phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

add embedding model by default to distribution templates (#617)

Browse source 
# What does this PR do?
Adds the sentence transformer provider and the `all-MiniLM-L6-v2`
embedding model to the default models to register in the run.yaml for
all providers.

## Test Plan
llama stack build --template together --image-type conda
llama stack run
~/.llama/distributions/llamastack-together/together-run.yaml
This commit is contained in:
Dinesh Yeduguru 2024-12-13 12:48:00 -08:00 • committed by GitHub
parent e893b22868
commit 516e1a3e59
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
41 changed files with 473 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -337,7 +337,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
async def register_model(self, model: Model) -> Model:
# ollama does not have embedding models running. Check if the model is in list of available models.
if model.model_type == ModelType.embedding_model:
if model.model_type == ModelType.embedding:
response = await self.client.list()
available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models:

2
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -207,7 +207,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
model = await self.model_store.get_model(model_id)
kwargs = {}
assert model.model_type == ModelType.embedding_model
assert model.model_type == ModelType.embedding
assert model.metadata.get("embedding_dimensions")
kwargs["dimensions"] = model.metadata.get("embedding_dimensions")
assert all(