phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add info to upgrade run.yaml when the default embedding model is not found

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-13 12:47:07 -08:00
parent ee5066806e
commit d73575dd9d
1 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/distribution/routers/routing_tables.py
View file

@ -308,7 +308,14 @@ class MemoryBanksRoutingTable(CommonRoutingTableImpl, MemoryBanks):
)
model = await self.get_object_by_identifier("model", params.embedding_model)
if model is None:
raise ValueError(f"Model {params.embedding_model} not found")
if params.embedding_model == "all-MiniLM-L6-v2":
raise ValueError(
"Embeddings are now served via Inference providers. "
"Please upgrade your run.yaml to include inline::sentence-transformer as an additional inference provider. "
"See https://github.com/meta-llama/llama-stack/blob/main/llama_stack/templates/together/run.yaml for an example."
)
else:
raise ValueError(f"Model {params.embedding_model} not found")
if model.model_type != ModelType.embedding:
raise ValueError(
f"Model {params.embedding_model} is not an embedding model"