mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-28 08:51:59 +00:00
107 lines
2.7 KiB
YAML
107 lines
2.7 KiB
YAML
version: '2'
|
|
image_name: watsonx
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: watsonx
|
|
provider_type: remote::watsonx
|
|
config:
|
|
url: ${env.WATSONX_BASE_URL:https://us-south.ml.cloud.ibm.com}
|
|
api_key: ${env.WATSONX_API_KEY:}
|
|
project_id: ${env.WATSONX_PROJECT_ID:}
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config: {}
|
|
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/llamastack-watsonx}/agents_store.db
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llamastack-watsonx}/faiss_store.db
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config: {}
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config: {}
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: {}
|
|
post_training:
|
|
- provider_id: torchtune
|
|
provider_type: inline::torchtune
|
|
config: {}
|
|
tool_runtime:
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/llamastack-watsonx/trace_store.db}
|
|
metadata_store: null
|
|
models:
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-3-70b-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-3-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-2-13b-chat
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-2-13b-chat
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-1-70b-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-1-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-1-8b-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-1-8b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-2-11b-vision-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-11b-vision-instruct
|
|
model_type: llm
|
|
shields: []
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|