phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)

Browse source 
# What does this PR do?

- remove auto-download of ollama embedding models
- add embedding model metadata to dynamic listing w/ unit test
- add support and tests for allowed_models
- removed inference provider models.py files where dynamic listing is
enabled
- store embedding metadata in embedding_model_metadata field on
inference providers
- make model_entries optional on ModelRegistryHelper and
LiteLLMOpenAIMixin
- make OpenAIMixin a ModelRegistryHelper
- skip base64 embedding test for remote::ollama, always returns floats
- only use OpenAI client for ollama model listing
- remove unused build_model_entry function
- remove unused get_huggingface_repo function


## Test Plan

ci w/ new tests
This commit is contained in:
Matthew Farrellee 2025-09-25 17:17:00 -04:00 • committed by GitHub
parent a50b63906c
commit b67aef2fc4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 368 additions and 1015 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/distributions/nvidia/nvidia.py
View file

@ -7,12 +7,11 @@
from pathlib import Path
from llama_stack.core.datatypes import BuildProvider, ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings, get_model_registry
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
@ -68,9 +67,6 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
provider_id="nvidia",
)
available_models = {
"nvidia": MODEL_ENTRIES,
}
default_tool_groups = [
ToolGroupInput(
toolgroup_id="builtin::rag",
@ -78,7 +74,6 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
),
]
default_models, _ = get_model_registry(available_models)
return DistributionTemplate(
name=name,
distro_type="self_hosted",
@ -86,7 +81,6 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
container_image=None,
template_path=Path(__file__).parent / "doc_template.md",
providers=providers,
available_models_by_provider=available_models,
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
@ -95,7 +89,6 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
"eval": [eval_provider],
"files": [files_provider],
},
default_models=default_models,
default_tool_groups=default_tool_groups,
),
"run-with-safety.yaml": RunConfigSettings(

85
llama_stack/distributions/nvidia/run.yaml
View file

@ -92,90 +92,7 @@ metadata_store:
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: meta/llama3-8b-instruct
provider_id: nvidia
provider_model_id: meta/llama3-8b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama3-70b-instruct
provider_id: nvidia
provider_model_id: meta/llama3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-8b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.1-8b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-70b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.1-70b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-405b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.1-405b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-1b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-3b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.2-3b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-11b-vision-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-90b-vision-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.3-70b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata: {}
model_id: nvidia/vila
provider_id: nvidia
provider_model_id: nvidia/vila
model_type: llm
- metadata:
embedding_dimension: 2048
context_length: 8192
model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
provider_id: nvidia
provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: nvidia/nv-embedqa-e5-v5
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-e5-v5
model_type: embedding
- metadata:
embedding_dimension: 4096
context_length: 512
model_id: nvidia/nv-embedqa-mistral-7b-v2
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: snowflake/arctic-embed-l
provider_id: nvidia
provider_model_id: snowflake/arctic-embed-l
model_type: embedding
models: []
shields: []
vector_dbs: []
datasets: []