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

Make embedding generation go through inference (#606)

Browse source 
This PR does the following:
1) adds the ability to generate embeddings in all supported inference
providers.
2) Moves all the memory providers to use the inference API and improved
the memory tests to setup the inference stack correctly and use the
embedding models

This is a merge from #589 and #598
This commit is contained in:
Dinesh Yeduguru 2024-12-12 11:47:50 -08:00 • committed by GitHub
parent a14785af46
commit 96e158eaac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
37 changed files with 677 additions and 156 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,