Fetching metadata from the HF Docker repository...
-
feat: use local guard model
Not ideal, but better than disabling -
chore: correct ollama model dir
It was being run as the root user, but then used as the non-root user. -
chore: pull model again on runtime
Should be cached, so shouldnt require too much time.
-
feat: use local ollama for embedding model
-
chore: update readme
-
chore: use a better name
-
chore: import scripts to process nml-docs
-
feat: update to use new webgui
-
fix: correct server url
-
feat: update configs for klea updates
-
feat: update for latest rag
-
fix: update vector store config
-
feat: update docker and env files
Models on HF have changed again. Waiting to get access from
Llama 4 for the guard model.
-
feat: limit api to internal hostname
-
feat: correct vector store paths
-
feat(stores): make a couple relative
To see if the rag code works correctly here too.
-
chore: use fastapi `run`
-
feat(deployment): update huggingface
-
feat: add dockerfile
