phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki 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

16
llama_stack/distribution/routers/routing_tables.py
View file

@ -225,10 +225,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
metadata = {}
if model_type is None:
model_type = ModelType.llm
if (
"embedding_dimension" not in metadata
and model_type == ModelType.embedding_model
):
if "embedding_dimension" not in metadata and model_type == ModelType.embedding:
raise ValueError(
"Embedding model must have an embedding dimension in its metadata"
)
@ -311,8 +308,15 @@ 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 model.model_type != ModelType.embedding_model:
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"
)