RFC-0001-The-Llama-Stack (#8)

* RFC-0001-The-Llama-Stack

* Add OpenAPI generation utility, update SPEC to reflect latest types

* First cut at an observability API

* llama3_1 -> llama3

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_toolchain/evaluations/api/endpoints.py

@@ -60,19 +60,19 @@ class EvaluationJobArtifactsResponse(BaseModel):
 
 class Evaluations(Protocol):
     @webmethod(route="/evaluate/text_generation/")
-    def post_evaluate_text_generation(
+    def evaluate_text_generation(
         self,
         request: EvaluateTextGenerationRequest,
     ) -> EvaluationJob: ...
 
     @webmethod(route="/evaluate/question_answering/")
-    def post_evaluate_question_answering(
+    def evaluate_question_answering(
         self,
         request: EvaluateQuestionAnsweringRequest,
     ) -> EvaluationJob: ...
 
     @webmethod(route="/evaluate/summarization/")
-    def post_evaluate_summarization(
+    def evaluate_summarization(
         self,
         request: EvaluateSummarizationRequest,
     ) -> EvaluationJob: ...

llama_toolchain/memory/api/endpoints.py

@@ -13,7 +13,7 @@ from .datatypes import *  # noqa: F403
 
 class MemoryBanks(Protocol):
     @webmethod(route="/memory_banks/create")
-    def post_create_memory_bank(
+    def create_memory_bank(
         self,
         bank_id: str,
         bank_name: str,
@@ -33,14 +33,14 @@ class MemoryBanks(Protocol):
     ) -> str: ...
 
     @webmethod(route="/memory_bank/insert")
-    def post_insert_memory_documents(
+    def insert_memory_documents(
         self,
         bank_id: str,
         documents: List[MemoryBankDocument],
     ) -> None: ...
 
     @webmethod(route="/memory_bank/update")
-    def post_update_memory_documents(
+    def update_memory_documents(
         self,
         bank_id: str,
         documents: List[MemoryBankDocument],

llama_toolchain/observability/__init__.py

@@ -0,0 +1,5 @@
+# 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.

llama_toolchain/observability/api/__init__.py

@@ -0,0 +1,8 @@
+# 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 .datatypes import *  # noqa: F401 F403
+from .endpoints import *  # noqa: F401 F403

llama_toolchain/observability/api/datatypes.py

@@ -0,0 +1,80 @@
+# 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 datetime import datetime
+from enum import Enum
+
+from typing import Any, Dict, Optional, Union
+
+from llama_models.schema_utils import json_schema_type
+
+from pydantic import BaseModel
+
+
+@json_schema_type
+class ExperimentStatus(Enum):
+    NOT_STARTED = "not_started"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+
+@json_schema_type
+class Experiment(BaseModel):
+    id: str
+    name: str
+    status: ExperimentStatus
+    created_at: datetime
+    updated_at: datetime
+    metadata: Dict[str, Any]
+
+
+@json_schema_type
+class Run(BaseModel):
+    id: str
+    experiment_id: str
+    status: str
+    started_at: datetime
+    ended_at: Optional[datetime]
+    metadata: Dict[str, Any]
+
+
+@json_schema_type
+class Metric(BaseModel):
+    name: str
+    value: Union[float, int, str, bool]
+    timestamp: datetime
+    run_id: str
+
+
+@json_schema_type
+class Log(BaseModel):
+    message: str
+    level: str
+    timestamp: datetime
+    additional_info: Dict[str, Any]
+
+
+@json_schema_type
+class ArtifactType(Enum):
+    MODEL = "model"
+    DATASET = "dataset"
+    CHECKPOINT = "checkpoint"
+    PLOT = "plot"
+    METRIC = "metric"
+    CONFIG = "config"
+    CODE = "code"
+    OTHER = "other"
+
+
+@json_schema_type
+class Artifact(BaseModel):
+    id: str
+    name: str
+    type: ArtifactType
+    size: int
+    created_at: datetime
+    metadata: Dict[str, Any]

llama_toolchain/observability/api/endpoints.py

@@ -0,0 +1,108 @@
+# 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 datetime import datetime
+from typing import Any, Dict, List, Optional, Protocol
+
+from llama_models.schema_utils import json_schema_type, webmethod
+from pydantic import BaseModel
+from llama_models.llama3.api.datatypes import *  # noqa: F403
+from .datatypes import *  # noqa: F403
+
+
+@json_schema_type
+class CreateExperimentRequest(BaseModel):
+    name: str
+    metadata: Optional[Dict[str, Any]] = None
+
+
+@json_schema_type
+class UpdateExperimentRequest(BaseModel):
+    experiment_id: str
+    status: Optional[ExperimentStatus] = None
+    metadata: Optional[Dict[str, Any]] = None
+
+
+@json_schema_type
+class CreateRunRequest(BaseModel):
+    experiment_id: str
+    metadata: Optional[Dict[str, Any]] = None
+
+
+@json_schema_type
+class UpdateRunRequest(BaseModel):
+    run_id: str
+    status: Optional[str] = None
+    ended_at: Optional[datetime] = None
+    metadata: Optional[Dict[str, Any]] = None
+
+
+@json_schema_type
+class LogMetricsRequest(BaseModel):
+    run_id: str
+    metrics: List[Metric]
+
+
+@json_schema_type
+class LogMessagesRequest(BaseModel):
+    logs: List[Log]
+    run_id: Optional[str] = None
+
+
+@json_schema_type
+class UploadArtifactRequest(BaseModel):
+    experiment_id: str
+    name: str
+    artifact_type: str
+    content: bytes
+    metadata: Optional[Dict[str, Any]] = None
+
+
+@json_schema_type
+class LogSearchRequest(BaseModel):
+    query: str
+    filters: Optional[Dict[str, Any]] = None
+
+
+class Observability(Protocol):
+    @webmethod(route="/experiments/create")
+    def create_experiment(self, request: CreateExperimentRequest) -> Experiment: ...
+
+    @webmethod(route="/experiments/list")
+    def list_experiments(self) -> List[Experiment]: ...
+
+    @webmethod(route="/experiments/get")
+    def get_experiment(self, experiment_id: str) -> Experiment: ...
+
+    @webmethod(route="/experiments/update")
+    def update_experiment(self, request: UpdateExperimentRequest) -> Experiment: ...
+
+    @webmethod(route="/experiments/create_run")
+    def create_run(self, request: CreateRunRequest) -> Run: ...
+
+    @webmethod(route="/runs/update")
+    def update_run(self, request: UpdateRunRequest) -> Run: ...
+
+    @webmethod(route="/runs/log_metrics")
+    def log_metrics(self, request: LogMetricsRequest) -> None: ...
+
+    @webmethod(route="/runs/metrics", method="GET")
+    def get_metrics(self, run_id: str) -> List[Metric]: ...
+
+    @webmethod(route="/logging/log_messages")
+    def log_messages(self, request: LogMessagesRequest) -> None: ...
+
+    @webmethod(route="/logging/get_logs")
+    def get_logs(self, request: LogSearchRequest) -> List[Log]: ...
+
+    @webmethod(route="/experiments/artifacts/upload")
+    def upload_artifact(self, request: UploadArtifactRequest) -> Artifact: ...
+
+    @webmethod(route="/experiments/artifacts/get")
+    def list_artifacts(self, experiment_id: str) -> List[Artifact]: ...
+
+    @webmethod(route="/artifacts/get")
+    def get_artifact(self, artifact_id: str) -> Artifact: ...

llama_toolchain/post_training/api/endpoints.py

@@ -95,13 +95,13 @@ class PostTrainingJobArtifactsResponse(BaseModel):
 
 class PostTraining(Protocol):
     @webmethod(route="/post_training/supervised_fine_tune")
-    def post_supervised_fine_tune(
+    def supervised_fine_tune(
         self,
         request: PostTrainingSFTRequest,
     ) -> PostTrainingJob: ...
 
     @webmethod(route="/post_training/preference_optimize")
-    def post_preference_optimize(
+    def preference_optimize(
         self,
         request: PostTrainingRLHFRequest,
     ) -> PostTrainingJob: ...

llama_toolchain/reward_scoring/api/endpoints.py

@@ -27,7 +27,7 @@ class RewardScoringResponse(BaseModel):
 
 class RewardScoring(Protocol):
     @webmethod(route="/reward_scoring/score")
-    def post_score(
+    def reward_score(
         self,
         request: RewardScoringRequest,
     ) -> Union[RewardScoringResponse]: ...

llama_toolchain/stack.py

@@ -0,0 +1,30 @@
+# 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 llama_models.llama3.api.datatypes import *  # noqa: F403
+from llama_toolchain.agentic_system.api import *  # noqa: F403
+from llama_toolchain.dataset.api import *  # noqa: F403
+from llama_toolchain.evaluations.api import *  # noqa: F403
+from llama_toolchain.inference.api import *  # noqa: F403
+from llama_toolchain.memory.api import *  # noqa: F403
+from llama_toolchain.observability.api import *  # noqa: F403
+from llama_toolchain.post_training.api import *  # noqa: F403
+from llama_toolchain.reward_scoring.api import *  # noqa: F403
+from llama_toolchain.synthetic_data_generation.api import *  # noqa: F403
+
+
+class LlamaStack(
+    Inference,
+    AgenticSystem,
+    RewardScoring,
+    SyntheticDataGeneration,
+    Datasets,
+    Observability,
+    PostTraining,
+    MemoryBanks,
+    Evaluations,
+):
+    pass

llama_toolchain/synthetic_data_generation/api/endpoints.py

@@ -34,7 +34,7 @@ class SyntheticDataGenerationResponse(BaseModel):
 
 class SyntheticDataGeneration(Protocol):
     @webmethod(route="/synthetic_data_generation/generate")
-    def post_generate(
+    def synthetic_data_generate(
         self,
         request: SyntheticDataGenerationRequest,
     ) -> Union[SyntheticDataGenerationResponse]: ...