mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
81ad240faa
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
56 lines
4.6 KiB
YAML
56 lines
4.6 KiB
YAML
apiVersion: v1
|
|
data:
|
|
stack_run_config.yaml: "version: '2'\nimage_name: kubernetes-demo\napis:\n- agents\n-
|
|
inference\n- files\n- safety\n- telemetry\n- tool_runtime\n- vector_io\nproviders:\n
|
|
\ inference:\n - provider_id: vllm-inference\n provider_type: remote::vllm\n
|
|
\ config:\n url: ${env.VLLM_URL:=http://localhost:8000/v1}\n max_tokens:
|
|
${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n tls_verify:
|
|
${env.VLLM_TLS_VERIFY:=true}\n - provider_id: vllm-safety\n provider_type:
|
|
remote::vllm\n config:\n url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}\n
|
|
\ max_tokens: ${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n
|
|
\ tls_verify: ${env.VLLM_TLS_VERIFY:=true}\n - provider_id: sentence-transformers\n
|
|
\ provider_type: inline::sentence-transformers\n config: {}\n vector_io:\n
|
|
\ - provider_id: ${env.ENABLE_CHROMADB:+chromadb}\n provider_type: remote::chromadb\n
|
|
\ config:\n url: ${env.CHROMADB_URL:=}\n kvstore:\n type: postgres\n
|
|
\ host: ${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n
|
|
\ db: ${env.POSTGRES_DB:=llamastack}\n user: ${env.POSTGRES_USER:=llamastack}\n
|
|
\ password: ${env.POSTGRES_PASSWORD:=llamastack}\n files:\n - provider_id:
|
|
meta-reference-files\n provider_type: inline::localfs\n config:\n storage_dir:
|
|
${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}\n metadata_store:\n
|
|
\ type: sqlite\n db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
|
|
\ \n safety:\n - provider_id: llama-guard\n provider_type: inline::llama-guard\n
|
|
\ config:\n excluded_categories: []\n agents:\n - provider_id: meta-reference\n
|
|
\ provider_type: inline::meta-reference\n config:\n persistence_store:\n
|
|
\ type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n port:
|
|
${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
|
|
${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
|
|
\ responses_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
|
|
\ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
|
|
\ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
|
|
\ telemetry:\n - provider_id: meta-reference\n provider_type: inline::meta-reference\n
|
|
\ config:\n service_name: \"${env.OTEL_SERVICE_NAME:=\\u200B}\"\n sinks:
|
|
${env.TELEMETRY_SINKS:=console}\n tool_runtime:\n - provider_id: brave-search\n
|
|
\ provider_type: remote::brave-search\n config:\n api_key: ${env.BRAVE_SEARCH_API_KEY:+}\n
|
|
\ max_results: 3\n - provider_id: tavily-search\n provider_type: remote::tavily-search\n
|
|
\ config:\n api_key: ${env.TAVILY_SEARCH_API_KEY:+}\n max_results:
|
|
3\n - provider_id: rag-runtime\n provider_type: inline::rag-runtime\n config:
|
|
{}\n - provider_id: model-context-protocol\n provider_type: remote::model-context-protocol\n
|
|
\ config: {}\nmetadata_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
|
|
\ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
|
|
${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
|
|
\ table_name: llamastack_kvstore\ninference_store:\n type: postgres\n host:
|
|
${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
|
|
\ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\nmodels:\n-
|
|
metadata:\n embedding_dimension: 384\n model_id: all-MiniLM-L6-v2\n provider_id:
|
|
sentence-transformers\n model_type: embedding\n- metadata: {}\n model_id: ${env.INFERENCE_MODEL}\n
|
|
\ provider_id: vllm-inference\n model_type: llm\n- metadata: {}\n model_id:
|
|
${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\n provider_id: vllm-safety\n
|
|
\ model_type: llm\nshields:\n- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\nvector_dbs:
|
|
[]\ndatasets: []\nscoring_fns: []\nbenchmarks: []\ntool_groups:\n- toolgroup_id:
|
|
builtin::websearch\n provider_id: tavily-search\n- toolgroup_id: builtin::rag\n
|
|
\ provider_id: rag-runtime\nserver:\n port: 8321\n auth:\n provider_config:\n
|
|
\ type: github_token\n"
|
|
kind: ConfigMap
|
|
metadata:
|
|
creationTimestamp: null
|
|
name: llama-stack-config
|