Merge branch 'main' into rag_scoring_fn_1

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -13,19 +13,64 @@ import secrets
 import string
 import uuid
 from datetime import datetime
-from typing import AsyncGenerator, List, Tuple
+from typing import AsyncGenerator, Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 
 import httpx
 
+from llama_models.llama3.api.datatypes import BuiltinTool
 
-from llama_stack.apis.agents import *  # noqa: F403
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTool,
+    AgentTurnCreateRequest,
+    AgentTurnResponseEvent,
+    AgentTurnResponseEventType,
+    AgentTurnResponseStepCompletePayload,
+    AgentTurnResponseStepProgressPayload,
+    AgentTurnResponseStepStartPayload,
+    AgentTurnResponseStreamChunk,
+    AgentTurnResponseTurnCompletePayload,
+    AgentTurnResponseTurnStartPayload,
+    Attachment,
+    CodeInterpreterToolDefinition,
+    FunctionCallToolDefinition,
+    InferenceStep,
+    MemoryRetrievalStep,
+    MemoryToolDefinition,
+    PhotogenToolDefinition,
+    SearchToolDefinition,
+    ShieldCallStep,
+    StepType,
+    ToolExecutionStep,
+    Turn,
+    WolframAlphaToolDefinition,
+)
 
-from llama_stack.apis.common.content_types import InterleavedContent, TextContentItem
+from llama_stack.apis.common.content_types import (
+    InterleavedContent,
+    TextContentItem,
+    URL,
+)
+from llama_stack.apis.inference import (
+    ChatCompletionResponseEventType,
+    CompletionMessage,
+    Inference,
+    Message,
+    SamplingParams,
+    StopReason,
+    SystemMessage,
+    ToolCallDelta,
+    ToolCallParseStatus,
+    ToolChoice,
+    ToolDefinition,
+    ToolResponse,
+    ToolResponseMessage,
+    UserMessage,
+)
+from llama_stack.apis.memory import Memory, MemoryBankDocument, QueryDocumentsResponse
+from llama_stack.apis.memory_banks import MemoryBanks, VectorMemoryBankParams
+from llama_stack.apis.safety import Safety
 
 from llama_stack.providers.utils.kvstore import KVStore
 from llama_stack.providers.utils.memory.vector_store import concat_interleaved_content

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -9,15 +9,26 @@ import logging
 import shutil
 import tempfile
 import uuid
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from termcolor import colored
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentCreateResponse,
+    Agents,
+    AgentSessionCreateResponse,
+    AgentStepResponse,
+    AgentTurnCreateRequest,
+    Attachment,
+    Session,
+    Turn,
+)
+
+from llama_stack.apis.inference import Inference, ToolResponseMessage, UserMessage
 from llama_stack.apis.memory import Memory
 from llama_stack.apis.memory_banks import MemoryBanks
 from llama_stack.apis.safety import Safety
-from llama_stack.apis.agents import *  # noqa: F403
 
 from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
 

llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -10,9 +10,11 @@ import uuid
 from datetime import datetime
 
 from typing import List, Optional
-from llama_stack.apis.agents import *  # noqa: F403
+
 from pydantic import BaseModel
 
+from llama_stack.apis.agents import Turn
+
 from llama_stack.providers.utils.kvstore import KVStore
 
 log = logging.getLogger(__name__)

llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py

@@ -7,8 +7,6 @@
 from typing import List
 
 from jinja2 import Template
-from llama_models.llama3.api import *  # noqa: F403
-
 
 from llama_stack.apis.agents import (
     DefaultMemoryQueryGeneratorConfig,
@@ -16,7 +14,7 @@ from llama_stack.apis.agents import (
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.inference import Message, UserMessage
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )

llama_stack/providers/inline/agents/meta_reference/safety.py

@@ -9,7 +9,9 @@ import logging
 
 from typing import List
 
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.inference import Message
+
+from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
 
 log = logging.getLogger(__name__)
 

llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py

@@ -8,10 +8,26 @@ from typing import AsyncIterator, List, Optional, Union
 
 import pytest
 
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
-from llama_stack.apis.agents import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTurnCreateRequest,
+    AgentTurnResponseTurnCompletePayload,
+)
+
+from llama_stack.apis.inference import (
+    ChatCompletionResponse,
+    ChatCompletionResponseEvent,
+    ChatCompletionResponseStreamChunk,
+    CompletionMessage,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    UserMessage,
+)
+from llama_stack.apis.memory import MemoryBank
+from llama_stack.apis.safety import RunShieldResponse
 
