Setup instructions
-
replace the values in
.env.example
and rename it to.env
-
in the root folder run the following command:
python manage.py runserver
Two ways:
- dont
- see llm/installscripts
- In llm/server.py set
ISDOCKER = True
and changePORT
if needed - Run the following in an elevated terminal:
docker build -t llm_server ./llm
docker run -it -p 2023:2023 --gpus all llm_server
TODO:
- refactor /llm to latest version of llamaindex
- fix output of zephyr