phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 19:29:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add embedding model by default

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-12 14:46:51 -08:00
parent 2a9b13dd52
commit 2f88006bd0
43 changed files with 446 additions and 85 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(