mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-26 08:11:59 +00:00
Merge branch 'main' into feature/dpo-training
This commit is contained in:
Ashwin Bharambe
GitHub
commit
9ac1a01daa
419 changed files with 44853 additions and 1661 deletions
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import AccessRule, Api
|
||||
from llama_stack.core.datatypes import AccessRule, Api
|
||||
|
||||
from .config import MetaReferenceAgentsImplConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ from llama_stack.apis.inference import (
|
|||
from llama_stack.apis.safety import Safety
|
||||
from llama_stack.apis.tools import ToolGroups, ToolInvocationResult, ToolRuntime
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.distribution.datatypes import AccessRule
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.models.llama.datatypes import (
|
||||
BuiltinTool,
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ from llama_stack.apis.inference import (
|
|||
from llama_stack.apis.safety import Safety
|
||||
from llama_stack.apis.tools import ToolGroups, ToolRuntime
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.distribution.datatypes import AccessRule
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
|
||||
from llama_stack.providers.utils.pagination import paginate_records
|
||||
from llama_stack.providers.utils.responses.responses_store import ResponsesStore
|
||||
|
|
|
|||
|
|
@ -10,10 +10,10 @@ import uuid
|
|||
from datetime import UTC, datetime
|
||||
|
||||
from llama_stack.apis.agents import AgentConfig, Session, ToolExecutionStep, Turn
|
||||
from llama_stack.distribution.access_control.access_control import AccessDeniedError, is_action_allowed
|
||||
from llama_stack.distribution.access_control.datatypes import AccessRule
|
||||
from llama_stack.distribution.datatypes import User
|
||||
from llama_stack.distribution.request_headers import get_authenticated_user
|
||||
from llama_stack.core.access_control.access_control import AccessDeniedError, is_action_allowed
|
||||
from llama_stack.core.access_control.datatypes import AccessRule
|
||||
from llama_stack.core.datatypes import User
|
||||
from llama_stack.core.request_headers import get_authenticated_user
|
||||
from llama_stack.providers.utils.kvstore import KVStore
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import MetaReferenceEvalConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import AccessRule, Api
|
||||
from llama_stack.core.datatypes import AccessRule, Api
|
||||
|
||||
from .config import LocalfsFilesImplConfig
|
||||
from .files import LocalfsFilesImpl
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ from llama_stack.apis.files import (
|
|||
OpenAIFileObject,
|
||||
OpenAIFilePurpose,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import AccessRule
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
|
||||
from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.distribution.utils.model_utils import model_local_dir
|
||||
from llama_stack.core.utils.model_utils import model_local_dir
|
||||
|
||||
|
||||
def model_checkpoint_dir(model_id) -> str:
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import HuggingFacePostTrainingConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import TorchtunePostTrainingConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -43,8 +43,8 @@ from llama_stack.apis.post_training import (
|
|||
QATFinetuningConfig,
|
||||
TrainingConfig,
|
||||
)
|
||||
from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
|
||||
from llama_stack.distribution.utils.model_utils import model_local_dir
|
||||
from llama_stack.core.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
|
||||
from llama_stack.core.utils.model_utils import model_local_dir
|
||||
from llama_stack.models.llama.sku_list import resolve_model
|
||||
from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device
|
||||
from llama_stack.providers.inline.post_training.torchtune.common import utils
|
||||
|
|
|
|||
|
|
@ -21,7 +21,7 @@ from llama_stack.apis.safety import (
|
|||
ViolationLevel,
|
||||
)
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
from llama_stack.models.llama.datatypes import Role
|
||||
from llama_stack.models.llama.sku_types import CoreModelId
|
||||
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ from llama_stack.apis.safety import (
|
|||
ViolationLevel,
|
||||
)
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.distribution.utils.model_utils import model_local_dir
|
||||
from llama_stack.core.utils.model_utils import model_local_dir
|
||||
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.prompt_adapter import (
|
||||
interleaved_content_as_str,
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import BasicScoringConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ from llama_stack.apis.scoring import (
|
|||
ScoringResult,
|
||||
)
|
||||
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
|
||||
from llama_stack.providers.utils.common.data_schema_validator import (
|
||||
get_valid_schemas,
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import BraintrustScoringConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -29,8 +29,8 @@ from llama_stack.apis.scoring import (
|
|||
ScoringResultRow,
|
||||
)
|
||||
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.datatypes import Api
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
|
||||
from llama_stack.providers.utils.common.data_schema_validator import (
|
||||
get_valid_schemas,
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import LlmAsJudgeScoringConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ from llama_stack.apis.scoring import (
|
|||
ScoringResult,
|
||||
)
|
||||
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
|
||||
from llama_stack.providers.utils.common.data_schema_validator import (
|
||||
get_valid_schemas,
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import TelemetryConfig, TelemetrySink
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
|
||||
from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
from llama_stack.core.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
|
||||
|
||||
class TelemetrySink(StrEnum):
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ from llama_stack.apis.telemetry import (
|
|||
Trace,
|
||||
UnstructuredLogEvent,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
from llama_stack.providers.inline.telemetry.meta_reference.console_span_processor import (
|
||||
ConsoleSpanProcessor,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@ import faiss
|
|||
import numpy as np
|
||||
from numpy.typing import NDArray
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files import Files
|
||||
from llama_stack.apis.inference import Inference, InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
|
|
@ -285,7 +286,7 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
|
|||
) -> QueryChunksResponse:
|
||||
index = self.cache.get(vector_db_id)
|
||||
if index is None:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@ import numpy as np
|
|||
import sqlite_vec
|
||||
from numpy.typing import NDArray
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files import Files
|
||||
from llama_stack.apis.inference import Inference
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
|
|
@ -508,11 +509,11 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
return self.cache[vector_db_id]
|
||||
|
||||
if self.vector_db_store is None:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
vector_db = self.vector_db_store.get_vector_db(vector_db_id)
|
||||
if not vector_db:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
index = VectorDBWithIndex(
|
||||
vector_db=vector_db,
|
||||
|
|
@ -537,7 +538,7 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
# The VectorDBWithIndex helper is expected to compute embeddings via the inference_api
|
||||
# and then call our index's add_chunks.
|
||||
await index.insert_chunks(chunks)
|
||||
|
|
@ -547,14 +548,14 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
) -> QueryChunksResponse:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
async def delete_chunks(self, store_id: str, chunk_ids: list[str]) -> None:
|
||||
"""Delete a chunk from a sqlite_vec index."""
|
||||
index = await self._get_and_cache_vector_db_index(store_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {store_id} not found")
|
||||
raise VectorStoreNotFoundError(store_id)
|
||||
|
||||
for chunk_id in chunk_ids:
|
||||
# Use the index's delete_chunk method
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ os.environ["NVIDIA_API_KEY"] = "your-api-key"
|
|||
os.environ["NVIDIA_CUSTOMIZER_URL"] = "http://nemo.test"
|
||||
os.environ["NVIDIA_DATASET_NAMESPACE"] = "default"
|
||||
os.environ["NVIDIA_PROJECT_ID"] = "test-project"
|
||||
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
|
||||
from llama_stack.core.library_client import LlamaStackAsLibraryClient
|
||||
|
||||
client = LlamaStackAsLibraryClient("nvidia")
|
||||
client.initialize()
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
from .config import NVIDIAEvalConfig
|
||||
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ os.environ["NVIDIA_API_KEY"] = (
|
|||
)
|
||||
os.environ["NVIDIA_BASE_URL"] = "http://nim.test" # NIM URL
|
||||
|
||||
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
|
||||
from llama_stack.core.library_client import LlamaStackAsLibraryClient
|
||||
|
||||
client = LlamaStackAsLibraryClient("nvidia")
|
||||
client.initialize()
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ from llama_stack.apis.inference import (
|
|||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.models import Model
|
||||
from llama_stack.distribution.library_client import convert_pydantic_to_json_value, convert_to_pydantic
|
||||
from llama_stack.core.library_client import convert_pydantic_to_json_value, convert_to_pydantic
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
|
||||
|
||||
|
|
|
|||
|
|
@ -38,7 +38,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ os.environ["NVIDIA_DATASET_NAMESPACE"] = "default"
|
|||
os.environ["NVIDIA_PROJECT_ID"] = "test-project"
|
||||
os.environ["NVIDIA_OUTPUT_MODEL_DIR"] = "test-example-model@v1"
|
||||
|
||||
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
|
||||
from llama_stack.core.library_client import LlamaStackAsLibraryClient
|
||||
|
||||
client = LlamaStackAsLibraryClient("nvidia")
|
||||
client.initialize()
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ import os
|
|||
os.environ["NVIDIA_API_KEY"] = "your-api-key"
|
||||
os.environ["NVIDIA_GUARDRAILS_URL"] = "http://guardrails.test"
|
||||
|
||||
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
|
||||
from llama_stack.core.library_client import LlamaStackAsLibraryClient
|
||||
|
||||
client = LlamaStackAsLibraryClient("nvidia")
|
||||
client.initialize()
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ from llama_stack.apis.safety import (
|
|||
ViolationLevel,
|
||||
)
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
|
||||
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
|
|||
ToolParameter,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
|
||||
|
||||
from .config import BingSearchToolConfig
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ from llama_stack.apis.tools import (
|
|||
ToolParameter,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.models.llama.datatypes import BuiltinTool
|
||||
from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
|
||||
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ from llama_stack.apis.tools import (
|
|||
ToolInvocationResult,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
|
||||
from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
|
|||
ToolParameter,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
|
||||
|
||||
from .config import TavilySearchToolConfig
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
|
|||
ToolParameter,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
|
||||
|
||||
from .config import WolframAlphaToolConfig
|
||||
|
|
|
|||
|
|
@ -13,6 +13,7 @@ from typing import Any
|
|||
from numpy.typing import NDArray
|
||||
from pymilvus import DataType, Function, FunctionType, MilvusClient
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files.files import Files
|
||||
from llama_stack.apis.inference import Inference, InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
|
|
@ -329,11 +330,11 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
|
|||
return self.cache[vector_db_id]
|
||||
|
||||
if self.vector_db_store is None:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
|
||||
if not vector_db:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
index = VectorDBWithIndex(
|
||||
vector_db=vector_db,
|
||||
|
|
@ -356,7 +357,7 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
|
|||
) -> None:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
await index.insert_chunks(chunks)
|
||||
|
||||
|
|
@ -368,7 +369,7 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
|
|||
) -> QueryChunksResponse:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
if params and params.get("mode") == "keyword":
|
||||
# Check if this is inline Milvus (Milvus-Lite)
|
||||
|
|
@ -384,7 +385,7 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
|
|||
"""Delete a chunk from a milvus vector store."""
|
||||
index = await self._get_and_cache_vector_db_index(store_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {store_id} not found")
|
||||
raise VectorStoreNotFoundError(store_id)
|
||||
|
||||
for chunk_id in chunk_ids:
|
||||
# Use the index's delete_chunk method
|
||||
|
|
|
|||
|
|
@ -13,6 +13,7 @@ from psycopg2 import sql
|
|||
from psycopg2.extras import Json, execute_values
|
||||
from pydantic import BaseModel, TypeAdapter
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files.files import Files
|
||||
from llama_stack.apis.inference import InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
|
|
@ -275,7 +276,7 @@ class PGVectorVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoco
|
|||
"""Delete a chunk from a PostgreSQL vector store."""
