alihan/genai-stack-neo4j
1
0
Fork 0
mirror of https://github.com/docker/genai-stack.git synced 2024-08-30 16:49:54 +03:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Linux nvidia GPU option"

Browse Source 
This reverts commit 76f031856a.
This commit is contained in:
Michael Hunger
2023-11-03 17:16:06 +01:00
parent 76f031856a
commit 4071ae1b69
1 changed files with 0 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
readme.md
View File

@@ -38,19 +38,6 @@ No need to install Ollama manually, it will run in a container as
part of the stack when running with the Linux profile: run `docker compose --profile linux up`.
Make sure to set the `OLLAMA_BASE_URL=http://llm:11434` in the `.env` file when using Ollama docker container.
If run into issues that your Nvidia GPU is not used under Linux (despite using the profile), ensure that you have `nvidia-container-toolkit` installed.
And add this to the `llm` service.
```yaml
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
```
**Windows**
Not supported by Ollama, so Windows users need to generate a OpenAI API key and configure the stack to use `gpt-3.5` or `gpt-4` in the `.env` file.
# Develop