 from ..agents import (
     AGENT_INSTANCES_BY_ID,

llama_stack/providers/inline/agents/meta_reference/tools/safety.py

@@ -7,7 +7,7 @@
 from typing import List
 
 from llama_stack.apis.inference import Message
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.safety import Safety
 
 from ..safety import ShieldRunnerMixin
 from .builtin import BaseTool

llama_stack/providers/inline/datasetio/localfs/config.py

@@ -3,7 +3,7 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.datasetio import *  # noqa: F401, F403
+from pydantic import BaseModel
 
 
 class LocalFSDatasetIOConfig(BaseModel): ...

llama_stack/providers/inline/datasetio/localfs/datasetio.py

@@ -3,18 +3,19 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import Any, Dict, List, Optional
-
-import pandas
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-
-from llama_stack.apis.datasetio import *  # noqa: F403
 import base64
 import os
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
+from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
+import pandas
+
+from llama_stack.apis.common.content_types import URL
+from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult
+from llama_stack.apis.datasets import Dataset
+
 from llama_stack.providers.datatypes import DatasetsProtocolPrivate
 from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url
 

llama_stack/providers/inline/eval/meta_reference/eval.py

@@ -8,6 +8,11 @@ from typing import Any, Dict, List, Optional
 from tqdm import tqdm
 
 from llama_stack.apis.agents import Agents
+from llama_stack.apis.common.type_system import (
+    ChatCompletionInputType,
+    CompletionInputType,
+    StringType,
+)
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
 from llama_stack.apis.eval_tasks import EvalTask

llama_stack/providers/inline/inference/meta_reference/config.py

@@ -6,11 +6,10 @@
 
 from typing import Any, Dict, Optional
 
-from llama_models.datatypes import *  # noqa: F403
-
-from llama_stack.apis.inference import *  # noqa: F401, F403
 from pydantic import BaseModel, field_validator
 
+from llama_stack.apis.inference import QuantizationConfig
+
 from llama_stack.providers.utils.inference import supported_inference_models
 
 

llama_stack/providers/inline/inference/meta_reference/generation.py

@@ -32,11 +32,16 @@ from llama_models.llama3.reference_impl.multimodal.model import (
     CrossAttentionTransformer,
 )
 from llama_models.sku_list import resolve_model
-from pydantic import BaseModel
-
-from llama_stack.apis.inference import *  # noqa: F403
 
 from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
+from pydantic import BaseModel
+
+from llama_stack.apis.inference import (
+    Fp8QuantizationConfig,
+    Int4QuantizationConfig,
+    ResponseFormat,
+    ResponseFormatType,
+)
 
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.utils.inference.prompt_adapter import (
@@ -44,12 +49,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     CompletionRequestWithRawContent,
 )
 
-from .config import (
-    Fp8QuantizationConfig,
-    Int4QuantizationConfig,
-    MetaReferenceInferenceConfig,
-    MetaReferenceQuantizedInferenceConfig,
-)
+from .config import MetaReferenceInferenceConfig, MetaReferenceQuantizedInferenceConfig
 
 log = logging.getLogger(__name__)
 

llama_stack/providers/inline/inference/meta_reference/model_parallel.py

@@ -14,7 +14,10 @@ from llama_models.llama3.api.datatypes import Model
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 
-from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
+from llama_stack.providers.utils.inference.prompt_adapter import (
+    ChatCompletionRequestWithRawContent,
+    CompletionRequestWithRawContent,
+)
 
 from .config import MetaReferenceInferenceConfig
 from .generation import Llama, model_checkpoint_dir
@@ -27,9 +30,9 @@ class ModelRunner:
 
     # the `task` object is the same that is sent to `ModelParallelProcessGroup.run_inference()`
     def __call__(self, req: Any):
-        if isinstance(req, ChatCompletionRequest):
+        if isinstance(req, ChatCompletionRequestWithRawContent):
             return self.llama.chat_completion(req)
-        elif isinstance(req, CompletionRequest):
+        elif isinstance(req, CompletionRequestWithRawContent):
             return self.llama.completion(req)
         else:
             raise ValueError(f"Unexpected task type {type(req)}")
@@ -100,7 +103,7 @@ class LlamaModelParallelGenerator:
 
     def completion(
         self,
-        request: CompletionRequest,
+        request: CompletionRequestWithRawContent,
     ) -> Generator:
         req_obj = deepcopy(request)
         gen = self.group.run_inference(req_obj)
@@ -108,7 +111,7 @@ class LlamaModelParallelGenerator:
 
     def chat_completion(
         self,
-        request: ChatCompletionRequest,
+        request: ChatCompletionRequestWithRawContent,
     ) -> Generator:
         req_obj = deepcopy(request)
         gen = self.group.run_inference(req_obj)

llama_stack/providers/inline/inference/meta_reference/parallel_utils.py

@@ -34,7 +34,10 @@ from pydantic import BaseModel, Field
 from torch.distributed.launcher.api import elastic_launch, LaunchConfig
 from typing_extensions import Annotated
 
-from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
+from llama_stack.providers.utils.inference.prompt_adapter import (
+    ChatCompletionRequestWithRawContent,
+    CompletionRequestWithRawContent,
+)
 
 from .generation import TokenResult
 
@@ -79,7 +82,7 @@ class TaskRequest(BaseModel):
     type: Literal[ProcessingMessageName.task_request] = (
         ProcessingMessageName.task_request
     )
-    task: Union[CompletionRequest, ChatCompletionRequest]
+    task: Union[CompletionRequestWithRawContent, ChatCompletionRequestWithRawContent]
 
 
 class TaskResponse(BaseModel):
@@ -264,9 +267,6 @@ def launch_dist_group(
     init_model_cb: Callable,
     **kwargs,
 ) -> None:
-    id = uuid.uuid4().hex
-    dist_url = f"file:///tmp/llama3_{id}_{time.time()}"
-
     with tempfile.TemporaryDirectory() as tmpdir:
         # TODO: track workers and if they terminate, tell parent process about it so cleanup can happen
         launch_config = LaunchConfig(
@@ -315,7 +315,7 @@ def start_model_parallel_process(
     # wait until the model is loaded; rank 0 will send a message to indicate it's ready
 
     request_socket.send(encode_msg(ReadyRequest()))
-    response = request_socket.recv()
+    _response = request_socket.recv()
     log.info("Loaded model...")
 
     return request_socket, process
@@ -349,7 +349,10 @@ class ModelParallelProcessGroup:
         self.started = False
 
     def run_inference(
-        self, req: Union[CompletionRequest, ChatCompletionRequest]
+        self,
+        req: Union[
+            CompletionRequestWithRawContent, ChatCompletionRequestWithRawContent
+        ],
     ) -> Generator:
         assert not self.running, "inference already running"
 

llama_stack/providers/inline/inference/vllm/vllm.py

@@ -7,10 +7,10 @@
 import logging
 import os
 import uuid
-from typing import AsyncGenerator, Optional
+from typing import AsyncGenerator, List, Optional
 
 from llama_models.llama3.api.chat_format import ChatFormat
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 
@@ -18,9 +18,26 @@ from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.sampling_params import SamplingParams as VLLMSamplingParams
 
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionResponseStreamChunk,
+    CompletionResponse,
+    CompletionResponseStreamChunk,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.apis.models import Model
 
-from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
+from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,

llama_stack/providers/inline/memory/faiss/faiss.py

@@ -16,11 +16,14 @@ import faiss
 import numpy as np
 from numpy.typing import NDArray
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-
-from llama_stack.apis.memory import *  # noqa: F403
 from llama_stack.apis.inference import InterleavedContent
-from llama_stack.apis.memory_banks import MemoryBankType, VectorMemoryBank
+from llama_stack.apis.memory import (
+    Chunk,
+    Memory,
+    MemoryBankDocument,
+    QueryDocumentsResponse,
+)
+from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType, VectorMemoryBank
 from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.memory.vector_store import (

llama_stack/providers/inline/post_training/torchtune/common/utils.py

@@ -14,11 +14,10 @@ from enum import Enum
 from typing import Any, Callable, Dict, List
 
 import torch
-from llama_stack.apis.datasets import Datasets
-from llama_stack.apis.common.type_system import *  # noqa
 from llama_models.datatypes import Model
 from llama_models.sku_list import resolve_model
-from llama_stack.apis.common.type_system import ParamType
+from llama_stack.apis.common.type_system import ParamType, StringType
+from llama_stack.apis.datasets import Datasets
 
 from torchtune.models.llama3 import llama3_tokenizer, lora_llama3_8b
 from torchtune.models.llama3._tokenizer import Llama3Tokenizer

llama_stack/providers/inline/post_training/torchtune/post_training.py

@@ -3,11 +3,26 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+from datetime import datetime
+from typing import Any, Dict, List, Optional
+
+from llama_models.schema_utils import webmethod
+
 from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.post_training import (
+    AlgorithmConfig,
+    DPOAlignmentConfig,
+    JobStatus,
+    LoraFinetuningConfig,
+    PostTrainingJob,
+    PostTrainingJobArtifactsResponse,
+    PostTrainingJobStatusResponse,
+    TrainingConfig,
+)
 from llama_stack.providers.inline.post_training.torchtune.config import (
     TorchtunePostTrainingConfig,
 )
-from llama_stack.apis.post_training import *  # noqa
 from llama_stack.providers.inline.post_training.torchtune.recipes.lora_finetuning_single_device import (
     LoraFinetuningSingleDevice,
 )

llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py

@@ -14,27 +14,33 @@ from typing import Any, Dict, List, Optional, Tuple
 import torch
 from llama_models.sku_list import resolve_model
 
+from llama_stack.apis.common.training_types import PostTrainingMetric
 from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.post_training import (
+    AlgorithmConfig,
+    Checkpoint,
+    LoraFinetuningConfig,
+    OptimizerConfig,
+    TrainingConfig,
+)
 
 from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
-from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import (
-    TorchtuneCheckpointer,
-)
-from torch import nn
-from torchtune import utils as torchtune_utils
-from torchtune.training.metric_logging import DiskLogger
-from tqdm import tqdm
-from llama_stack.apis.post_training import *  # noqa
+
 from llama_stack.distribution.utils.model_utils import model_local_dir
 
 from llama_stack.providers.inline.post_training.torchtune.common import utils
+from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import (
+    TorchtuneCheckpointer,
+)
 from llama_stack.providers.inline.post_training.torchtune.config import (
     TorchtunePostTrainingConfig,
 )
 from llama_stack.providers.inline.post_training.torchtune.datasets.sft import SFTDataset
+from torch import nn
 from torch.optim import Optimizer
 from torch.utils.data import DataLoader, DistributedSampler
-from torchtune import modules, training
+from torchtune import modules, training, utils as torchtune_utils
 from torchtune.data import AlpacaToMessages, padded_collate_sft
 
 from torchtune.modules.loss import CEWithChunkedOutputLoss
@@ -43,11 +49,12 @@ from torchtune.modules.peft import (
     get_adapter_state_dict,
     get_lora_module_names,
     get_merged_lora_ckpt,
-    load_dora_magnitudes,
     set_trainable_params,
     validate_missing_and_unexpected_for_lora,
 )
 from torchtune.training.lr_schedulers import get_cosine_schedule_with_warmup
+from torchtune.training.metric_logging import DiskLogger
+from tqdm import tqdm
 
 log = logging.getLogger(__name__)
 
@@ -110,6 +117,10 @@ class LoraFinetuningSingleDevice:
             self.checkpoint_dir = config.checkpoint_dir
         else:
             model = resolve_model(self.model_id)
+            if model is None:
+                raise ValueError(
+                    f"{self.model_id} not found. Your model id should be in the llama models SKU list"
+                )
             self.checkpoint_dir = model_checkpoint_dir(model)
 
         self._output_dir = str(DEFAULT_CHECKPOINT_DIR)
@@ -277,7 +288,6 @@ class LoraFinetuningSingleDevice:
             for m in model.modules():
                 if hasattr(m, "initialize_dora_magnitude"):
                     m.initialize_dora_magnitude()
-            load_dora_magnitudes(model)
         if lora_weights_state_dict:
             lora_missing, lora_unexpected = model.load_state_dict(
                 lora_weights_state_dict, strict=False

llama_stack/providers/inline/safety/code_scanner/code_scanner.py

@@ -7,8 +7,14 @@
 import logging
 from typing import Any, Dict, List
 
-from llama_stack.apis.safety import *  # noqa: F403
 from llama_stack.apis.inference import Message
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    ViolationLevel,
+)
+from llama_stack.apis.shields import Shield
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -9,10 +9,24 @@ import re
 from string import Template
 from typing import Any, Dict, List, Optional
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_models.datatypes import CoreModelId
+from llama_models.llama3.api.datatypes import Role
+
 from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
+from llama_stack.apis.inference import (
+    ChatCompletionResponseEventType,
+    Inference,
+    Message,
+    UserMessage,
+)
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    ViolationLevel,
+)
+
+from llama_stack.apis.shields import Shield
 from llama_stack.distribution.datatypes import Api
 
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate

llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py

@@ -11,11 +11,16 @@ import torch
 
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-from llama_stack.distribution.utils.model_utils import model_local_dir
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+from llama_stack.apis.inference import Message
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    ViolationLevel,
+)
+from llama_stack.apis.shields import Shield
 
+from llama_stack.distribution.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,

llama_stack/providers/inline/scoring/basic/scoring.py

@@ -3,14 +3,17 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import List
+from typing import Any, Dict, List, Optional
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.scoring import *  # noqa: F403
-from llama_stack.apis.scoring_functions import *  # noqa: F403
-from llama_stack.apis.common.type_system import *  # noqa: F403
-from llama_stack.apis.datasetio import *  # noqa: F403
-from llama_stack.apis.datasets import *  # noqa: F403
+from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.scoring import (
+    ScoreBatchResponse,
+    ScoreResponse,
+    Scoring,
+    ScoringResult,
+)
+from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 from llama_stack.providers.utils.common.data_schema_validator_mixin import (
     DataSchemaValidatorMixin,

llama_stack/providers/inline/scoring/braintrust/braintrust.py

@@ -3,21 +3,24 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import List
-
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.scoring import *  # noqa: F403
-from llama_stack.apis.scoring_functions import *  # noqa: F403
-from llama_stack.apis.common.type_system import *  # noqa: F403
-from llama_stack.apis.datasetio import *  # noqa: F403
-from llama_stack.apis.datasets import *  # noqa: F403
-
 import os
+from typing import Any, Dict, List, Optional
 
 from autoevals.llm import Factuality
 from autoevals.ragas import AnswerCorrectness
 from pydantic import BaseModel
 
+from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.scoring import (
+    ScoreBatchResponse,
+    ScoreResponse,
+    Scoring,
+    ScoringResult,
+    ScoringResultRow,
+)
+from llama_stack.apis.scoring_functions import AggregationFunctionType, ScoringFn
+
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 from llama_stack.providers.utils.common.data_schema_validator_mixin import (

llama_stack/providers/inline/scoring/braintrust/config.py

@@ -3,7 +3,9 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.scoring import *  # noqa: F401, F403
+from typing import Any, Dict, Optional
+
+from pydantic import BaseModel, Field
 
 
 class BraintrustScoringConfig(BaseModel):

llama_stack/providers/inline/telemetry/meta_reference/telemetry.py

@@ -17,6 +17,22 @@ from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
 from opentelemetry.semconv.resource import ResourceAttributes
 
+from llama_stack.apis.telemetry import (
+    Event,
+    MetricEvent,
+    QueryCondition,
+    SpanEndPayload,
+    SpanStartPayload,
+    SpanStatus,
+    SpanWithStatus,
+    StructuredLogEvent,
+    Telemetry,
+    Trace,
+    UnstructuredLogEvent,
+)
+
+from llama_stack.distribution.datatypes import Api
+
 from llama_stack.providers.inline.telemetry.meta_reference.console_span_processor import (
     ConsoleSpanProcessor,
 )
@@ -27,10 +43,6 @@ from llama_stack.providers.inline.telemetry.meta_reference.sqlite_span_processor
 from llama_stack.providers.utils.telemetry.dataset_mixin import TelemetryDatasetMixin
 from llama_stack.providers.utils.telemetry.sqlite_trace_store import SQLiteTraceStore
 
-from llama_stack.apis.telemetry import *  # noqa: F403
-
-from llama_stack.distribution.datatypes import Api
-
 from .config import TelemetryConfig, TelemetrySink
 
 _GLOBAL_STORAGE = {

llama_stack/providers/inline/telemetry/sample/sample.py

@@ -4,12 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from llama_stack.apis.telemetry import Telemetry
 from .config import SampleConfig
 
