phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-26 14:18:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: configure vector-io provider with an embedding model

Browse source 
Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>
This commit is contained in:
Mustafa Elbehery 2025-07-31 13:07:03 +02:00
parent 1f0766308d
commit d8f013b35a
29 changed files with 228 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/inline/vector_io/milvus/config.py
View file

@ -12,6 +12,7 @@ from llama_stack.providers.utils.kvstore.config import (
KVStoreConfig,
SqliteKVStoreConfig,
)
from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
from llama_stack.schema_utils import json_schema_type
@ -20,6 +21,10 @@ class MilvusVectorIOConfig(BaseModel):
db_path: str
kvstore: KVStoreConfig = Field(description="Config for KV store backend (SQLite only for now)")
consistency_level: str = Field(description="The consistency level of the Milvus server", default="Strong")
embedding: EmbeddingConfig | None = Field(
default=None,
description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
)
@classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
@ -29,4 +34,9 @@ class MilvusVectorIOConfig(BaseModel):
__distro_dir__=__distro_dir__,
db_name="milvus_registry.db",
),
# Optional: Configure default embedding model for this provider
# "embedding": {
# "model": "${env.MILVUS_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
# "dimensions": 384
# },
}