mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
81e44b06ff
Fixes issues in the storage system by guaranteeing immediate durability for responses and ensuring background writers stay alive. Three related fixes: * Responses to the OpenAI-compatible API now write directly to Postgres/SQLite inside the request instead of detouring through an async queue that might never drain; this restores the expected read-after-write behavior and removes the "response not found" races reported by users. * The access-control shim was stamping owner_principal/access_attributes as SQL NULL, which Postgres interprets as non-public rows; fixing it to use the empty-string/JSON-null pattern means conversations and responses stored without an authenticated user stay queryable (matching SQLite). * The inference-store queue remains for batching, but its worker tasks now start lazily on the live event loop so server startup doesn't cancel them—writes keep flowing even when the stack is launched via llama stack run. Closes #4115 Added a matrix entry to test our "base" suite against Postgres as the store.
140 lines
3.7 KiB
YAML
140 lines
3.7 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:
|
|
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:
|
|
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: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
namespace: datasetio::localfs
|
|
backend: kv_default
|
|
- 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:
|
|
- 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
|
|
telemetry:
|
|
enabled: true
|