yes! it works @jgpruitt! thanks for the update 👍

jgpruitt commented 2 weeks ago

@jonatas Oh wow! Good point. I guess I'm spoiled with my Apple M2 Pro. I didn't realize how slow it could be.