phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 03:12:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Enabling teste for Weaviate and some minor changes

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-07-23 21:20:16 -04:00
parent 266e2afb9c
commit 01d90eb8ab
17 changed files with 216 additions and 103 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/distribution/routers/inference.py
View file

@ -17,6 +17,7 @@ from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.common.errors import ModelNotFoundError
from llama_stack.apis.inference import (
BatchChatCompletionResponse,
BatchCompletionResponse,
@ -188,7 +189,7 @@ class InferenceRouter(Inference):
sampling_params = SamplingParams()
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
raise ModelNotFoundError(model_id)
if model.model_type == ModelType.embedding:
raise ValueError(f"Model '{model_id}' is an embedding model and does not support chat completions")
if tool_config:
@ -317,7 +318,7 @@ class InferenceRouter(Inference):
)
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
raise ModelNotFoundError(model_id)
if model.model_type == ModelType.embedding:
raise ValueError(f"Model '{model_id}' is an embedding model and does not support chat completions")
provider = await self.routing_table.get_provider_impl(model_id)
@ -390,7 +391,7 @@ class InferenceRouter(Inference):
logger.debug(f"InferenceRouter.embeddings: {model_id}")
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
raise ModelNotFoundError(model_id)
if model.model_type == ModelType.llm:
raise ValueError(f"Model '{model_id}' is an LLM model and does not support embeddings")
provider = await self.routing_table.get_provider_impl(model_id)
@ -430,7 +431,7 @@ class InferenceRouter(Inference):
)
model_obj = await self.routing_table.get_model(model)
if model_obj is None:
raise ValueError(f"Model '{model}' not found")
raise ModelNotFoundError(model)
if model_obj.model_type == ModelType.embedding:
raise ValueError(f"Model '{model}' is an embedding model and does not support completions")
@ -491,7 +492,7 @@ class InferenceRouter(Inference):
)
model_obj = await self.routing_table.get_model(model)
if model_obj is None:
raise ValueError(f"Model '{model}' not found")
raise ModelNotFoundError(model)
if model_obj.model_type == ModelType.embedding:
raise ValueError(f"Model '{model}' is an embedding model and does not support chat completions")
@ -562,7 +563,7 @@ class InferenceRouter(Inference):
)
model_obj = await self.routing_table.get_model(model)
if model_obj is None:
raise ValueError(f"Model '{model}' not found")
raise ModelNotFoundError(model)
if model_obj.model_type != ModelType.embedding:
raise ValueError(f"Model '{model}' is not an embedding model")