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 model type to APIs (#588)

Browse source 
# What does this PR do?

This PR adds a new model type field to support embedding models to be
registered. Summary of changes:
1) Each registered model by default is an llm model. 
2) User can specify an embedding model type, while registering.If
specified, the model bypass the llama model checks since embedding
models can by of any type and based on llama.
3) User needs to include the required embedding dimension in metadata.
This will be used by embedding generation to generate the requried size
of embeddings.


## Test Plan

This PR will go together will need to be merged with two follow up PRs
that will include test plans.
This commit is contained in:
Dinesh Yeduguru 2024-12-11 10:16:53 -08:00 • committed by GitHub
parent 7e1d628864
commit 8e33db6015
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 77 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

24
llama_stack/distribution/routers/routers.py
View file

@ -88,9 +88,10 @@ class InferenceRouter(Inference):
provider_model_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
model_type: Optional[ModelType] = None,
) -> None:
await self.routing_table.register_model(
model_id, provider_model_id, provider_id, metadata
model_id, provider_model_id, provider_id, metadata, model_type
)
async def chat_completion(
@ -105,6 +106,13 @@ class InferenceRouter(Inference):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
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:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)
params = dict(
model_id=model_id,
messages=messages,
@ -131,6 +139,13 @@ class InferenceRouter(Inference):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
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:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)
provider = self.routing_table.get_provider_impl(model_id)
params = dict(
model_id=model_id,
@ -150,6 +165,13 @@ class InferenceRouter(Inference):
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
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.llm:
raise ValueError(
f"Model '{model_id}' is an LLM model and does not support embeddings"
)
return await self.routing_table.get_provider_impl(model_id).embeddings(
model_id=model_id,
contents=contents,