v0.1.1

A bunch of small / big improvements everywhere including support for Windows, switching to uv and many provider improvements.

What's Changed

• Update doc templates for running safety on self-hosted templates by @hardikjshah in #874
• Update GH action so it correctly queries for test.pypi, etc. by @ashwinb in #875
• Fix report generation for url endpoints by @hardikjshah in #876
• Fixed typo by @BakungaBronson in #877
• Fixed multiple typos by @BakungaBronson in #878
• Ensure llama stack build --config <> --image-type <> works by @ashwinb in #879
• Update documentation by @ashwinb in #865
• Update discriminator to have the correct mapping by @ashwinb in #881
• Fix telemetry init by @dineshyv in #885
• Sambanova - LlamaGuard by @snova-edwardm in #886
• Update index.md by @Ckhanoyan in #888
• Report generation minor fixes by @sixianyi0721 in #884
• adding readme to docs folder for easier discoverability of notebooks … by @heyjustinai in #857
• Agent response format by @hanzlfs in #660
• Add windows support for build execution by @VladOS95-cyber in #889
• Add run win command for stack by @VladOS95-cyber in #890
• Use ruamel.yaml to format the OpenAPI spec by @ashwinb in #892
• Fix Chroma adapter by @ashwinb in #893
• align with CompletionResponseStreamChunk.delta as str (instead of TextDelta) by @mattf in #900
• add NVIDIA_BASE_URL and NVIDIA_API_KEY to control hosted vs local endpoints by @mattf in #897
• Fix validator of "container" image type by @terrytangyuan in #901
• Update OpenAPI generator to add param and field documentation by @ashwinb in #896
• Fix link to selection guide and change "docker" to "container" by @terrytangyuan in #898
• [#432] Groq Provider tool call tweaks by @aidando73 in #811
• Fix running stack built with base conda environment by @dvrogozh in #903
• create a github action for triggering client-sdk tests on new pull-request by @sixianyi0721 in #850
• log probs - mark pytests as xfail for unsupported providers + add support for together by @sixianyi0721 in #883
• SambaNova supports Llama 3.3 by @snova-edwardm in #905
• fix ImageContentItem to take base64 string as image.data by @yanxi0830 in #909
• Fix Agents to support code and rag simultaneously by @hardikjshah in #908
• add test for user message w/ image.data content by @mattf in #906
• openapi gen return type fix for streaming/non-streaming by @yanxi0830 in #910
• feat: enable xpu support for meta-reference stack by @dvrogozh in #558
• Sec fixes as raised by bandit by @hardikjshah in #917
• Run code-gen by @hardikjshah in #916
• fix rag tests by @hardikjshah in #918
• Use uv pip install instead of pip install by @ashwinb in #921
• add image support to NVIDIA inference provider by @mattf in #907

New Contributors

• @BakungaBronson made their first contribution in #877
• @Ckhanoyan made their first contribution in #888
• @hanzlfs made their first contribution in #660
• @dvrogozh made their first contribution in #903

Full Changelog: v0.1.0...v0.1.1