mostlyai-engine 1.0.1__tar.gz → 1.0.3__tar.gz

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: mostlyai-engine
-Version: 1.0.1
-Summary: Synthetic Data - Engine
-Project-URL: Homepage, https://github.com/mostly-ai/mostlyai-engine
-Project-URL: Documentation, https://mostly-ai.github.io/mostlyai-engine/
-Project-URL: Source, https://github.com/mostly-ai/mostlyai-engine
+Version: 1.0.3
+Summary: Synthetic Data Engine
+Project-URL: homepage, https://github.com/mostly-ai/mostlyai-engine
+Project-URL: repository, https://github.com/mostly-ai/mostlyai-engine
+Project-URL: documentation, https://mostly-ai.github.io/mostlyai-engine/
 Author-email: MOSTLY AI <dev@mostly.ai>
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -17,9 +17,13 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Typing :: Typed
-Requires-Python: <3.13,>=3.10
+Requires-Python: >=3.10
 Requires-Dist: accelerate<0.32,>=0.31.0
 Requires-Dist: datasets<3,>=2.20.0
 Requires-Dist: formatron<0.5,>=0.4.11
@@ -34,14 +38,14 @@ Requires-Dist: pyarrow>=16.0.0
 Requires-Dist: rich<14,>=13.9.4
 Requires-Dist: setuptools<76,>=75.0.0
 Requires-Dist: tokenizers<0.21,>=0.20.1
-Requires-Dist: torch==2.5.1; sys_platform == 'darwin'
+Requires-Dist: torch>=2.5.1; sys_platform == 'darwin'
 Requires-Dist: transformers<5,>=4.45.2
 Provides-Extra: cpu
-Requires-Dist: torch==2.5.1+cpu; (sys_platform != 'darwin') and extra == 'cpu'
-Requires-Dist: torch==2.5.1; (sys_platform == 'darwin') and extra == 'cpu'
+Requires-Dist: torch==2.5.1+cpu; (sys_platform == 'linux') and extra == 'cpu'
+Requires-Dist: torch>=2.5.1; (sys_platform != 'linux') and extra == 'cpu'
 Provides-Extra: gpu
 Requires-Dist: bitsandbytes<0.44,>=0.43.3; extra == 'gpu'
-Requires-Dist: torch==2.5.1; extra == 'gpu'
+Requires-Dist: torch>=2.5.1; extra == 'gpu'
 Requires-Dist: vllm<0.7,>=0.6.4; extra == 'gpu'
 Description-Content-Type: text/markdown
 
@@ -77,7 +81,7 @@ pip install -U mostlyai-engine
 
 or alternatively for a GPU setup:
 ```bash
-pip install -U mostlyai-engine[gpu]
+pip install -U 'mostlyai-engine[gpu]'
 ```
 
 
@@ -90,8 +94,9 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+# set up workspace and default logging
 ws = Path("ws-tabular-flat")
+engine.init_logging()
 
 # load original data
 url = "https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/census"
@@ -120,8 +125,11 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+engine.init_logging()
+
+# set up workspace and default logging
 ws = Path("ws-tabular-sequential")
+engine.init_logging()
 
 # load original data
 url = "https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/baseball"
@@ -154,8 +162,9 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+# init workspace and logging
 ws = Path("ws-language-flat")
+engine.init_logging()
 
 # load original data
 trn_df = pd.read_parquet("https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/headlines/headlines.parquet")

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/README.md

@@ -30,7 +30,7 @@ pip install -U mostlyai-engine
 
 or alternatively for a GPU setup:
 ```bash
-pip install -U mostlyai-engine[gpu]
+pip install -U 'mostlyai-engine[gpu]'
 ```
 
 
@@ -43,8 +43,9 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+# set up workspace and default logging
 ws = Path("ws-tabular-flat")
+engine.init_logging()
 
 # load original data
 url = "https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/census"
@@ -73,8 +74,11 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+engine.init_logging()
+
+# set up workspace and default logging
 ws = Path("ws-tabular-sequential")
+engine.init_logging()
 
 # load original data
 url = "https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/baseball"
@@ -107,8 +111,9 @@ from pathlib import Path
 import pandas as pd
 from mostlyai import engine
 
-# set up workspace
+# init workspace and logging
 ws = Path("ws-language-flat")
+engine.init_logging()
 
 # load original data
 trn_df = pd.read_parquet("https://github.com/mostly-ai/public-demo-data/raw/refs/heads/dev/headlines/headlines.parquet")

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/mostlyai/engine/__init__.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 import warnings
 
+from mostlyai.engine.logging import init_logging
 from mostlyai.engine.splitting import split
 from mostlyai.engine.analysis import analyze
 from mostlyai.engine.training import train
@@ -20,8 +21,8 @@ from mostlyai.engine.encoding import encode
 from mostlyai.engine.generation import generate
 
