Differences

This shows you the differences between two versions of the page.

--- linux64 [2025/06/01 08:54] – [squeezebox/lyrionmusicserver for music] bengt
+++ linux64 [2025/07/13 14:09] (current) – [ollama in podman for ai] bengt
@@ Line 805: / Line 805: @@
 URL Redirect Record	@ http://www.johannesson.rocks Unmasked
 (If you keep the URL redirect stuff then the ip-addresses will be combined with namecheaps. Not good.)
+==== ollama in podman for ai ====
+Using rootless podman as a separate user (starting with cpu only):
+  # dnf install
+  # useradd ollama
+  # visudo
+  ALL ALL=(ollama) NOPASSWD: /home/ollama/start.sh
+  # firewall-config # Add tcp 11434 to be able to access it from hass
+  # su - ollama
+  $ mkdir ollama
+  $ vi start.sh
+  #!/bin/bash -x
+  cd $HOME
+  loginctl enable-linger ollama
+  podman run -d --rm -v /home/ollama/ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
+  $ chmod u+x start.sh
+Then setup a start.sh-script containing the startup command line and maybe start this using "lxterminal -t ollama -e sudo -u ollama /home/ollama/start.sh". Replace "-d" with "-it" in the podman command line to see the output if starting this way.
+Test it as the ollama user:
+  # su - ollama
+  $ podman exec -it ollama ollama run llama2
+You can add the ollama integration to home assistant. On issues check your firewall config. Be sure to have "conversation:" "assist_pipeline:" in configuration.yaml if you do not use the default config before trying to setup assist pipelines.
+TODO: GPU support. Need to use nvidia drivers first...