phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 13:39:48 +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

4
llama_stack/distribution/routers/routers.py
View file

@ -109,7 +109,7 @@ class InferenceRouter(Inference):
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
if model.model_type == ModelType.embedding_model:
if model.model_type == ModelType.embedding:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)
@ -142,7 +142,7 @@ class InferenceRouter(Inference):
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
if model.model_type == ModelType.embedding_model:
if model.model_type == ModelType.embedding:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)