phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-24 03:48:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(vector-io): configurable embedding models for all providers (v2)\n\nAdds embedding_model and embedding_dimension fields to all VectorIOConfig classes.\nRouter respects provider defaults with fallback.\nIntroduces embedding_utils helper.\nComprehensive docs & samples.\nResolves #2729

Browse source
This commit is contained in:
skamenan7 2025-07-17 11:51:40 -04:00
parent c8f274347d
commit d55dd3e9a0
24 changed files with 482 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/providers/remote/vector_io/chroma/config.py
View file

@ -6,12 +6,25 @@
from typing import Any
from pydantic import BaseModel
from pydantic import BaseModel, Field
class ChromaVectorIOConfig(BaseModel):
url: str | None
embedding_model: str | None = Field(
default=None,
description="Optional default embedding model for this provider. If not specified, will use system default.",
)
embedding_dimension: int | None = Field(
default=None,
description="Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.",
)
@classmethod
def sample_run_config(cls, url: str = "${env.CHROMADB_URL}", **kwargs: Any) -> dict[str, Any]:
return {"url": url}
return {
"url": url,
# Optional: Configure default embedding model for this provider
# "embedding_model": "all-MiniLM-L6-v2",
# "embedding_dimension": 384, # Only needed for variable-dimension models
}

11
llama_stack/providers/remote/vector_io/milvus/config.py
View file

@ -18,6 +18,14 @@ class MilvusVectorIOConfig(BaseModel):
token: str | None = Field(description="The token of the Milvus server")
consistency_level: str = Field(description="The consistency level of the Milvus server", default="Strong")
kvstore: KVStoreConfig = Field(description="Config for KV store backend")
embedding_model: str | None = Field(
default=None,
description="Optional default embedding model for this provider. If not specified, will use system default.",
)
embedding_dimension: int | None = Field(
default=None,
description="Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.",
)
# This configuration allows additional fields to be passed through to the underlying Milvus client.
# See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general.
@ -32,4 +40,7 @@ class MilvusVectorIOConfig(BaseModel):
__distro_dir__=__distro_dir__,
db_name="milvus_remote_registry.db",
),
# Optional: Configure default embedding model for this provider
# "embedding_model": "all-MiniLM-L6-v2",
# "embedding_dimension": 384, # Only needed for variable-dimension models
}

13
llama_stack/providers/remote/vector_io/pgvector/config.py
View file

@ -23,13 +23,21 @@ class PGVectorVectorIOConfig(BaseModel):
user: str | None = Field(default="postgres")
password: str | None = Field(default="mysecretpassword")
kvstore: KVStoreConfig | None = Field(description="Config for KV store backend (SQLite only for now)", default=None)
embedding_model: str | None = Field(
default=None,
description="Optional default embedding model for this provider. If not specified, will use system default.",
)
embedding_dimension: int | None = Field(
default=None,
description="Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.",
)
@classmethod
def sample_run_config(
cls,
__distro_dir__: str,
host: str = "${env.PGVECTOR_HOST:=localhost}",
port: int = "${env.PGVECTOR_PORT:=5432}",
port: int | str = "${env.PGVECTOR_PORT:=5432}",
db: str = "${env.PGVECTOR_DB}",
user: str = "${env.PGVECTOR_USER}",
password: str = "${env.PGVECTOR_PASSWORD}",
@ -45,4 +53,7 @@ class PGVectorVectorIOConfig(BaseModel):
__distro_dir__=__distro_dir__,
db_name="pgvector_registry.db",
),
# Optional: Configure default embedding model for this provider
# "embedding_model": "all-MiniLM-L6-v2",
# "embedding_dimension": 384, # Only needed for variable-dimension models
}

13
llama_stack/providers/remote/vector_io/qdrant/config.py
View file

@ -6,7 +6,7 @@
from typing import Any
from pydantic import BaseModel
from pydantic import BaseModel, Field
from llama_stack.schema_utils import json_schema_type
@ -23,9 +23,20 @@ class QdrantVectorIOConfig(BaseModel):
prefix: str | None = None
timeout: int | None = None
host: str | None = None
embedding_model: str | None = Field(
default=None,
description="Optional default embedding model for this provider. If not specified, will use system default.",
)
embedding_dimension: int | None = Field(
default=None,
description="Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.",
)
@classmethod
def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
return {
"api_key": "${env.QDRANT_API_KEY}",
# Optional: Configure default embedding model for this provider
# "embedding_model": "all-MiniLM-L6-v2",
# "embedding_dimension": 384, # Only needed for variable-dimension models
}

12
llama_stack/providers/remote/vector_io/weaviate/config.py
View file

@ -21,6 +21,15 @@ class WeaviateRequestProviderData(BaseModel):
class WeaviateVectorIOConfig(BaseModel):
embedding_model: str | None = Field(
default=None,
description="Optional default embedding model for this provider. If not specified, will use system default.",
)
embedding_dimension: int | None = Field(
default=None,
description="Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.",
)
@classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
return {
@ -28,4 +37,7 @@ class WeaviateVectorIOConfig(BaseModel):
__distro_dir__=__distro_dir__,
db_name="weaviate_registry.db",
),
# Optional: Configure default embedding model for this provider
# "embedding_model": "all-MiniLM-L6-v2",
# "embedding_dimension": 384, # Only needed for variable-dimension models
}