mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
7a9c32f737
Completes #3732 by removing runtime URL transformations and requiring users to provide full URLs in configuration. All providers now use 'base_url' consistently and respect the exact URL provided without appending paths like /v1 or /openai/v1 at runtime. Add unit test to enforce URL standardization across remote inference providers (verifies all use 'base_url' field with HttpUrl | None type) BREAKING CHANGE: Users must update configs to include full URL paths (e.g., http://localhost:11434/v1 instead of http://localhost:11434). Signed-off-by: Charlie Doern <cdoern@redhat.com>
118 lines
3.1 KiB
YAML
118 lines
3.1 KiB
YAML
version: 2
|
|
image_name: nvidia
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- files
|
|
- inference
|
|
- post_training
|
|
- safety
|
|
- scoring
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
|
|
api_key: ${env.NVIDIA_API_KEY:=}
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
persistence:
|
|
namespace: vector_io::faiss
|
|
backend: kv_default
|
|
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:
|
|
agent_state:
|
|
namespace: agents
|
|
backend: kv_default
|
|
responses:
|
|
table_name: responses
|
|
backend: sql_default
|
|
max_write_queue_size: 10000
|
|
num_writers: 4
|
|
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:
|
|
table_name: files_metadata
|
|
backend: sql_default
|
|
storage:
|
|
backends:
|
|
kv_default:
|
|
type: kv_sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
|
|
sql_default:
|
|
type: sql_sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
|
|
stores:
|
|
metadata:
|
|
namespace: registry
|
|
backend: kv_default
|
|
inference:
|
|
table_name: inference_store
|
|
backend: sql_default
|
|
max_write_queue_size: 10000
|
|
num_writers: 4
|
|
conversations:
|
|
table_name: openai_conversations
|
|
backend: sql_default
|
|
prompts:
|
|
namespace: prompts
|
|
backend: kv_default
|
|
registered_resources:
|
|
models: []
|
|
shields: []
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|
|
telemetry:
|
|
enabled: true
|