skamenan7 17fbd21c0d feat(vector-io): implement global default embedding model configuration (Issue #2729) ... - Add VectorStoreConfig with global default_embedding_model and default_embedding_dimension - Support environment variables LLAMA_STACK_DEFAULT_EMBEDDING_MODEL and LLAMA_STACK_DEFAULT_EMBEDDING_DIMENSION - Implement precedence: explicit model > global default > clear error (no fallback) - Update VectorIORouter with _resolve_embedding_model() precedence logic - Remove non-deterministic 'first model in run.yaml' fallback behavior - Add vector_store_config to StackRunConfig and all distribution templates - Include comprehensive unit tests for config loading and router precedence - Update documentation with configuration examples and usage patterns - Fix error messages to include 'Failed to' prefix per coding standards Resolves deterministic vector store creation by eliminating unpredictable fallbacks and providing clear configuration options at the stack level.		2025-09-18 10:11:44 -04:00
..
ci-tests	feat: add Azure OpenAI inference provider support (#3396)	2025-09-11 13:48:38 +02:00
dell	fix: Dell distribution missing kvstore (#3113)	2025-08-13 06:18:25 -07:00
meta-reference-gpu	chore: remove absolute paths (#3263)	2025-08-27 12:04:25 -07:00
nvidia	fix: add missing files provider to NVIDIA distribution (#3479)	2025-09-18 13:49:46 +02:00
open-benchmark	fix: Remove bfcl scoring function as not supported (#3281)	2025-08-29 11:03:52 -07:00
postgres-demo	chore: update postgres_demo with new config (#3045)	2025-08-06 07:48:40 -07:00
starter	feat: combine ProviderSpec datatypes (#3378)	2025-09-18 16:10:00 +02:00
starter-gpu	feat: add Azure OpenAI inference provider support (#3396)	2025-09-11 13:48:38 +02:00
watsonx	feat(vector-io): implement global default embedding model configuration (Issue #2729)	2025-09-18 10:11:44 -04:00
__init__.py	chore: rename templates to distributions (#3035)	2025-08-04 11:34:17 -07:00
template.py	chore: rename templates to distributions (#3035)	2025-08-04 11:34:17 -07:00