phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add OLLAMA_EMBEDDING_MODEL to starter distro

Browse source 
This allows a user to specify the Ollama Embedding Model to use, if any.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-06-25 09:16:01 -04:00
parent 497c97487f
commit 9239b338d5
2 changed files with 21 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/templates/starter/run.yaml
View file

@ -542,6 +542,12 @@ models:
provider_id: ollama
provider_model_id: ${env.OLLAMA_INFERENCE_MODEL:__disabled__}
model_type: llm
- metadata:
embedding_dimension: ${env.OLLAMA_EMBEDDING_DIMENSION:384}
model_id: ollama/${env.OLLAMA_EMBEDDING_MODEL:__disabled__}
provider_id: ollama
provider_model_id: ${env.OLLAMA_EMBEDDING_MODEL:__disabled__}
model_type: embedding
- metadata: {}
model_id: anthropic/claude-3-5-sonnet-latest
provider_id: anthropic

15
llama_stack/templates/starter/starter.py
View file

@ -88,6 +88,13 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
provider_model_id="${env.OLLAMA_INFERENCE_MODEL:__disabled__}",
model_type=ModelType.llm,
),
ProviderModelEntry(
provider_model_id="${env.OLLAMA_EMBEDDING_MODEL:__disabled__}",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": "${env.OLLAMA_EMBEDDING_DIMENSION:384}",
},
),
],
OllamaImplConfig.sample_run_config(
url="${env.OLLAMA_URL:http://localhost:11434}", raise_on_connect_error=False
@ -286,5 +293,13 @@ def get_distribution_template() -> DistributionTemplate:
"",
"Optional Ollama Inference Model to register on startup",
),
"OLLAMA_EMBEDDING_MODEL": (
"",
"Optional Ollama Embedding Model to register on startup",
),
"OLLAMA_EMBEDDING_DIMENSION": (
"384",
"Ollama Embedding Dimension",
),
},
)