fix(k8s): unwedge run.yaml to add files
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Update ReadTheDocs / update-readthedocs (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 6s
UI Tests / ui-tests (22) (push) Successful in 38s
Pre-commit / pre-commit (push) Successful in 1m28s

This commit is contained in:
Ashwin Bharambe 2025-09-09 23:00:50 -07:00
parent dd1f946b3e
commit 81ad240faa
4 changed files with 77 additions and 142 deletions

View file

@ -6,6 +6,7 @@ data:
apis: apis:
- agents - agents
- inference - inference
- files
- safety - safety
- telemetry - telemetry
- tool_runtime - tool_runtime
@ -19,13 +20,6 @@ data:
max_tokens: ${env.VLLM_MAX_TOKENS:=4096} max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake} api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true} tls_verify: ${env.VLLM_TLS_VERIFY:=true}
- provider_id: vllm-safety
provider_type: remote::vllm
config:
url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
- provider_id: sentence-transformers - provider_id: sentence-transformers
provider_type: inline::sentence-transformers provider_type: inline::sentence-transformers
config: {} config: {}
@ -41,6 +35,14 @@ data:
db: ${env.POSTGRES_DB:=llamastack} db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack} user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack} password: ${env.POSTGRES_PASSWORD:=llamastack}
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
safety: safety:
- provider_id: llama-guard - provider_id: llama-guard
provider_type: inline::llama-guard provider_type: inline::llama-guard
@ -111,9 +113,6 @@ data:
- model_id: ${env.INFERENCE_MODEL} - model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference provider_id: vllm-inference
model_type: llm model_type: llm
- model_id: ${env.SAFETY_MODEL}
provider_id: vllm-safety
model_type: llm
shields: shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B} - shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: [] vector_dbs: []

View file

@ -3,6 +3,7 @@ image_name: kubernetes-benchmark-demo
apis: apis:
- agents - agents
- inference - inference
- files
- safety - safety
- telemetry - telemetry
- tool_runtime - tool_runtime
@ -31,6 +32,14 @@ providers:
db: ${env.POSTGRES_DB:=llamastack} db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack} user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack} password: ${env.POSTGRES_PASSWORD:=llamastack}
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
safety: safety:
- provider_id: llama-guard - provider_id: llama-guard
provider_type: inline::llama-guard provider_type: inline::llama-guard

