llama-stack-mirror/docs/source/distributions
skamenan7 32930868de tightened vector store embedding model validation
includes:
- require models to exist in registry before use
- make default_embedding_dimension mandatory when setting default model
- use first available model fallback instead of hardcoded all-MiniLM-L6-v2
- add tests for error cases and update docs
2025-09-18 10:51:50 -04:00
..
eks fix: update k8s templates (#2645) 2025-07-08 15:57:01 -07:00
k8s fix(k8s): unwedge run.yaml to add files 2025-09-09 23:02:26 -07:00
ondevice_distro chore: remove absolute paths (#3263) 2025-08-27 12:04:25 -07:00
remote_hosted_distro refactor: remove Conda support from Llama Stack (#2969) 2025-08-02 15:52:59 -07:00
self_hosted_distro fix: add missing files provider to NVIDIA distribution (#3479) 2025-09-18 13:49:46 +02:00
building_distro.md fix(docs): update llama stack build CLI doc (#3050) 2025-08-06 09:32:09 -07:00
configuration.md tightened vector store embedding model validation 2025-09-18 10:51:50 -04:00
customizing_run_yaml.md docs: clarify run.yaml files are starting points for customization (#2746) 2025-07-14 09:53:13 -07:00
importing_as_library.md chore: remove absolute paths (#3263) 2025-08-27 12:04:25 -07:00
index.md docs: part 1 - fix warnings in documentation generation (#2861) 2025-07-30 10:50:10 -07:00
list_of_distributions.md fix: Restore the nvidia distro (#2639) 2025-07-07 15:50:05 -07:00
starting_llama_stack_server.md refactor: remove Conda support from Llama Stack (#2969) 2025-08-02 15:52:59 -07:00