mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
122 lines
3 KiB
Python
122 lines
3 KiB
Python
# 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 enum import Enum
|
|
from typing import List, Protocol
|
|
|
|
from llama_models.schema_utils import webmethod
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.dataset import * # noqa: F403
|
|
from llama_stack.apis.common.training_types import * # noqa: F403
|
|
|
|
|
|
class TextGenerationMetric(Enum):
|
|
perplexity = "perplexity"
|
|
rouge = "rouge"
|
|
bleu = "bleu"
|
|
|
|
|
|
class QuestionAnsweringMetric(Enum):
|
|
em = "em"
|
|
f1 = "f1"
|
|
|
|
|
|
class SummarizationMetric(Enum):
|
|
rouge = "rouge"
|
|
bleu = "bleu"
|
|
|
|
|
|
class EvaluationJob(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
class EvaluationJobLogStream(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
class EvaluateTaskRequestCommon(BaseModel):
|
|
job_uuid: str
|
|
dataset: TrainEvalDataset
|
|
|
|
checkpoint: Checkpoint
|
|
|
|
# generation params
|
|
sampling_params: SamplingParams = SamplingParams()
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateTextGenerationRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate text generation."""
|
|
|
|
metrics: List[TextGenerationMetric]
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateQuestionAnsweringRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate question answering."""
|
|
|
|
metrics: List[QuestionAnsweringMetric]
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateSummarizationRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate summarization."""
|
|
|
|
metrics: List[SummarizationMetric]
|
|
|
|
|
|
class EvaluationJobStatusResponse(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluationJobArtifactsResponse(BaseModel):
|
|
"""Artifacts of a evaluation job."""
|
|
|
|
job_uuid: str
|
|
|
|
|
|
class Evaluations(Protocol):
|
|
@webmethod(route="/evaluate/text_generation/")
|
|
def evaluate_text_generation(
|
|
self,
|
|
metrics: List[TextGenerationMetric],
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/question_answering/")
|
|
def evaluate_question_answering(
|
|
self,
|
|
metrics: List[QuestionAnsweringMetric],
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/summarization/")
|
|
def evaluate_summarization(
|
|
self,
|
|
metrics: List[SummarizationMetric],
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/jobs")
|
|
def get_evaluation_jobs(self) -> List[EvaluationJob]: ...
|
|
|
|
@webmethod(route="/evaluate/job/status")
|
|
def get_evaluation_job_status(
|
|
self, job_uuid: str
|
|
) -> EvaluationJobStatusResponse: ...
|
|
|
|
# sends SSE stream of logs
|
|
@webmethod(route="/evaluate/job/logs")
|
|
def get_evaluation_job_logstream(self, job_uuid: str) -> EvaluationJobLogStream: ...
|
|
|
|
@webmethod(route="/evaluate/job/cancel")
|
|
def cancel_evaluation_job(self, job_uuid: str) -> None: ...
|
|
|
|
@webmethod(route="/evaluate/job/artifacts")
|
|
def get_evaluation_job_artifacts(
|
|
self, job_uuid: str
|
|
) -> EvaluationJobArtifactsResponse: ...
|