phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-22 22:42:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into fix-2729-vector-io-embedding-config

Browse source
This commit is contained in:
Sumanth Kamenani 2025-07-17 10:39:49 -04:00 • committed by GitHub
commit 1c7405384d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/templates/starter/run.yaml
View file

@ -262,6 +262,11 @@ inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/inference_store.db
models:
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ${env.ENABLE_SENTENCE_TRANSFORMERS:=sentence-transformers}
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/llama3.1-8b
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
@ -1168,11 +1173,6 @@ models:
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ${env.ENABLE_SENTENCE_TRANSFORMERS:=sentence-transformers}
model_type: embedding
shields:
- shield_id: ${env.SAFETY_MODEL:=__disabled__}
provider_shield_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.SAFETY_MODEL:=__disabled__}

2
llama_stack/templates/starter/starter.py
View file

@ -323,7 +323,7 @@ def get_distribution_template() -> DistributionTemplate:
"files": [files_provider],
"post_training": [post_training_provider],
},
default_models=default_models + [embedding_model],
default_models=[embedding_model] + default_models,
default_tool_groups=default_tool_groups,
# TODO: add a way to enable/disable shields on the fly
default_shields=shields,