mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
466ef6f490
- 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
105 lines
3.1 KiB
YAML
105 lines
3.1 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}
|
|
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:=console,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: 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: []
|
|
shields: []
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|