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

fix: ensure ollama embedding model is registered properly in the template

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-27 22:49:06 -08:00
parent 999195fe5b
commit 4c8a0fa8dc
3 changed files with 8 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -318,14 +318,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
)
model = await self.get_object_by_identifier("model", embedding_model)
if model is None:
if 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 {embedding_model} not found")
raise ValueError(f"Model {embedding_model} not found")
if model.model_type != ModelType.embedding:
raise ValueError(f"Model {embedding_model} is not an embedding model")
if "embedding_dimension" not in model.metadata: