phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-23 00:27:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(k8s): update run configs to v2 storage and registered_resources structure
Some checks failed
Python Package Build Test / build (3.13) (push) Failing after 1s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Details
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Details
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Details
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Details
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Details
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Details
Python Package Build Test / build (3.12) (push) Failing after 3s
Details
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Details
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Details
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 4s
Details
Test Llama Stack Build / build (push) Failing after 3s
Details
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Details
Test External API and Providers / test-external (venv) (push) Failing after 4s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Details
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
Details
UI Tests / ui-tests (22) (push) Successful in 42s
Details
Pre-commit / pre-commit (push) Successful in 1m30s
Details

Browse source 
Migrates k8s run configs to match the updated run configs

- Replace storage.references with storage.stores
- Wrap resources under registered_resources section
- Update provider configs to use persistence with namespace/backend
- Add telemetry and vector_stores top-level sections
- Simplify agent/files metadata store configuration
This commit is contained in:
Ashwin Bharambe 2025-10-22 15:33:07 -07:00
parent 0e57233a0a
commit 658fb2c777
2 changed files with 107 additions and 99 deletions
Download patch file Download diff file Expand all files Collapse all files

100
benchmarking/k8s-benchmark/stack_run_config.yaml
View file

@ -27,28 +27,24 @@ providers:
config:
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
table_name: files_metadata
backend: sql_default
vector_io:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
kvstore:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
persistence:
namespace: vector_io::chroma_remote
backend: kv_default
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
table_name: files_metadata
backend: sql_default
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -58,20 +54,15 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
responses_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
persistence:
agent_state:
namespace: agents
backend: kv_default
responses:
table_name: responses
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -112,32 +103,45 @@ storage:
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
references:
stores:
metadata:
backend: kv_default
namespace: registry
backend: kv_default
inference:
backend: sql_default
table_name: inference_store
models:
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
registered_resources:
models:
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8323
telemetry:
enabled: true
vector_stores:
default_provider_id: chromadb
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5

106
docs/docs/distributions/k8s/stack_run_config.yaml
View file

@ -32,21 +32,17 @@ providers:
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
kvstore:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
persistence:
namespace: vector_io::chroma_remote
backend: kv_default
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
table_name: files_metadata
backend: sql_default
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -56,20 +52,15 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
responses_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
persistence:
agent_state:
namespace: agents
backend: kv_default
responses:
table_name: responses
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -110,40 +101,53 @@ storage:
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
references:
stores:
metadata:
backend: kv_default
namespace: registry
backend: kv_default
inference:
backend: sql_default
table_name: inference_store
models:
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
provider_id: vllm-safety
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
registered_resources:
models:
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
provider_id: vllm-safety
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321
auth:
provider_config:
type: github_token
telemetry:
enabled: true
vector_stores:
default_provider_id: chromadb
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5