phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Updating how default embedding model is set in stack

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

# Conflicts:
#	.github/workflows/integration-vector-io-tests.yml
#	llama_stack/distributions/ci-tests/run.yaml
#	llama_stack/distributions/starter-gpu/run.yaml
#	llama_stack/distributions/starter/run.yaml
#	llama_stack/distributions/template.py
#	llama_stack/providers/utils/memory/openai_vector_store_mixin.py
This commit is contained in:
Francisco Javier Arceo 2025-10-15 17:15:43 -04:00
parent cd152f4240
commit 24a1430c8b
32 changed files with 276 additions and 265 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distributions/ci-tests/run.yaml
View file

@ -239,3 +239,5 @@ server:
port: 8321
telemetry:
enabled: true
vector_stores:
default_embedding_model_id: sentence-transformers/nomic-ai/nomic-embed-text-v1.5

2
llama_stack/distributions/starter-gpu/run.yaml
View file

@ -240,5 +240,7 @@ tool_groups:
provider_id: rag-runtime
server:
port: 8321
vector_stores:
default_embedding_model_id: sentence-transformers/nomic-ai/nomic-embed-text-v1.5
telemetry:
enabled: true

2
llama_stack/distributions/starter/run.yaml
View file

@ -239,3 +239,5 @@ server:
port: 8321
telemetry:
enabled: true
vector_stores:
default_embedding_model_id: sentence-transformers/nomic-ai/nomic-embed-text-v1.5

4
llama_stack/distributions/starter/starter.py
View file

@ -13,6 +13,7 @@ from llama_stack.core.datatypes import (
ProviderSpec,
ShieldInput,
ToolGroupInput,
VectorStoresConfig,
)
from llama_stack.core.utils.dynamic import instantiate_class_type
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
@ -227,6 +228,9 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
default_models=[],
default_tool_groups=default_tool_groups,
default_shields=default_shields,
vector_stores_config=VectorStoresConfig(
default_embedding_model_id="sentence-transformers/nomic-ai/nomic-embed-text-v1.5"
),
),
},
run_config_env_vars={

9
llama_stack/distributions/template.py
View file

@ -27,6 +27,7 @@ from llama_stack.core.datatypes import (
ShieldInput,
TelemetryConfig,
ToolGroupInput,
VectorStoresConfig,
)
from llama_stack.core.distribution import get_provider_registry
from llama_stack.core.utils.dynamic import instantiate_class_type
@ -183,6 +184,7 @@ class RunConfigSettings(BaseModel):
metadata_store: dict | None = None
inference_store: dict | None = None
conversations_store: dict | None = None
vector_stores_config: VectorStoresConfig | None = None
telemetry: TelemetryConfig = Field(default_factory=lambda: TelemetryConfig(enabled=True))
def run_config(
@ -227,7 +229,7 @@ class RunConfigSettings(BaseModel):
apis = sorted(providers.keys())
# Return a dict that matches StackRunConfig structure
return {
config = {
"version": LLAMA_STACK_RUN_CONFIG_VERSION,
"image_name": name,
"container_image": container_image,
@ -261,6 +263,11 @@ class RunConfigSettings(BaseModel):
"telemetry": self.telemetry.model_dump(exclude_none=True) if self.telemetry else None,
}
if self.vector_stores_config:
config["vector_stores"] = self.vector_stores_config.model_dump(exclude_none=True)
return config
class DistributionTemplate(BaseModel):
"""