 
-from llama_stack.apis.telemetry import *  # noqa: F403
-
-
 class SampleTelemetryImpl(Telemetry):
     def __init__(self, config: SampleConfig):
         self.config = config

llama_stack/providers/inline/tool_runtime/brave_search/__init__.py

@@ -0,0 +1,20 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from pydantic import BaseModel
+
+from .brave_search import BraveSearchToolRuntimeImpl
+from .config import BraveSearchToolConfig
+
+
+class BraveSearchToolProviderDataValidator(BaseModel):
+    api_key: str
+
+
+async def get_provider_impl(config: BraveSearchToolConfig, _deps):
+    impl = BraveSearchToolRuntimeImpl(config)
+    await impl.initialize()
+    return impl

llama_stack/providers/inline/tool_runtime/brave_search/brave_search.py

@@ -0,0 +1,123 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Any, Dict, List
+
+import requests
+
+from llama_stack.apis.tools import Tool, ToolGroupDef, ToolInvocationResult, ToolRuntime
+from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.providers.datatypes import ToolsProtocolPrivate
+
+from .config import BraveSearchToolConfig
+
+
+class BraveSearchToolRuntimeImpl(
+    ToolsProtocolPrivate, ToolRuntime, NeedsRequestProviderData
+):
+    def __init__(self, config: BraveSearchToolConfig):
+        self.config = config
+
+    async def initialize(self):
+        pass
+
+    async def register_tool(self, tool: Tool):
+        if tool.identifier != "brave_search":
+            raise ValueError(f"Tool identifier {tool.identifier} is not supported")
+
+    async def unregister_tool(self, tool_id: str) -> None:
+        return
+
+    def _get_api_key(self) -> str:
+        if self.config.api_key:
+            return self.config.api_key
+
+        provider_data = self.get_request_provider_data()
+        if provider_data is None or not provider_data.api_key:
+            raise ValueError(
+                'Pass Search provider\'s API Key in the header X-LlamaStack-ProviderData as { "api_key": <your api key>}'
+            )
+        return provider_data.api_key
+
+    async def discover_tools(self, tool_group: ToolGroupDef) -> List[Tool]:
+        raise NotImplementedError("Brave search tool group not supported")
+
+    async def invoke_tool(
+        self, tool_name: str, args: Dict[str, Any]
+    ) -> ToolInvocationResult:
+        api_key = self._get_api_key()
+        url = "https://api.search.brave.com/res/v1/web/search"
+        headers = {
+            "X-Subscription-Token": api_key,
+            "Accept-Encoding": "gzip",
+            "Accept": "application/json",
+        }
+        payload = {"q": args["query"]}
+        response = requests.get(url=url, params=payload, headers=headers)
+        response.raise_for_status()
+        results = self._clean_brave_response(response.json())
+        content_items = "\n".join([str(result) for result in results])
+        return ToolInvocationResult(
+            content=content_items,
+        )
+
+    def _clean_brave_response(self, search_response):
+        clean_response = []
+        if "mixed" in search_response:
+            mixed_results = search_response["mixed"]
+            for m in mixed_results["main"][: self.config.max_results]:
+                r_type = m["type"]
+                results = search_response[r_type]["results"]
+                cleaned = self._clean_result_by_type(r_type, results, m.get("index"))
+                clean_response.append(cleaned)
+
+        return clean_response
+
+    def _clean_result_by_type(self, r_type, results, idx=None):
+        type_cleaners = {
+            "web": (
+                ["type", "title", "url", "description", "date", "extra_snippets"],
+                lambda x: x[idx],
+            ),
+            "faq": (["type", "question", "answer", "title", "url"], lambda x: x),
+            "infobox": (
+                ["type", "title", "url", "description", "long_desc"],
+                lambda x: x[idx],
+            ),
+            "videos": (["type", "url", "title", "description", "date"], lambda x: x),
+            "locations": (
+                [
+                    "type",
+                    "title",
+                    "url",
+                    "description",
+                    "coordinates",
+                    "postal_address",
+                    "contact",
+                    "rating",
+                    "distance",
+                    "zoom_level",
+                ],
+                lambda x: x,
+            ),
+            "news": (["type", "title", "url", "description"], lambda x: x),
+        }
+
+        if r_type not in type_cleaners:
+            return ""
+
+        selected_keys, result_selector = type_cleaners[r_type]
+        results = result_selector(results)
+
+        if isinstance(results, list):
+            cleaned = [
+                {k: v for k, v in item.items() if k in selected_keys}
+                for item in results
+            ]
+        else:
+            cleaned = {k: v for k, v in results.items() if k in selected_keys}
+
+        return str(cleaned)

llama_stack/providers/inline/tool_runtime/brave_search/config.py

@@ -0,0 +1,20 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class BraveSearchToolConfig(BaseModel):
+    api_key: Optional[str] = Field(
+        default=None,
+        description="The Brave Search API Key",
+    )
+    max_results: int = Field(
+        default=3,
+        description="The maximum number of results to return",
+    )