mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-21 20:08:42 +00:00
RHAIENG-565: purge the midstream repo content to only host the build artifacts, so only the redhat-distribution should remain
This commit is contained in:
parent
5d65c017b0
commit
9803329350
8 changed files with 448 additions and 0 deletions
138
redhat-distribution/run.yaml
Normal file
138
redhat-distribution/run.yaml
Normal file
|
|
@ -0,0 +1,138 @@
|
|||
version: 2
|
||||
image_name: rh
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- 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: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
config: {}
|
||||
vector_io:
|
||||
- provider_id: milvus
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/milvus.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/milvus_registry.db
|
||||
safety:
|
||||
- provider_id: trustyai_fms
|
||||
provider_type: remote::trustyai_fms
|
||||
config:
|
||||
orchestrator_url: ${env.FMS_ORCHESTRATOR_URL:=}
|
||||
ssl_cert_path: ${env.FMS_SSL_CERT_PATH:=}
|
||||
shields: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/responses_store.db
|
||||
eval:
|
||||
- provider_id: trustyai_lmeval
|
||||
provider_type: remote::trustyai_lmeval
|
||||
config:
|
||||
use_k8s: True
|
||||
base_url: ${env.VLLM_URL:=http://localhost:8000/v1}
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
config: {}
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
config: {}
|
||||
- provider_id: braintrust
|
||||
provider_type: inline::braintrust
|
||||
config:
|
||||
openai_api_key: ${env.OPENAI_API_KEY:=}
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: /opt/app-root/src/.llama/distributions/rh/trace_store.db
|
||||
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
||||
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: sqlite
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: /opt/app-root/src/.llama/distributions/rh/inference_store.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: vllm-inference
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 768
|
||||
model_id: granite-embedding-125m
|
||||
provider_id: sentence-transformers
|
||||
provider_model_id: ibm-granite/granite-embedding-125m-english
|
||||
model_type: embedding
|
||||
shields: []
|
||||
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
|
||||
external_providers_dir: /opt/app-root/src/.llama/providers.d
|
||||
Loading…
Add table
Add a link
Reference in a new issue