mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-26 15:51:59 +00:00
2f994cfc50
using the new template.py, regenerate all distros and their new provider configs Signed-off-by: Charlie Doern <cdoern@redhat.com>
93 lines
2.6 KiB
YAML
93 lines
2.6 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:=}
|
|
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: ~/.llama/distributions/nvidia/provider_configs/vector_io/faiss.yaml
|
|
safety:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config: ~/.llama/distributions/nvidia/provider_configs/safety/nvidia.yaml
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: ~/.llama/distributions/nvidia/provider_configs/agents/meta-reference.yaml
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: ~/.llama/distributions/nvidia/provider_configs/telemetry/meta-reference.yaml
|
|
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: ~/.llama/distributions/nvidia/provider_configs/post_training/nvidia.yaml
|
|
datasetio:
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config: ~/.llama/distributions/nvidia/provider_configs/datasetio/localfs.yaml
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config: ~/.llama/distributions/nvidia/provider_configs/datasetio/nvidia.yaml
|
|
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
|
|
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
|