View file

@ -1,137 +1,55 @@
apiVersion: v1 apiVersion: v1
data: data:
stack_run_config.yaml: | stack_run_config.yaml: "version: '2'\nimage_name: kubernetes-demo\napis:\n- agents\n-
version: '2' inference\n- files\n- safety\n- telemetry\n- tool_runtime\n- vector_io\nproviders:\n
image_name: kubernetes-demo \ inference:\n - provider_id: vllm-inference\n provider_type: remote::vllm\n
apis: \ config:\n url: ${env.VLLM_URL:=http://localhost:8000/v1}\n max_tokens:
- agents ${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n tls_verify:
- inference ${env.VLLM_TLS_VERIFY:=true}\n - provider_id: vllm-safety\n provider_type:
- safety remote::vllm\n config:\n url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}\n
- telemetry \ max_tokens: ${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n
- tool_runtime \ tls_verify: ${env.VLLM_TLS_VERIFY:=true}\n - provider_id: sentence-transformers\n
- vector_io \ provider_type: inline::sentence-transformers\n config: {}\n vector_io:\n
providers: \ - provider_id: ${env.ENABLE_CHROMADB:+chromadb}\n provider_type: remote::chromadb\n
inference: \ config:\n url: ${env.CHROMADB_URL:=}\n kvstore:\n type: postgres\n
- provider_id: vllm-inference \ host: ${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n
provider_type: remote::vllm \ db: ${env.POSTGRES_DB:=llamastack}\n user: ${env.POSTGRES_USER:=llamastack}\n
config: \ password: ${env.POSTGRES_PASSWORD:=llamastack}\n files:\n - provider_id:
url: ${env.VLLM_URL:=http://localhost:8000/v1} meta-reference-files\n provider_type: inline::localfs\n config:\n storage_dir:
max_tokens: ${env.VLLM_MAX_TOKENS:=4096} ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}\n metadata_store:\n
api_token: ${env.VLLM_API_TOKEN:=fake} \ type: sqlite\n db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
tls_verify: ${env.VLLM_TLS_VERIFY:=true} \ \n safety:\n - provider_id: llama-guard\n provider_type: inline::llama-guard\n
- provider_id: vllm-safety \ config:\n excluded_categories: []\n agents:\n - provider_id: meta-reference\n
provider_type: remote::vllm \ provider_type: inline::meta-reference\n config:\n persistence_store:\n
config: \ type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n port:
url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1} ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
max_tokens: ${env.VLLM_MAX_TOKENS:=4096} ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
api_token: ${env.VLLM_API_TOKEN:=fake} \ responses_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
tls_verify: ${env.VLLM_TLS_VERIFY:=true} \ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
- provider_id: sentence-transformers \ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
provider_type: inline::sentence-transformers \ telemetry:\n - provider_id: meta-reference\n provider_type: inline::meta-reference\n
config: {} \ config:\n service_name: \"${env.OTEL_SERVICE_NAME:=\\u200B}\"\n sinks:
vector_io: ${env.TELEMETRY_SINKS:=console}\n tool_runtime:\n - provider_id: brave-search\n
- provider_id: ${env.ENABLE_CHROMADB:+chromadb} \ provider_type: remote::brave-search\n config:\n api_key: ${env.BRAVE_SEARCH_API_KEY:+}\n
provider_type: remote::chromadb \ max_results: 3\n - provider_id: tavily-search\n provider_type: remote::tavily-search\n
config: \ config:\n api_key: ${env.TAVILY_SEARCH_API_KEY:+}\n max_results:
url: ${env.CHROMADB_URL:=} 3\n - provider_id: rag-runtime\n provider_type: inline::rag-runtime\n config:
kvstore: {}\n - provider_id: model-context-protocol\n provider_type: remote::model-context-protocol\n
type: postgres \ config: {}\nmetadata_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
host: ${env.POSTGRES_HOST:=localhost} \ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
port: ${env.POSTGRES_PORT:=5432} ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
db: ${env.POSTGRES_DB:=llamastack} \ table_name: llamastack_kvstore\ninference_store:\n type: postgres\n host:
user: ${env.POSTGRES_USER:=llamastack} ${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
password: ${env.POSTGRES_PASSWORD:=llamastack} \ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\nmodels:\n-
safety: metadata:\n embedding_dimension: 384\n model_id: all-MiniLM-L6-v2\n provider_id:
- provider_id: llama-guard sentence-transformers\n model_type: embedding\n- metadata: {}\n model_id: ${env.INFERENCE_MODEL}\n
provider_type: inline::llama-guard \ provider_id: vllm-inference\n model_type: llm\n- metadata: {}\n model_id:
config: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\n provider_id: vllm-safety\n
excluded_categories: [] \ model_type: llm\nshields:\n- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\nvector_dbs:
agents: []\ndatasets: []\nscoring_fns: []\nbenchmarks: []\ntool_groups:\n- toolgroup_id:
- provider_id: meta-reference builtin::websearch\n provider_id: tavily-search\n- toolgroup_id: builtin::rag\n
provider_type: inline::meta-reference \ provider_id: rag-runtime\nserver:\n port: 8321\n auth:\n provider_config:\n
config: \ type: github_token\n"
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: ${env.POSTGRES_PASSWORD:=llamastack}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
sinks: ${env.TELEMETRY_SINKS:=console}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:+}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
metadata_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}
table_name: llamastack_kvstore
inference_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}
models:
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
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
kind: ConfigMap kind: ConfigMap
metadata: metadata:
creationTimestamp: null creationTimestamp: null

View file

@ -3,6 +3,7 @@ image_name: kubernetes-demo
apis: apis:
- agents - agents
- inference - inference
- files
- safety - safety
- telemetry - telemetry
- tool_runtime - tool_runtime
@ -38,6 +39,14 @@ providers:
db: ${env.POSTGRES_DB:=llamastack} db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack} user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack} password: ${env.POSTGRES_PASSWORD:=llamastack}
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
safety: safety:
- provider_id: llama-guard - provider_id: llama-guard
provider_type: inline::llama-guard provider_type: inline::llama-guard