nixos/services/ollama.nix

{ config, pkgs, lib, ... }:
{
    config = lib.mkIf (config.networking.hostName == "FredOS-Mediaserver") {

        services.ollama.enable = true;
        # Quadro M2000 (Maxwell/GM206) uses legacy_535 driver which caps CUDA
        # at 12.2. nixpkgs has removed all CUDA versions ≤12.5 as unmaintained,
        # and 12.6+ requires driver ≥560. CPU inference is the only option.

        services.open-webui.enable = true;
        services.open-webui.port = 8888;
        services.open-webui.environment.WEBUI_AUTH = "False"; # auth handled by Authelia upstream

        nixpkgs.overlays = [
            (final: prev: {
                # We need to reach into the python package set
                pythonPackagesExtensions = prev.pythonPackagesExtensions ++ [
                    (python-final: python-prev: {
                        langchain = python-prev.langchain.overridePythonAttrs (oldAttrs: {
                            doCheck = false;
                        });
                    })
                ];
                # valkey 8.1.x has a flaky replication integration test that
                # fails non-deterministically; skip checks to unblock open-webui.
                valkey = prev.valkey.overrideAttrs (oldAttrs: {
                    doCheck = false;
                });
            })
        ];
    };
}