phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 03:59:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Clean up instructions and implementation; reorganize notebooks

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-18 16:27:19 -04:00
parent 0d9d333a4e
commit 4131e8146f
29 changed files with 2756 additions and 89 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/templates/nvidia/nvidia.py
View file

@ -65,7 +65,7 @@ def get_distribution_template() -> DistributionTemplate:
default_models = get_model_registry(available_models)
return DistributionTemplate(
name="nvidia",
distro_type="remote_hosted",
distro_type="self_hosted",
description="Use NVIDIA NIM for running LLM inference, evaluation and safety",
container_image=None,
template_path=Path(__file__).parent / "doc_template.md",
@ -103,6 +103,10 @@ def get_distribution_template() -> DistributionTemplate:
"llama-stack-user",
"NVIDIA User ID",
),
"NVIDIA_APPEND_API_VERSION": (
"True",
"Whether to append the API version to the base_url",
),
"NVIDIA_DATASET_NAMESPACE": (
"default",
"NVIDIA Dataset Namespace",
@ -127,6 +131,10 @@ def get_distribution_template() -> DistributionTemplate:
"http://0.0.0.0:7331",
"URL for the NeMo Guardrails Service",
),
"NVIDIA_GUARDRAILS_CONFIG_ID": (
"self-check",
"NVIDIA Guardrail Configuration ID",
),
"NVIDIA_EVALUATOR_URL": (
"http://0.0.0.0:7331",
"URL for the NeMo Evaluator Service",

5
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -18,11 +18,12 @@ providers:
config:
url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
api_key: ${env.NVIDIA_API_KEY:}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:True}
- provider_id: nvidia
provider_type: remote::nvidia
config:
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
config_id: self-check
config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:self-check}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
@ -36,7 +37,7 @@ providers:
provider_type: remote::nvidia
config:
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
config_id: self-check
config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:self-check}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference

3
llama_stack/templates/nvidia/run.yaml
View file

@ -18,6 +18,7 @@ providers:
config:
url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
api_key: ${env.NVIDIA_API_KEY:}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:True}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
@ -31,7 +32,7 @@ providers:
provider_type: remote::nvidia
config:
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
config_id: self-check
config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:self-check}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference