phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-13 05:17:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix ollama.py bug

Browse source
This commit is contained in:
Kai Wu 2025-02-25 15:08:48 -08:00
parent 733b9c07b5
commit 32e89191c2
2 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -93,7 +93,7 @@ def get_distribution_template() -> DistributionTemplate:
"inference": [inference_provider], "inference": [inference_provider],
"vector_io": [vector_io_provider_sqlite], "vector_io": [vector_io_provider_sqlite],
}, },
default_models=[inference_model], default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups, default_tool_groups=default_tool_groups,
), ),
"run-with-safety.yaml": RunConfigSettings( "run-with-safety.yaml": RunConfigSettings(

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

@ -87,6 +87,12 @@ models:
model_id: ${env.INFERENCE_MODEL} model_id: ${env.INFERENCE_MODEL}
provider_id: ollama provider_id: ollama
model_type: llm model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ollama
provider_model_id: all-minilm:latest
model_type: embedding
shields: [] shields: []
vector_dbs: [] vector_dbs: []
datasets: [] datasets: []