diff --git a/machine/jobs/build_clearml_helper.py b/machine/jobs/build_clearml_helper.py index bbc2c7bf..7d56ed0d 100644 --- a/machine/jobs/build_clearml_helper.py +++ b/machine/jobs/build_clearml_helper.py @@ -2,15 +2,18 @@ import logging import os from datetime import datetime, timezone -from typing import Callable, Optional, Union, cast +from typing import Callable, Optional, TypeVar, Union, cast from clearml import Task from dynaconf.base import Settings +from pydantic import BaseModel, ValidationError from ..utils.canceled_error import CanceledError from ..utils.phased_progress_reporter import PhaseProgressStatus from ..utils.progress_status import ProgressStatus +T = TypeVar("T", bound=BaseModel) + class ProgressInfo: last_percent_completed: Union[int, None] = 0 @@ -119,7 +122,7 @@ def local_progress(progress_status: ProgressStatus) -> None: return local_progress -def update_settings(settings: Settings, args: dict, task: Optional[Task], logger: logging.Logger): +def update_settings(settings: Settings, args: dict, task: Optional[Task], logger: logging.Logger, model: type[T]): settings.update(args) settings.model_type = cast(str, settings.model_type).lower() if "build_options" in settings: @@ -129,6 +132,10 @@ def update_settings(settings: Settings, args: dict, task: Optional[Task], logger raise ValueError("Build options could not be parsed: Invalid JSON") from e except TypeError as e: raise TypeError(f"Build options could not be parsed: {e}") from e + try: + model.model_validate(build_options) + except ValidationError as e: + raise ValueError(f"Invalid build options: {e}") from e settings.update({settings.model_type: build_options}) if "align_pretranslations" in build_options: settings.update({"align_pretranslations": build_options["align_pretranslations"]}) diff --git a/machine/jobs/build_nmt_engine.py b/machine/jobs/build_nmt_engine.py index 5e4d208a..09522975 100644 --- a/machine/jobs/build_nmt_engine.py +++ b/machine/jobs/build_nmt_engine.py @@ -8,6 +8,7 @@ from ..utils.progress_status import ProgressStatus from .build_clearml_helper import report_clearml_progress, update_settings from .config import SETTINGS +from .nmt_build_options import NmtBuildOptions from .nmt_engine_build_job import NmtEngineBuildJob from .nmt_model_factory import NmtModelFactory from .shared_file_service_factory import SharedFileServiceType @@ -45,7 +46,7 @@ def clearml_progress(status: ProgressStatus) -> None: try: logger.info("NMT Engine Build Job started") - update_settings(SETTINGS, args, task, logger) + update_settings(SETTINGS, args, task, logger, NmtBuildOptions) translation_file_service = TranslationFileService(SharedFileServiceType.CLEARML, SETTINGS) nmt_model_factory: NmtModelFactory diff --git a/machine/jobs/build_smt_engine.py b/machine/jobs/build_smt_engine.py index 8a9883d1..357888e3 100644 --- a/machine/jobs/build_smt_engine.py +++ b/machine/jobs/build_smt_engine.py @@ -14,6 +14,7 @@ ) from .config import SETTINGS from .shared_file_service_factory import SharedFileServiceType +from .smt_build_options import SmtBuildOptions from .smt_engine_build_job import SmtEngineBuildJob from .smt_model_factory import SmtModelFactory from .translation_file_service import TranslationFileService @@ -46,7 +47,7 @@ def run(args: dict) -> None: try: logger.info("SMT Engine Build Job started") - update_settings(SETTINGS, args, task, logger) + update_settings(SETTINGS, args, task, logger, SmtBuildOptions) shared_file_service = TranslationFileService(SharedFileServiceType.CLEARML, SETTINGS) smt_model_factory: SmtModelFactory diff --git a/machine/jobs/build_word_alignment_model.py b/machine/jobs/build_word_alignment_model.py index 1181e665..e68ff0db 100644 --- a/machine/jobs/build_word_alignment_model.py +++ b/machine/jobs/build_word_alignment_model.py @@ -16,6 +16,7 @@ from .shared_file_service_factory import SharedFileServiceType from .thot.thot_word_alignment_model_factory import ThotWordAlignmentModelFactory from .word_alignment_build_job import WordAlignmentBuildJob +from .word_alignment_build_options import WordAlignmentBuildOptions from .word_alignment_file_service import WordAlignmentFileService from .word_alignment_model_factory import WordAlignmentModelFactory @@ -47,7 +48,7 @@ def run(args: dict): try: logger.info("Word Alignment Build Job started") - update_settings(SETTINGS, args, task, logger) + update_settings(SETTINGS, args, task, logger, WordAlignmentBuildOptions) word_alignment_file_service = WordAlignmentFileService(SharedFileServiceType.CLEARML, SETTINGS) word_alignment_model_factory: WordAlignmentModelFactory diff --git a/machine/jobs/nmt_build_options.py b/machine/jobs/nmt_build_options.py new file mode 100644 index 00000000..9ae5e625 --- /dev/null +++ b/machine/jobs/nmt_build_options.py @@ -0,0 +1,71 @@ +from typing import Literal + +from pydantic import BaseModel, ConfigDict + + +class TrainParams(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + do_train: bool | None = None + optim: str | None = None + warmup_steps: int | None = None + per_device_train_batch_size: int | None = None + gradient_accumulation_steps: int | None = None + label_smoothing_factor: float | None = None + group_by_length: bool | None = None + gradient_checkpointing: bool | None = None + lr_scheduler_type: str | None = None + learning_rate: float | None = None + fp16: bool | None = None + tf32: bool | None = None + save_strategy: str | None = None + max_steps: int | None = None + + +class GenerateParams(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + device: int | None = None + num_beams: int | None = 2 + batch_size: int | None = None + oom_batch_size_backoff_mult: float | None = None + + +class TokenizerConfig(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + add_unk_src_tokens: bool | None = None + add_unk_trg_tokens: bool | None = None + + +class NmtBuildOptions(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + align_pretranslations: bool | None = None + tags: list[str] | str | None = None + use_key_terms: bool | None = None + parent_model_name: ( + Literal[ + "facebook/nllb-200-distilled-1.3B", + "facebook/nllb-200-distilled-600M", + "hf-internal-testing/tiny-random-nllb", + ] + | None + ) = None + train_params: TrainParams | None = None + generate_params: GenerateParams | None = None + tokenizer: TokenizerConfig | None = None + attn_implementation: str | None = None + max_steps: int | None = None diff --git a/machine/jobs/smt_build_options.py b/machine/jobs/smt_build_options.py new file mode 100644 index 00000000..ebfb0470 --- /dev/null +++ b/machine/jobs/smt_build_options.py @@ -0,0 +1,22 @@ +from pydantic import BaseModel, ConfigDict + + +class ThotMt(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + word_alignment_model_type: str | None = None + tokenizer: str | None = None + + +class SmtBuildOptions(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + tags: list[str] | str | None = None + use_key_terms: bool | None = None + thot_mt: ThotMt | None = None diff --git a/machine/jobs/word_alignment_build_options.py b/machine/jobs/word_alignment_build_options.py new file mode 100644 index 00000000..aced6d21 --- /dev/null +++ b/machine/jobs/word_alignment_build_options.py @@ -0,0 +1,23 @@ +from pydantic import BaseModel, ConfigDict + + +class ThotAlign(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + word_alignment_heuristic: str | None = None + model_type: str | None = None + tokenizer: str | None = None + + +class WordAlignmentBuildOptions(BaseModel): + model_config = ConfigDict( + extra="forbid", + strict=True, + ) + + tags: list[str] | str | None = None + use_key_terms: bool | None = None + thot_align: ThotAlign | None = None diff --git a/poetry.lock b/poetry.lock index 453496c2..b3c1362b 100644 --- a/poetry.lock +++ b/poetry.lock @@ -198,6 +198,17 @@ files = [ frozenlist = ">=1.1.0" typing-extensions = {version = ">=4.2", markers = "python_version < \"3.13\""} +[[package]] +name = "annotated-types" +version = "0.7.0" +description = "Reusable constraint types to use with typing.Annotated" +optional = false +python-versions = ">=3.8" +files = [ + {file = "annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53"}, + {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"}, +] + [[package]] name = "anyio" version = "4.12.1" @@ -3417,6 +3428,159 @@ files = [ {file = "pycparser-2.23.tar.gz", hash = "sha256:78816d4f24add8f10a06d6f05b4d424ad9e96cfebf68a4ddc99c65c0720d00c2"}, ] +[[package]] +name = "pydantic" +version = "2.13.4" +description = "Data validation using Python type hints" +optional = false +python-versions = ">=3.9" +files = [ + {file = "pydantic-2.13.4-py3-none-any.whl", hash = "sha256:45a282cde31d808236fd7ea9d919b128653c8b38b393d1c4ab335c62924d9aba"}, + {file = "pydantic-2.13.4.tar.gz", hash = "sha256:c40756b57adaa8b1efeeced5c196f3f3b7c435f90e84ea7f443901bec8099ef6"}, +] + +[package.dependencies] +annotated-types = ">=0.6.0" +pydantic-core = "2.46.4" +typing-extensions = ">=4.14.1" +typing-inspection = ">=0.4.2" + +[package.extras] +email = ["email-validator (>=2.0.0)"] +timezone = ["tzdata"] + +[[package]] +name = "pydantic-core" +version = "2.46.4" +description = "Core functionality for Pydantic validation and serialization" +optional = false +python-versions = ">=3.9" +files = [ + {file = "pydantic_core-2.46.4-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:a396dcc17e5a0b164dbe026896245a4fa9ff402edca1dff0be3d53a517f74de4"}, + {file = "pydantic_core-2.46.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:da4b951fe36dc7c3a1ccb4e3cd1747c3542b8c9ceede8fc86cae054e764485f5"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb63e0198ca18aad131c089b9204c23079c3afa95487e561f4c522d519e55aba"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f47286a97f0bc9b8859519809077b91b2cefe4ae47fcbf5e466a009c1c5d742b"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:905a0ed8ea6f2d61c1738835f99b699348d7857379083e5fc497fa0c967a407c"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea793e075b70290d89d8142074262885d3f7da19634845135751bd6344f73b50"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:395aebd9183f9d112f569aeb5b2214d1a10a33bec8456447f7fbdfa51d38d4cd"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_31_riscv64.whl", hash = "sha256:b078afbc25f3a1436c7a1d2cd3e322497ee99615ba97c563566fdf46aff1ee01"}, + {file = "pydantic_core-2.46.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f747929cf940cddb5b3668a390056ddd5ba2e5010615ea2dcf4f9c4f3ab8791d"}, + {file = "pydantic_core-2.46.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:daa27d92c36f24388fe3ad306b174781c747627f134452e4f128ea00ce1fe8c4"}, + {file = "pydantic_core-2.46.4-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:19e51f073cd3df251856a8a4189fbdf1de4012c3ebacfb1884f94f1eb406079f"}, + {file = "pydantic_core-2.46.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c1747f85cee84c26985853c6f3d9bd3e75da5212912443fa111c113b9c246f39"}, + {file = "pydantic_core-2.46.4-cp310-cp310-win32.whl", hash = "sha256:2f84c03c8607173d16b5a854ec68a2f9079ae03237a54fb506d13af47e1d018d"}, + {file = "pydantic_core-2.46.4-cp310-cp310-win_amd64.whl", hash = "sha256:8358a950c8909158e3df31538a7e4edc2d7265a7c54b47f0864d9e5bae9dcebf"}, + {file = "pydantic_core-2.46.4-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:0e96592440881c74a213e5ad528e2b24d3d4f940de2766bed9010ab1d9e51594"}, + {file = "pydantic_core-2.46.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e0d65b8c354be7fb5f720c3caa8bc940bc2d20ce749c8e06135f07f8ed95dd7c"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bfb192b3f4b9e8a89b6277b6ce787564f62cfd272055f6e685726b111dc7826"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9037063db01f09b09e237c282b6792bd4da634b5402c4e7f0c61effed7701a04"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fc010ab034c8c7452522748bf937df58020d256ccae0874463d1f4d01758af8e"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c5dac79fa1614d1e06ca695109c6105923bd9c7d1d6c918d4e637b7e6b32fd3"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9fa868638bf362d3d138ea55829cefb3d5f4b0d7f142234382a15e2485dbec4"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_31_riscv64.whl", hash = "sha256:17299feefe090f2caa5b8e37222bb5f663e4935a8bfa6931d4102e5df1a9f398"}, + {file = "pydantic_core-2.46.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4c63ebc82684aa89d9a3bcbd13d515b3be44250dc68dd3bd81526c1cb31286c3"}, + {file = "pydantic_core-2.46.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:aaa2a54443eff1950ba5ddc6b6ccda0d9c84a364276a62f969bdf2a390650848"}, + {file = "pydantic_core-2.46.4-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:18e5ceec2ab67e6d5f1a9085e5a24c9c4e2ac4545730bfe668680bca05e555f3"}, + {file = "pydantic_core-2.46.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a0f62d0a58f4e7da165457e995725421e0064f2255d8eccebc49f41bbc23b109"}, + {file = "pydantic_core-2.46.4-cp311-cp311-win32.whl", hash = "sha256:041bde0a48fd37cf71cab1c9d56d3e8625a3793fef1f7dd232b3ff37e978ecda"}, + {file = "pydantic_core-2.46.4-cp311-cp311-win_amd64.whl", hash = "sha256:6f2eeda33a839975441c86a4119e1383c50b47faf0cbb5176985565c6bb02c33"}, + {file = "pydantic_core-2.46.4-cp311-cp311-win_arm64.whl", hash = "sha256:14f4c5d6db102bd796a627bbb3a17b4cf4574b9ae861d8b7c9a9661c6dd3362d"}, + {file = "pydantic_core-2.46.4-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:3245406455a5d98187ec35530fd772b1d799b26667980872c8d4614991e2c4a2"}, + {file = "pydantic_core-2.46.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:962ccbab7b642487b1d8b7df90ef677e03134cf1fd8880bf698649b22a69371f"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8233f2947cf85404441fd7e0085f53b10c93e0ee78611099b5c7237e36aacbf7"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3a233125ac121aa3ffba9a2b59edfc4a985a76092dc8279586ab4b71390875e7"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5b712b53160b79a5850310b912a5ef8e57e56947c8ad690c227f5c9d7e561712"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9401557acd873c3a7f3eb9383edef8ac4968f9510e340f4808d427e75667e7b4"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:926c9541b14b12b1681dca8a0b75feb510b06c6341b70a8e500c2fdcff837cce"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_31_riscv64.whl", hash = "sha256:56cb4851bcaf3d117eddcef4fe66afd750a50274b0da8e22be256d10e5611987"}, + {file = "pydantic_core-2.46.4-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c68fcd102d71ea85c5b2dfac3f4f8476eff42a9e078fd5faefff6d145063536b"}, + {file = "pydantic_core-2.46.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b2f69dec1725e79a012d920df1707de5caf7ed5e08f3be4435e25803efc47458"}, + {file = "pydantic_core-2.46.4-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:8d0820e8192167f80d88d64038e609c31452eeca865b4e1d9950a27a4609b00b"}, + {file = "pydantic_core-2.46.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fbdb89b3e1c94a30cc5edfce477c6e6a5dc4d8f84665b455c27582f211a1c72c"}, + {file = "pydantic_core-2.46.4-cp312-cp312-win32.whl", hash = "sha256:9aa768456404a8bf48a4406685ac2bec8e72b62c69313734fa3b73cf33b3a894"}, + {file = "pydantic_core-2.46.4-cp312-cp312-win_amd64.whl", hash = "sha256:e9c26f834c65f5752f3f06cb08cb86a913ceb7274d0db6e267808a708b46bc89"}, + {file = "pydantic_core-2.46.4-cp312-cp312-win_arm64.whl", hash = "sha256:4fc73cb559bdb54b1134a706a2802a4cddd27a0633f5abb7e53056268751ac6a"}, + {file = "pydantic_core-2.46.4-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:5d5902252db0d3cedf8d4a1bc68f70eeb430f7e4c7104c8c476753519b423008"}, + {file = "pydantic_core-2.46.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:c94f0688e7b8d0a67abf40e57a7eaaecd17cc9586706a31b76c031f63df052b4"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f027324c56cd5406ca49c124b0db10e56c69064fec039acc571c29020cc87c76"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e739fee756ba1010f8bcccb534252e85a35fe45ae92c295a06059ce58b74ccd3"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9d56801be94b86a9da183e5f3766e6310752b99ff647e38b09a9500d88e46e76"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2412e734dcb48da14d4e4006b82b46b74f2518b8a26ee7e58c6844a6cd6d03c4"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9551187363ffc0de2a00b2e47c25aeaeb1020b69b668762966df15fc5659dd5a"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_31_riscv64.whl", hash = "sha256:0186750b482eefa11d7f435892b09c5c606193ef3375bcf94aa00ae6bfb66262"}, + {file = "pydantic_core-2.46.4-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5855698a4856556d86e8e6cd8434bc3ac0314ee8e12089ae0e143f64c6256e4e"}, + {file = "pydantic_core-2.46.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:cbaf13819775b7f769bf4a1f066cb6df7a28d4480081a589828ef190226881cd"}, + {file = "pydantic_core-2.46.4-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:633147d34cf4550417f12e2b1a0383973bdf5cdfde212cb09e9a581cf10820be"}, + {file = "pydantic_core-2.46.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:82cf5301172168103724d49a1444d3378cb20cdee30b116a1bd6031236298a5d"}, + {file = "pydantic_core-2.46.4-cp313-cp313-win32.whl", hash = "sha256:9fa8ae11da9e2b3126c6426f147e0fba88d96d65921799bb30c6abd1cb2c97fb"}, + {file = "pydantic_core-2.46.4-cp313-cp313-win_amd64.whl", hash = "sha256:6b3ace8194b0e5204818c92802dcdca7fc6d88aabbb799d7c795540d9cd6d292"}, + {file = "pydantic_core-2.46.4-cp313-cp313-win_arm64.whl", hash = "sha256:184c081504d17f1c1066e430e117142b2c77d9448a97f7b65c6ac9fd9aee238d"}, + {file = "pydantic_core-2.46.4-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:428e04521a40150c85216fc8b85e8d39fece235a9cf5e383761238c7fa9b96fb"}, + {file = "pydantic_core-2.46.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:23ace664830ee0bfe014a0c7bc248b1f7f25ed7ad103852c317624a1083af462"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce5c1d2a8b27468f433ca974829c44060b8097eedc39933e3c206a90ee49c4a9"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7283d57845ecf5a163403eb0702dfc220cc4fbdd18919cb5ccea4f95ee1cdab4"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8daafc69c93ee8a0204506a3b6b30f586ef54028f52aeeeb5c4cfc5184fd5914"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd2213145bcc2ba85884d0ac63d222fece9209678f77b9b4d76f054c561adb28"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7a5f930472650a82629163023e630d160863fce524c616f4e5186e5de9d9a49b"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_31_riscv64.whl", hash = "sha256:c1b3f518abeca3aa13c712fd202306e145abf59a18b094a6bafb2d2bbf59192c"}, + {file = "pydantic_core-2.46.4-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1a7dd0b3ee80d90150e3495a3a13ac34dbcbfd4f012996a6a1d8900e91b5c0fb"}, + {file = "pydantic_core-2.46.4-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:3fb702cd90b0446a3a1c5e470bfa0dd23c0233b676a9099ddcc964fa6ca13898"}, + {file = "pydantic_core-2.46.4-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:b8458003118a712e66286df6a707db01c52c0f52f7db8e4a38f0da1d3b94fc4e"}, + {file = "pydantic_core-2.46.4-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:372429a130e469c9cd698925ce5fc50940b7a1336b0d82038e63d5bbc4edc519"}, + {file = "pydantic_core-2.46.4-cp314-cp314-win32.whl", hash = "sha256:85bb3611ff1802f3ee7fdd7dbff26b56f343fb432d57a4728fdd49b6ef35e2f4"}, + {file = "pydantic_core-2.46.4-cp314-cp314-win_amd64.whl", hash = "sha256:811ff8e9c313ab425368bcbb36e5c4ebd7108c2bbf4e4089cfbb0b01eff63fac"}, + {file = "pydantic_core-2.46.4-cp314-cp314-win_arm64.whl", hash = "sha256:bfec22eab3c8cc2ceec0248aec886624116dc079afa027ecc8ad4a7e62010f8a"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:af8244b2bef6aaad6d92cda81372de7f8c8d36c9f0c3ea36e827c60e7d9467a0"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:5a4330cdbc57162e4b3aa303f588ba752257694c9c9be3e7ebb11b4aca659b5d"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29c61fc04a3d840155ff08e475a04809278972fe6aef51e2720554e96367e34b"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c50f2528cf200c5eed56faf3f4e22fcd5f38c157a8b78576e6ba3168ec35f000"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0cbe8b01f948de4286c74cdd6c667aceb38f5c1e26f0693b3983d9d74887c65e"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:617d7e2ca7dcb8c5cf6bcb8c59b8832c94b36196bbf1cbd1bfb56ed341905edd"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7027560ee92211647d0d34e3f7cd6f50da56399d26a9c8ad0da286d3869a53f3"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_31_riscv64.whl", hash = "sha256:f99626688942fb746e545232e7726926f3be91b5975f8b55327665fafda991c7"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:fc3e9034a63de20e15e8ade85358bc6efc614008cab72898b4b4952bea0509ff"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:97e7cf2be5c77b7d1a9713a05605d49460d02c6078d38d8bef3cbe323c548424"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:3bf92c5d0e00fefaab325a4d27828fe6b6e2a21848686b5b60d2d9eeb09d76c6"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:3ecbc122d18468d06ca279dc26a8c2e2d5acb10943bb35e36ae92096dc3b5565"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-win32.whl", hash = "sha256:e846ae7835bf0703ae43f534ab79a867146dadd59dc9ca5c8b53d5c8f7c9ef02"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-win_amd64.whl", hash = "sha256:2108ba5c1c1eca18030634489dc544844144ee36357f2f9f780b93e7ddbb44b5"}, + {file = "pydantic_core-2.46.4-cp314-cp314t-win_arm64.whl", hash = "sha256:4fcbe087dbc2068af7eda3aa87634eba216dbda64d1ae73c8684b621d33f6596"}, + {file = "pydantic_core-2.46.4-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:fd8b3d9fd264be37976686c7f65cd52a83f5e84f4bfd2adf9c1d469676bbb6ae"}, + {file = "pydantic_core-2.46.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9f444c499b3eefd3a92e348059471ea0c3a6e303d9c1cec09fa748fd9f895201"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3447661d99f75a3683a4cf5c87da72f2161964611864dbbeac7fbb118bb4bfc0"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8b9bab013d1c7a79d3501ff86d0bc9c31bf587db4551677b96bec07df78c6b15"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d995260fdf4e1db774581b4900e0f832abe3c7c84996726bbc161b19c8f29e76"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f13a646d65d09fbf1bc6b3a9635d30095c8e7e5cc419ff35ecc563c5fd04cd49"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:432c179df7874eeb73307aad2df0755e1ae0efa61ff0ea89b93e194411ae3928"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_31_riscv64.whl", hash = "sha256:e68b7a074f65a2fd746c52a7ce6142ab7006074ac269ace0c25cd8ba171f8066"}, + {file = "pydantic_core-2.46.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4a05d69cba51d852c5c3e92758653245a50c0b646ced0cf05bd793ed592839d6"}, + {file = "pydantic_core-2.46.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:228ee9bae8bef5b1e97ec58302f80357c37199e0d0a99174e138d28e6957b9d9"}, + {file = "pydantic_core-2.46.4-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:10e17cbb10a330363733efc4d7c4d0dd827ac0909b8f6a6542298fed1ea62f29"}, + {file = "pydantic_core-2.46.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:91a06d2e259ecfbd8c901d70c3c507900458498142b3026a296b7de4d1322cc9"}, + {file = "pydantic_core-2.46.4-cp39-cp39-win32.whl", hash = "sha256:d80ee3d731373b24cebbc10d689ca4ee1875caf0d5703a245db18efd4dd37fc1"}, + {file = "pydantic_core-2.46.4-cp39-cp39-win_amd64.whl", hash = "sha256:3be77f45df024d789a672ae34f8b06fb346c4f9f46ea714956660ea4862e89ac"}, + {file = "pydantic_core-2.46.4-graalpy311-graalpy242_311_native-macosx_10_12_x86_64.whl", hash = "sha256:14d4edf427bdcf950a8a02d7cb44a08614388dd6e1bdcbf4f67504fa7887da9c"}, + {file = "pydantic_core-2.46.4-graalpy311-graalpy242_311_native-macosx_11_0_arm64.whl", hash = "sha256:0ce40cd7b21210e99342afafbd4d0f76d784eb5b1d60f3bdc566be4983c6c73b"}, + {file = "pydantic_core-2.46.4-graalpy311-graalpy242_311_native-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:90884113d8b48f760e9587002789ddd741e76ab9f89518cd1e43b1f1a52ec44b"}, + {file = "pydantic_core-2.46.4-graalpy311-graalpy242_311_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:66ce7632c22d837c95301830e111ad0128a32b8207533b60896a96c4915192ea"}, + {file = "pydantic_core-2.46.4-graalpy312-graalpy250_312_native-macosx_10_12_x86_64.whl", hash = "sha256:1d8ba486450b14f3b1d63bc521d410ec7565e52f887b9fb671791886436a42f7"}, + {file = "pydantic_core-2.46.4-graalpy312-graalpy250_312_native-macosx_11_0_arm64.whl", hash = "sha256:3009f12e4e90b7f88b4f9adb1b0c4a3d58fe7820f3238c190047209d148026df"}, + {file = "pydantic_core-2.46.4-graalpy312-graalpy250_312_native-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ad785e92e6dc634c21555edc8bd6b64957ab844541bcb96a1366c202951ae526"}, + {file = "pydantic_core-2.46.4-graalpy312-graalpy250_312_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00c603d540afdd6b80eb39f078f33ebd46211f02f33e34a32d9f053bba711de0"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:0c563b08bca408dc7f65f700633d8442fffb2421fc47b8101377e9fd65051ff0"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:db06ffe51636ffe9ca531fe9023dd64bdd794be8754cb5df57c5498ae5b518a7"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:133878133d271ade3d41d1bfb2a45ec38dbdbda40bc065921c6b04e4630127e2"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:9bc519fbf2b7578398853d815009ae5e4d4603d12f4e3f91da8c06852d3da3e9"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:c7a7bd4e39e8e4c12c39cd480356842b6a8a06e41b23a55a5e3e191718838ddf"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:d396ec2b979760aaf3218e76c24e65bd0aca24983298653b3a9d7a45f9e47b30"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:86e1a4418c6cd97d60c95c71164158eaf7324fae7b0923264016baa993eba6fc"}, + {file = "pydantic_core-2.46.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:d51026d73fcfd93610abc7b27789c26b313920fcfb20e27462d74a7f8b06e983"}, + {file = "pydantic_core-2.46.4.tar.gz", hash = "sha256:62f875393d7f270851f20523dd2e29f082bcc82292d66db2b64ea71f64b6e1c1"}, +] + +[package.dependencies] +typing-extensions = ">=4.14.1" + [[package]] name = "pyflakes" version = "3.4.0" @@ -4867,6 +5031,20 @@ files = [ {file = "typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466"}, ] +[[package]] +name = "typing-inspection" +version = "0.4.2" +description = "Runtime typing introspection tools" +optional = false +python-versions = ">=3.9" +files = [ + {file = "typing_inspection-0.4.2-py3-none-any.whl", hash = "sha256:4ed1cacbdc298c220f1bd249ed5287caa16f34d44ef4e9c3d0cbad5b521545e7"}, + {file = "typing_inspection-0.4.2.tar.gz", hash = "sha256:ba561c48a67c5958007083d386c3295464928b01faa735ab8547c5692e87f464"}, +] + +[package.dependencies] +typing-extensions = ">=4.12.0" + [[package]] name = "tzdata" version = "2025.3" @@ -5270,4 +5448,4 @@ thot = ["sil-thot"] [metadata] lock-version = "2.0" python-versions = ">=3.10,<3.14" -content-hash = "3015d427d7e11c94f8e11cdf6970930e2db564428736cd38fb3bd7513c78f947" +content-hash = "f428c5da552062e4c77ec54fd39765d37a43bd13110dfc6a5f00880e4dcb076c" diff --git a/pyproject.toml b/pyproject.toml index 77dc1d9b..6027a0d5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -60,6 +60,7 @@ sortedcontainers = "^2.4.0" networkx = "^3" charset-normalizer = "^2.1.1" urllib3 = "<2" +pydantic = "^2.13.4" sentencepiece = "^0.2.0" sil-thot = "^3.5.0"