|
||||
index = await self._get_and_cache_vector_db_index(store_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {store_id} not found")
|
||||
raise VectorStoreNotFoundError(store_id)
|
||||
|
||||
for chunk_id in chunk_ids:
|
||||
# Use the index's delete_chunk method
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ from numpy.typing import NDArray
|
|||
from qdrant_client import AsyncQdrantClient, models
|
||||
from qdrant_client.models import PointStruct
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.inference import InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import (
|
||||
|
|
@ -173,7 +174,7 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
|||
|
||||
vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
|
||||
if not vector_db:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
index = VectorDBWithIndex(
|
||||
vector_db=vector_db,
|
||||
|
|
@ -191,7 +192,7 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
|||
) -> None:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
await index.insert_chunks(chunks)
|
||||
|
||||
|
|
@ -203,7 +204,7 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
|||
) -> QueryChunksResponse:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
|
|
|
|||
|
|
@ -14,10 +14,11 @@ from weaviate.classes.init import Auth
|
|||
from weaviate.classes.query import Filter
|
||||
|
||||
from llama_stack.apis.common.content_types import InterleavedContent
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files.files import Files
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.api import KVStore
|
||||
|
|
@ -212,7 +213,7 @@ class WeaviateVectorIOAdapter(
|
|||
|
||||
vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
|
||||
if not vector_db:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
client = self._get_client()
|
||||
if not client.collections.exists(vector_db.identifier):
|
||||
|
|
@ -234,7 +235,7 @@ class WeaviateVectorIOAdapter(
|
|||
) -> None:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
await index.insert_chunks(chunks)
|
||||
|
||||
|
|
@ -246,7 +247,7 @@ class WeaviateVectorIOAdapter(
|
|||
) -> QueryChunksResponse:
|
||||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ from llama_stack.apis.common.type_system import (
|
|||
CompletionInputType,
|
||||
StringType,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import Api
|
||||
from llama_stack.core.datatypes import Api
|
||||
|
||||
|
||||
class ColumnName(Enum):
|
||||
|
|
|
|||
|
|
@ -10,8 +10,8 @@ from llama_stack.apis.inference import (
|
|||
OpenAIMessageParam,
|
||||
Order,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import AccessRule
|
||||
from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.core.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
|
||||
from ..sqlstore.api import ColumnDefinition, ColumnType
|
||||
from ..sqlstore.authorized_sqlstore import AuthorizedSqlStore
|
||||
|
|
|
|||
|
|
@ -38,7 +38,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ from typing import Annotated, Literal
|
|||
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
|
||||
from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
from llama_stack.core.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
|
||||
|
||||
class KVStoreType(Enum):
|
||||
|
|
|
|||
|
|
@ -13,6 +13,7 @@ import uuid
|
|||
from abc import ABC, abstractmethod
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.apis.common.errors import VectorStoreNotFoundError
|
||||
from llama_stack.apis.files import Files, OpenAIFileObject
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import (
|
||||
|
|
@ -322,7 +323,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreObject:
|
||||
"""Retrieves a vector store."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
store_info = self.openai_vector_stores[vector_store_id]
|
||||
return VectorStoreObject(**store_info)
|
||||
|
|
@ -336,7 +337,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreObject:
|
||||
"""Modifies a vector store."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
store_info = self.openai_vector_stores[vector_store_id].copy()
|
||||
|
||||
|
|
@ -365,7 +366,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreDeleteResponse:
|
||||
"""Delete a vector store."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
# Delete from persistent storage (provider-specific)
|
||||
await self._delete_openai_vector_store_from_storage(vector_store_id)
|
||||
|
|
@ -403,7 +404,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
