mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
9654dd9da1
This commit significantly improves the environment variable substitution
functionality in Llama Stack configuration files:
* The version field in configuration files has been changed from string
to integer type for better type consistency across build and run
configurations.
* The environment variable substitution system for ${env.FOO:} was fixed
and properly returns an error
* The environment variable substitution system for ${env.FOO+} returns
None instead of an empty strings, it better matches type annotations
in config fields
* The system includes automatic type conversion for boolean, integer,
and float values.
* The error messages have been enhanced to provide clearer guidance when
environment variables are missing, including suggestions for using
default values or conditional syntax.
* Comprehensive documentation has been added to the configuration guide
explaining all supported syntax patterns, best practices, and runtime
override capabilities.
* Multiple provider configurations have been updated to use the new
conditional syntax for optional API keys, making the system more
flexible for different deployment scenarios. The telemetry
configuration has been improved to properly handle optional endpoints
with appropriate validation, ensuring that required endpoints are
specified when their corresponding sinks are enabled.
* There were many instances of ${env.NVIDIA_API_KEY:} that should have
caused the code to fail. However, due to a bug, the distro server was
still being started, and early validation wasn’t triggered. As a
result, failures were likely being handled downstream by the
providers. I’ve maintained similar behavior by using
${env.NVIDIA_API_KEY:+}, though I believe this is incorrect for many
configurations. I’ll leave it to each provider to correct it as
needed.
* Environment variable substitution now uses the same syntax as Bash
parameter expansion.
Signed-off-by: Sébastien Han <seb@redhat.com>
128 lines
4 KiB
YAML
128 lines
4 KiB
YAML
apiVersion: v1
|
|
data:
|
|
stack_run_config.yaml: |
|
|
version: '2'
|
|
image_name: kubernetes-demo
|
|
apis:
|
|
- agents
|
|
- inference
|
|
- safety
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: vllm-inference
|
|
provider_type: remote::vllm
|
|
config:
|
|
url: ${env.VLLM_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: 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_type: inline::sentence-transformers
|
|
config: {}
|
|
vector_io:
|
|
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
|
|
provider_type: remote::chromadb
|
|
config:
|
|
url: ${env.CHROMADB_URL:+}
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config:
|
|
excluded_categories: []
|
|
agents:
|
|
- 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}
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:+}
|
|
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
|
|
kind: ConfigMap
|
|
metadata:
|
|
creationTimestamp: null
|
|
name: llama-stack-config
|