phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-24 05:28:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: standardize InferenceRouter model handling

Browse source 
* introduces ModelTypeError custom exception class
* introduces _get_model private method in InferenceRouter class
* standardizes inconsistent variable name usage for models in InferenceRouter class
* removes unneeded model type check in ollama provider

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
This commit is contained in:
Nathan Weinberg 2025-07-30 13:31:46 -04:00 • committed by Nathan Weinberg
parent 803114180b
commit ff8942bc71
4 changed files with 28 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/core/routing_tables/vector_dbs.py
View file

@ -8,7 +8,7 @@ from typing import Any
from pydantic import TypeAdapter
from llama_stack.apis.common.errors import ModelNotFoundError, VectorStoreNotFoundError
from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError, VectorStoreNotFoundError
from llama_stack.apis.models import ModelType
from llama_stack.apis.resource import ResourceType
from llama_stack.apis.vector_dbs import ListVectorDBsResponse, VectorDB, VectorDBs
@ -66,7 +66,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
if model is None:
raise ModelNotFoundError(embedding_model)
if model.model_type != ModelType.embedding:
raise ValueError(f"Model {embedding_model} is not an embedding model")
raise ModelTypeError(embedding_model, model.model_type, ModelType.embedding)
if "embedding_dimension" not in model.metadata:
raise ValueError(f"Model {embedding_model} does not have an embedding dimension")
vector_db_data = {