llama-stack-mirror/llama_stack/distributions/nvidia/run-with-safety.yaml
Ashwin Bharambe 42414a1a1b
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 21s
Test Llama Stack Build / build-single-provider (push) Failing after 25s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 27s
Unit Tests / unit-tests (3.12) (push) Failing after 22s
API Conformance Tests / check-schema-compatibility (push) Successful in 33s
UI Tests / ui-tests (22) (push) Successful in 39s
Pre-commit / pre-commit (push) Successful in 1m12s
fix(logging): disable console telemetry sink by default (#3623)
The current span processing dumps so much junk on the console that it
makes actual understanding of what is going on in the server impossible.
I am killing the console sink as a default. If you want, you are always
free to change your run.yaml to add it.

Before: 
<img width="1877" height="1107" alt="image"
src="https://github.com/user-attachments/assets/3a7ad261-e2ba-4d40-9820-fcc282c8df37"
/>

After:
<img width="1919" height="470" alt="image"
src="https://github.com/user-attachments/assets/bc7cf763-fba9-4e95-a4b5-f65f6d1c5332"
/>
2025-09-30 14:58:05 -07:00

126 lines
3.8 KiB
YAML

version: 2
image_name: nvidia
apis:
- agents
- datasetio
- eval
- files
- inference
- post_training
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: nvidia
provider_type: remote::nvidia
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: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/faiss_store.db
safety:
- provider_id: nvidia
provider_type: remote::nvidia
config:
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
sinks: ${env.TELEMETRY_SINKS:=sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/trace_store.db
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
eval:
- provider_id: nvidia
provider_type: remote::nvidia
config:
evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
post_training:
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
datasetio:
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/localfs_datasetio.db
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
scoring:
- provider_id: basic
provider_type: inline::basic
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: nvidia
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_id: nvidia
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL}
provider_id: nvidia
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321