raise ValueError(f"search_mode must be one of {valid_modes}, got {search_mode}")
|
||||
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
if isinstance(query, list):
|
||||
search_query = " ".join(query)
|
||||
|
|
@ -556,7 +557,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
chunking_strategy: VectorStoreChunkingStrategy | None = None,
|
||||
) -> VectorStoreFileObject:
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
attributes = attributes or {}
|
||||
chunking_strategy = chunking_strategy or VectorStoreChunkingStrategyAuto()
|
||||
|
|
@ -661,7 +662,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
order = order or "desc"
|
||||
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
store_info = self.openai_vector_stores[vector_store_id]
|
||||
|
||||
|
|
@ -709,7 +710,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreFileObject:
|
||||
"""Retrieves a vector store file."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
store_info = self.openai_vector_stores[vector_store_id]
|
||||
if file_id not in store_info["file_ids"]:
|
||||
|
|
@ -725,7 +726,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreFileContentsResponse:
|
||||
"""Retrieves the contents of a vector store file."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
file_info = await self._load_openai_vector_store_file(vector_store_id, file_id)
|
||||
dict_chunks = await self._load_openai_vector_store_file_contents(vector_store_id, file_id)
|
||||
|
|
@ -748,7 +749,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreFileObject:
|
||||
"""Updates a vector store file."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
store_info = self.openai_vector_stores[vector_store_id]
|
||||
if file_id not in store_info["file_ids"]:
|
||||
|
|
@ -766,7 +767,7 @@ class OpenAIVectorStoreMixin(ABC):
|
|||
) -> VectorStoreFileDeleteResponse:
|
||||
"""Deletes a vector store file."""
|
||||
if vector_store_id not in self.openai_vector_stores:
|
||||
raise ValueError(f"Vector store {vector_store_id} not found")
|
||||
raise VectorStoreNotFoundError(vector_store_id)
|
||||
|
||||
dict_chunks = await self._load_openai_vector_store_file_contents(vector_store_id, file_id)
|
||||
chunks = [Chunk.model_validate(c) for c in dict_chunks]
|
||||
|
|
|
|||
|
|
@ -14,8 +14,8 @@ from llama_stack.apis.agents.openai_responses import (
|
|||
OpenAIResponseObject,
|
||||
OpenAIResponseObjectWithInput,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import AccessRule
|
||||
from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.core.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
|
||||
from ..sqlstore.api import ColumnDefinition, ColumnType
|
||||
from ..sqlstore.authorized_sqlstore import AuthorizedSqlStore
|
||||
|
|
|
|||
|
|
@ -7,11 +7,11 @@
|
|||
from collections.abc import Mapping
|
||||
from typing import Any, Literal
|
||||
|
||||
from llama_stack.distribution.access_control.access_control import default_policy, is_action_allowed
|
||||
from llama_stack.distribution.access_control.conditions import ProtectedResource
|
||||
from llama_stack.distribution.access_control.datatypes import AccessRule, Action, Scope
|
||||
from llama_stack.distribution.datatypes import User
|
||||
from llama_stack.distribution.request_headers import get_authenticated_user
|
||||
from llama_stack.core.access_control.access_control import default_policy, is_action_allowed
|
||||
from llama_stack.core.access_control.conditions import ProtectedResource
|
||||
from llama_stack.core.access_control.datatypes import AccessRule, Action, Scope
|
||||
from llama_stack.core.datatypes import User
|
||||
from llama_stack.core.request_headers import get_authenticated_user
|
||||
from llama_stack.log import get_logger
|
||||
|
||||
from .api import ColumnDefinition, ColumnType, PaginatedResponse, SqlStore
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ from typing import Annotated, Literal
|
|||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
from llama_stack.core.utils.config_dirs import RUNTIME_BASE_DIR
|
||||
|
||||
from .api import SqlStore
|
||||
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ from llama_stack.apis.tools import (
|
|||
ToolInvocationResult,
|
||||
ToolParameter,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import AuthenticationRequiredError
|
||||
from llama_stack.core.datatypes import AuthenticationRequiredError
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.tools.ttl_dict import TTLDict
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue