forked from phoenix-oss/llama-stack-mirror
e830814399
* Add distribution CLI scaffolding * More progress towards `llama distribution install` * getting closer to a distro definition, distro install + configure works * Distribution server now functioning * read existing configuration, save enums properly * Remove inference uvicorn server entrypoint and llama inference CLI command * updated dependency and client model name * Improved exception handling * local imports for faster cli * undo a typo, add a passthrough distribution * implement full-passthrough in the server * add safety adapters, configuration handling, server + clients * cleanup, moving stuff to common, nuke utils * Add a Path() wrapper at the earliest place * fixes * Bring agentic system api to toolchain Add adapter dependencies and resolve adapters using a topological sort * refactor to reduce size of `agentic_system` * move straggler files and fix some important existing bugs * ApiSurface -> Api * refactor a method out * Adapter -> Provider * Make each inference provider into its own subdirectory * installation fixes * Rename Distribution -> DistributionSpec, simplify RemoteProviders * dict key instead of attr * update inference config to take model and not model_dir * Fix passthrough streaming, send headers properly not part of body :facepalm * update safety to use model sku ids and not model dirs * Update cli_reference.md * minor fixes * add DistributionConfig, fix a bug in model download * Make install + start scripts do proper configuration automatically * Update CLI_reference * Nuke fp8_requirements, fold fbgemm into common requirements * Update README, add newline between API surface configurations * Refactor download functionality out of the Command so can be reused * Add `llama model download` alias for `llama download` * Show message about checksum file so users can check themselves * Simpler intro statements * get ollama working * Reduce a bunch of dependencies from toolchain Some improvements to the distribution install script * Avoid using `conda run` since it buffers everything * update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes * add validation for configuration input * resort imports * make optional subclasses default to yes for configuration * Remove additional_pip_packages; move deps to providers * for inline make 8b model the default * Add scripts to MANIFEST * allow installing from test.pypi.org * Fix #2 to help with testing packages * Must install llama-models at that same version first * fix PIP_ARGS --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Hardik Shah <hjshah@meta.com>
99 lines
2.7 KiB
Python
99 lines
2.7 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 typing import List, Protocol
|
|
|
|
from llama_models.schema_utils import webmethod
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_models.llama3_1.api.datatypes import * # noqa: F403
|
|
from .datatypes import * # noqa: F403
|
|
from llama_toolchain.dataset.api.datatypes import * # noqa: F403
|
|
from llama_toolchain.common.training_types import * # noqa: F403
|
|
|
|
|
|
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 post_evaluate_text_generation(
|
|
self,
|
|
request: EvaluateTextGenerationRequest,
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/question_answering/")
|
|
def post_evaluate_question_answering(
|
|
self,
|
|
request: EvaluateQuestionAnsweringRequest,
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/summarization/")
|
|
def post_evaluate_summarization(
|
|
self,
|
|
request: EvaluateSummarizationRequest,
|
|
) -> 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: ...
|