scorebook 0.0.10__tar.gz → 0.0.12__tar.gz

{scorebook-0.0.10 → scorebook-0.0.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scorebook
-Version: 0.0.10
+Version: 0.0.12
 Summary: A Python project for LLM evaluation.
 License-File: LICENSE
 Author: Euan Campbell
@@ -23,6 +23,7 @@ Requires-Dist: datasets (>=3.6.0)
 Requires-Dist: fsspec[gcs] ; extra == "vertex"
 Requires-Dist: google-cloud-storage ; extra == "vertex"
 Requires-Dist: google-genai ; extra == "vertex"
+Requires-Dist: ipywidgets (>=8.0.0)
 Requires-Dist: notebook (>=7.4.5,<8.0.0)
 Requires-Dist: notebook ; extra == "examples"
 Requires-Dist: openai ; extra == "openai"
@@ -36,7 +37,7 @@ Requires-Dist: torch ; extra == "examples"
 Requires-Dist: torchaudio ; extra == "examples"
 Requires-Dist: torchvision ; extra == "examples"
 Requires-Dist: transformers ; extra == "examples"
-Requires-Dist: trismik (>=1.0.1,<2.0.0)
+Requires-Dist: trismik (==1.0.1)
 Description-Content-Type: text/markdown
 
 # Scorebook

{scorebook-0.0.10 → scorebook-0.0.12}/pyproject.toml

@@ -11,21 +11,23 @@ requires-python = ">=3.9, <3.14"
 dependencies = [
     "datasets>=3.6.0",
     "notebook (>=7.4.5,<8.0.0)",
-    "trismik (>=1.0.1, <2.0.0)",
+    "trismik==1.0.1",
+    "ipywidgets>=8.0.0",
 ]
 
 [project.scripts]
 scorebook = "scorebook.cli.main:main"
 
 [tool.poetry]
-version = "0.0.10"  # base version
+version = "0.0.12"  # base version
 packages = [{ include = "scorebook", from = "src" }]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<3.14"
 datasets = ">=3.6.0"
 notebook = ">=7.4.5,<8.0.0"
-trismik = ">=1.0.1,<2.0.0"
+trismik = "1.0.1"
+ipywidgets = ">=8.0.0"
 
 # Optional dependencies
 openai = {version = "*", optional = true}
@@ -68,6 +70,7 @@ toml = "^0.10.2"
 types-pyyaml = "^6.0.12.20250822"
 unasync = {version = "^0.5.0", python = ">=3.9,<4"}
 tomlkit = "^0.13.2"
+detect-secrets = "^1.5.0"
 
 [project.optional-dependencies]
 openai = ["openai", "python-dotenv"]
@@ -83,6 +86,10 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.pytest.ini_options]
 asyncio_default_fixture_loop_scope = "class"
+markers = [
+    "unit: Unit tests that use mocks and don't require external dependencies",
+    "integration: Integration tests that may require network access or external services",
+]
 
 [tool.black]
 line-length = 100
@@ -112,16 +119,22 @@ install_types = true
 [tool.flake8] # note that this depends on Flake8-pyproject
 ignore = ["D202", "W503", "W504"]
 
-[tool.unasync]
 [[tool.unasync.rules]]
 fromdir = "src/scorebook/evaluate/_async/"
 todir = "src/scorebook/evaluate/_sync/"
+replacements."scorebook.score._async.score_async" = "scorebook.score._sync.score"
+replacements."scorebook.score._async" = "scorebook.score._sync"
+replacements.evaluate_async = "evaluate"
+replacements."Asynchronous evaluation complete" = "Synchronous evaluation complete"
+replacements."    run_results = asyncio.gather(*[worker(run) for run in runs])" = "    run_results = [worker(run) for run in runs]"
+replacements.async_nullcontext = "nullcontext"
+replacements.create_trismik_async_client = "create_trismik_sync_client"
+replacements.score_async = "score"
 
-
-# Custom replacements beyond default async/await transformations
-[tool.unasync.rules.replacements]
-"evaluate_async" = "evaluate"
-"Asynchronous evaluation complete" = "Synchronous evaluation complete"
-"    run_results = asyncio.gather(*[worker(run) for run in runs])" = "    run_results = [worker(run) for run in runs]"
-"async_nullcontext" = "nullcontext"
-"create_trismik_async_client" = "create_trismik_sync_client"
+[[tool.unasync.rules]]
+fromdir = "src/scorebook/score/_async/"
+todir = "src/scorebook/score/_sync/"
+replacements.score_async = "score"
+replacements."Async scoring complete" = "Scoring complete"
+replacements.calculate_metric_scores_async = "calculate_metric_scores"
+replacements.upload_result_async = "upload_result"

{scorebook-0.0.10 → scorebook-0.0.12}/src/scorebook/__init__.py

@@ -9,18 +9,25 @@ import importlib.metadata
 # get version from pyproject.toml
 __version__ = importlib.metadata.version(__package__ or __name__)
 
-from scorebook.eval_dataset import EvalDataset
+from scorebook.eval_datasets import EvalDataset
 from scorebook.evaluate import evaluate, evaluate_async
 from scorebook.inference.inference_pipeline import InferencePipeline
-from scorebook.trismik.credentials import login, whoami
-from scorebook.utils.build_prompt import build_prompt
+from scorebook.score import score, score_async
+from scorebook.trismik.credentials import login, logout, whoami
+from scorebook.trismik.upload_results import upload_result, upload_result_async
+from scorebook.utils.render_template import render_template
 
 __all__ = [
     "EvalDataset",
     "evaluate",
     "evaluate_async",
-    "build_prompt",
+    "score",
+    "score_async",
+    "render_template",
     "login",
+    "logout",
     "whoami",
     "InferencePipeline",
+    "upload_result",
+    "upload_result_async",
 ]

scorebook-0.0.12/src/scorebook/eval_datasets/__init__.py

@@ -0,0 +1,5 @@
+"""Dataset utilities for scorebook."""
+
+from scorebook.eval_datasets.eval_dataset import EvalDataset
+
+__all__ = ["EvalDataset"]