phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 10:10:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-mcp-authentication-param

Browse source
This commit is contained in:
Omar Abdelwahab 2025-11-13 13:49:06 -08:00 • committed by GitHub
commit 949756ebb8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 46 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/llama_stack/core/routers/vector_io.py
View file

@ -14,7 +14,9 @@ from llama_stack_api import (
HealthResponse,
HealthStatus,
InterleavedContent,
ModelNotFoundError,
ModelType,
ModelTypeError,
OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
OpenAICreateVectorStoreRequestWithExtraBody,
QueryChunksResponse,
@ -124,6 +126,14 @@ class VectorIORouter(VectorIO):
if embedding_model is not None and embedding_dimension is None:
embedding_dimension = await self._get_embedding_model_dimension(embedding_model)
# Validate that embedding model exists and is of the correct type
if embedding_model is not None:
model = await self.routing_table.get_object_by_identifier("model", embedding_model)
if model is None:
raise ModelNotFoundError(embedding_model)
if model.model_type != ModelType.embedding:
raise ModelTypeError(embedding_model, model.model_type, ModelType.embedding)
# Auto-select provider if not specified
if provider_id is None:
num_providers = len(self.routing_table.impls_by_provider_id)