llama-stack/llama_stack/templates/kvant/run.yaml
2025-06-01 12:13:57 +02:00

153 lines
4.2 KiB
YAML

version: '2'
image_name: kvant
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: kvant
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:https://maas.kvant.cloud/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:400000}
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: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/faiss_store.db
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: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/trace_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/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:}
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: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
- 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: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/inference_store.db
models:
- metadata: {}
model_id: Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: kvant
provider_model_id: inference-llama4-maverick
model_type: llm
- metadata:
embedding_dimension: 1024
context_length: 8192
model_id: inference-bge-m3
provider_id: kvant
model_type: embedding
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
vector_dbs: []
# - vector_db_id: test-bge
# embedding_model: inference-bge-m3
# embedding_dimension: 1024
# provider_id: faiss
# - vector_db_id: test-MiniLM-L6-v2
# embedding_model: all-MiniLM-L6-v2
# embedding_dimension: 384
# provider_id: faiss
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321