phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 00:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor component path

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-07-29 21:20:21 -04:00
parent a29b62f820
commit 19d2555424
116 changed files with 7064 additions and 1265 deletions
Download patch file Download diff file Expand all files Collapse all files

19
llama_stack/distribution/library_client.py
View file

@ -39,7 +39,7 @@ from llama_stack.distribution.request_headers import (
request_provider_data_context,
)
from llama_stack.distribution.resolver import ProviderRegistry
from llama_stack.distribution.server.routes import find_matching_route, initialize_route_impls
from llama_stack.distribution.server.routes import RouteImpls, find_matching_route, initialize_route_impls
from llama_stack.distribution.stack import (
construct_stack,
get_stack_run_config_from_template,
@ -236,6 +236,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
self.config = config
self.custom_provider_registry = custom_provider_registry
self.provider_data = provider_data
self.route_impls: RouteImpls | None = None # Initialize to None to prevent AttributeError
async def initialize(self) -> bool:
try:
@ -297,8 +298,8 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
stream=False,
stream_cls=None,
):
if not self.route_impls:
raise ValueError("Client not initialized")
if self.route_impls is None:
raise ValueError("Client not initialized. Please call initialize() first.")
# Create headers with provider data if available
headers = options.headers or {}
@ -353,9 +354,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
cast_to: Any,
options: Any,
):
if self.route_impls is None:
raise ValueError("Client not initialized")
assert self.route_impls is not None # Should be guaranteed by request() method, assertion for mypy
path = options.url
body = options.params or {}
body |= options.json_data or {}
@ -412,9 +411,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
options: Any,
stream_cls: Any,
):
if self.route_impls is None:
raise ValueError("Client not initialized")
assert self.route_impls is not None # Should be guaranteed by request() method, assertion for mypy
path = options.url
body = options.params or {}
body |= options.json_data or {}
@ -474,9 +471,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
if not body:
return {}
if self.route_impls is None:
raise ValueError("Client not initialized")
assert self.route_impls is not None # Should be guaranteed by request() method, assertion for mypy
exclude_params = exclude_params or set()
func, _, _, _ = find_matching_route(method, path, self.route_impls)

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")

3
llama_stack/distribution/routing_tables/common.py
View file

@ -6,6 +6,7 @@
from typing import Any
from llama_stack.apis.common.errors import ModelNotFoundError
from llama_stack.apis.models import Model
from llama_stack.apis.resource import ResourceType
from llama_stack.apis.scoring_functions import ScoringFn
@ -257,7 +258,7 @@ async def lookup_model(routing_table: CommonRoutingTableImpl, model_id: str) ->
models = await routing_table.get_all_with_type("model")
matching_models = [m for m in models if m.provider_resource_id == model_id]
if len(matching_models) == 0:
raise ValueError(f"Model '{model_id}' not found")
raise ModelNotFoundError(model_id)
if len(matching_models) > 1:
raise ValueError(f"Multiple providers found for '{model_id}': {[m.provider_id for m in matching_models]}")

5
llama_stack/distribution/routing_tables/datasets.py
View file

@ -7,6 +7,7 @@
import uuid
from typing import Any
from llama_stack.apis.common.errors import DatasetNotFoundError
from llama_stack.apis.datasets import (
Dataset,
DatasetPurpose,
@ -35,7 +36,7 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
async def get_dataset(self, dataset_id: str) -> Dataset:
dataset = await self.get_object_by_identifier("dataset", dataset_id)
if dataset is None:
raise ValueError(f"Dataset '{dataset_id}' not found")
raise DatasetNotFoundError(dataset_id)
return dataset
async def register_dataset(
@ -87,6 +88,4 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
async def unregister_dataset(self, dataset_id: str) -> None:
dataset = await self.get_dataset(dataset_id)
if dataset is None:
raise ValueError(f"Dataset {dataset_id} not found")
await self.unregister_object(dataset)

3
llama_stack/distribution/routing_tables/models.py
View file

@ -7,6 +7,7 @@
import time
from typing import Any
from llama_stack.apis.common.errors import ModelNotFoundError
from llama_stack.apis.models import ListModelsResponse, Model, Models, ModelType, OpenAIListModelsResponse, OpenAIModel
from llama_stack.distribution.datatypes import (
ModelWithOwner,
@ -111,7 +112,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
async def unregister_model(self, model_id: str) -> None:
existing_model = await self.get_model(model_id)
if existing_model is None:
raise ValueError(f"Model {model_id} not found")
raise ModelNotFoundError(model_id)
await self.unregister_object(existing_model)
async def update_registered_models(

7
llama_stack/distribution/routing_tables/vector_dbs.py
View file

@ -8,6 +8,7 @@ from typing import Any
from pydantic import TypeAdapter
from llama_stack.apis.common.errors import ModelNotFoundError, 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
@ -39,7 +40,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
async def get_vector_db(self, vector_db_id: str) -> VectorDB:
vector_db = await self.get_object_by_identifier("vector_db", vector_db_id)
if vector_db is None:
raise ValueError(f"Vector DB '{vector_db_id}' not found")
raise VectorStoreNotFoundError(vector_db_id)
return vector_db
async def register_vector_db(
@ -63,7 +64,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
raise ValueError("No provider available. Please configure a vector_io provider.")
model = await lookup_model(self, embedding_model)
if model is None:
raise ValueError(f"Model {embedding_model} not found")
raise ModelNotFoundError(embedding_model)
if model.model_type != ModelType.embedding:
raise ValueError(f"Model {embedding_model} is not an embedding model")
if "embedding_dimension" not in model.metadata:
@ -84,7 +85,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
async def unregister_vector_db(self, vector_db_id: str) -> None:
existing_vector_db = await self.get_vector_db(vector_db_id)
if existing_vector_db is None:
raise ValueError(f"Vector DB {vector_db_id} not found")
raise VectorStoreNotFoundError(vector_db_id)
await self.unregister_object(existing_vector_db)
async def openai_retrieve_vector_store(