mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-24 05:14:30 +00:00
cc77f79f55
# What does this PR do? This PR adds support for NVIDIA's NeMo Evaluator API to the Llama Stack eval module. The integration enables users to evaluate models via the Llama Stack interface. ## Test Plan [Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.*] 1. Added unit tests and successfully ran from root of project: `./scripts/unit-tests.sh tests/unit/providers/nvidia/test_eval.py` ``` tests/unit/providers/nvidia/test_eval.py::TestNVIDIAEvalImpl::test_job_cancel PASSED tests/unit/providers/nvidia/test_eval.py::TestNVIDIAEvalImpl::test_job_result PASSED tests/unit/providers/nvidia/test_eval.py::TestNVIDIAEvalImpl::test_job_status PASSED tests/unit/providers/nvidia/test_eval.py::TestNVIDIAEvalImpl::test_register_benchmark PASSED tests/unit/providers/nvidia/test_eval.py::TestNVIDIAEvalImpl::test_run_eval PASSED ``` 2. Verified I could build the Llama Stack image: `LLAMA_STACK_DIR=$(pwd) llama stack build --template nvidia --image-type venv` Documentation added to `llama_stack/providers/remote/eval/nvidia/README.md` --------- Co-authored-by: Jash Gulabrai <jgulabrai@nvidia.com>
107 lines
2.8 KiB
YAML
107 lines
2.8 KiB
YAML
version: '2'
|
|
image_name: nvidia
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- 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:}
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
|
|
config_id: self-check
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
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: self-check
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
|
|
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
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
tool_runtime:
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.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
|