mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
6bb174bb05
# What does this PR do? Revert #2060 and fix PLE2515. --------- Signed-off-by: Sébastien Han <seb@redhat.com>
219 lines
6.3 KiB
YAML
219 lines
6.3 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:}
|
|
- 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/watsonx}/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/watsonx}/agents_store.db
|
|
responses_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/responses_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/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/watsonx}/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/watsonx}/huggingface_datasetio.db
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/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: 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/watsonx}/registry.db
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/inference_store.db
|
|
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-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-2-13b
|
|
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-3.1-70B-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-3.1-8B-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
|
|
- 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
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-2-1b-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-1b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-1B-Instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-1b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-2-3b-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-3b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-3B-Instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-3b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-3-2-90b-vision-instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/llama-guard-3-11b-vision
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-guard-3-11b-vision
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-Guard-3-11B-Vision
|
|
provider_id: watsonx
|
|
provider_model_id: meta-llama/llama-guard-3-11b-vision
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
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
|