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
..
__init__.py	chore: introduce write queue for inference_store (#3383)	2025-09-10 11:57:42 -07:00
datasets.py	refactor(logging): rename llama_stack logger categories (#3065)	2025-08-21 17:31:04 -07:00
eval_scoring.py	refactor(logging): rename llama_stack logger categories (#3065)	2025-08-21 17:31:04 -07:00
inference.py	chore: introduce write queue for inference_store (#3383)	2025-09-10 11:57:42 -07:00
safety.py	refactor(logging): rename llama_stack logger categories (#3065)	2025-08-21 17:31:04 -07:00
tool_runtime.py	refactor(logging): rename llama_stack logger categories (#3065)	2025-08-21 17:31:04 -07:00
vector_io.py	feat(vector-io): implement global default embedding model configuration (Issue #2729)	2025-09-18 10:11:44 -04:00