What's Changed

A few important updates some of which are backwards incompatible. You must update your run.yamls when upgrading. As always look to templates/<distro>/run.yaml for reference.

• Make embedding generation go through inference by @dineshyv in https://github.com/meta-llama/llama-stack/pull/606
• [/scoring] add ability to define aggregation functions for scoring functions & refactors by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/597
• Update the "InterleavedTextMedia" type by @ashwinb in https://github.com/meta-llama/llama-stack/pull/635
• [NEW!] Experimental post-training APIs! https://github.com/meta-llama/llama-stack/pull/540, https://github.com/meta-llama/llama-stack/pull/593, etc.

A variety of fixes and enhancements. Some selected ones:

• [#342] RAG - fix PDF format in vector database by @aidando73 in https://github.com/meta-llama/llama-stack/pull/551
• add completion api support to nvidia inference provider by @mattf in https://github.com/meta-llama/llama-stack/pull/533
• add model type to APIs by @dineshyv in https://github.com/meta-llama/llama-stack/pull/588
• Allow using an "inline" version of Chroma using PersistentClient by @ashwinb in https://github.com/meta-llama/llama-stack/pull/567
• [docs] add playground ui docs by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/592
• add colab notebook & update docs by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/619
• [tests] add client-sdk pytests & delete client.py by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/638
• [bugfix] no shield_call when there's no shields configured by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/642

New Contributors

• @SLR722 made their first contribution in https://github.com/meta-llama/llama-stack/pull/540
• @iamarunbrahma made their first contribution in https://github.com/meta-llama/llama-stack/pull/636

Full Changelog: https://github.com/meta-llama/llama-stack/compare/v0.0.61...v0.0.62