 
-__all__ = ["split", "analyze", "encode", "train", "generate"]
-__version__ = "1.0.1"
+__all__ = ["split", "analyze", "encode", "train", "generate", "init_logging"]
+__version__ = "1.0.3"
 
 # suppress specific warning related to os.fork() in multi-threaded processes
 warnings.filterwarnings("ignore", category=DeprecationWarning, message=".*multi-threaded.*fork.*")

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/mostlyai/engine/_language/generation.py

@@ -210,7 +210,7 @@ def generate(
             False  # needed for gated hf models that are not sharded, otherwise GatedRepoError in vLLM
         )
         # set the default env var so that we don't pass it explicitly to vLLM
-        os.environ["HF_TOKEN"] = os.getenv("MOSTLY_HUGGING_FACE_TOKEN", "")
+        os.environ["HF_TOKEN"] = os.getenv("MOSTLY_HUGGING_FACE_TOKEN") or os.getenv("HF_TOKEN", "")
 
         is_peft_adapter = (workspace.model_path / "adapter_config.json").exists()
         if is_peft_adapter and device.type == "cuda":

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/mostlyai/engine/_workspace.py

@@ -168,21 +168,6 @@ class Workspace:
         self.generated_data_path = Path(self._ws_path) / Path(*generated_data)
         self.generated_data = make_path_desc(parts=generated_data, fetch_multiple=fetch_part_parquets)
 
-        # Report-related
-        self.report_ctx_data_path = self._ws_path / "report-ctx-data"
-        self.report_ctx_data = make_path_desc(
-            parts=["report-ctx-data"],
-            fetch_multiple=fetch_part_parquets,
-        )
-        self.report_trn_ctx_data = make_path_desc(
-            parts=["report-ctx-data"],
-            fetch_multiple=fetch_part_trn_parquets,
-        )
-        self.report_val_ctx_data = make_path_desc(
-            parts=["report-ctx-data"],
-            fetch_multiple=fetch_part_val_parquets,
-        )
-
 
 def ensure_workspace_dir(workspace_dir: str | Path) -> Path:
     workspace_dir = Path(workspace_dir)

mostlyai_engine-1.0.3/mostlyai/engine/logging.py

@@ -0,0 +1,34 @@
+# Copyright 2025 MOSTLY AI
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import sys
+import logging
+
+_LOG = logging.getLogger(__name__.rsplit(".", 1)[0])  # get the logger with the root module name (mostlyai.engine)
+
+
+def init_logging() -> None:
+    """
+    Initialize the logging configuration. Either log to stdout or to a file.
+    """
+
+    # log to stdout
+    handler = logging.StreamHandler(stream=sys.stdout)
+    handler.setFormatter(logging.Formatter("[%(asctime)s] %(levelname)-7s: %(message)s"))
+    handler.setLevel(logging.INFO)
+
+    if not _LOG.hasHandlers():
+        _LOG.addHandler(handler)
+        _LOG.setLevel(logging.INFO)
+        _LOG.propagate = False

{mostlyai_engine-1.0.1 → mostlyai_engine-1.0.3}/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "mostlyai-engine"
-version = "1.0.1"
-description = "Synthetic Data - Engine"
+version = "1.0.3"
+description = "Synthetic Data Engine"
 authors = [{ name = "MOSTLY AI", email = "dev@mostly.ai" }]
-requires-python = ">=3.10,<3.13"
+requires-python = ">=3.10"
 readme = "README.md"
 license = "Apache-2.0"
 classifiers = [
@@ -14,6 +14,10 @@ classifiers = [
     "Intended Audience :: Financial and Insurance Industry",
     "Intended Audience :: Healthcare Industry",
     "Intended Audience :: Telecommunications Industry",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
     "Topic :: Software Development :: Libraries",
@@ -24,7 +28,6 @@ dependencies = [
     "setuptools>=75.0.0,<76",
     "numpy>=1.26.3,<2",
     "pandas~=2.2.0",
-    "torch==2.5.1; sys_platform == 'darwin'",
     "pyarrow>=16.0.0",
     "joblib>=1.3.0,<2",
     "psutil>=5.9.5,<6",  # upgrade when colab psutil is updated
@@ -37,17 +40,18 @@ dependencies = [
     "formatron>=0.4.11,<0.5",
     "json-repair>=0.30.0,<0.31",
     "rich>=13.9.4,<14",
+    "torch>=2.5.1; sys_platform == 'darwin'",
 ]
 
 [project.optional-dependencies]
 gpu = [
-    "torch==2.5.1",
+    "torch>=2.5.1",
     "bitsandbytes>=0.43.3,<0.44",
     "vllm>=0.6.4,<0.7",
 ]
 cpu = [
-    "torch==2.5.1+cpu; sys_platform != 'darwin'",
-    "torch==2.5.1; sys_platform == 'darwin'"
+    "torch==2.5.1+cpu; sys_platform == 'linux'",
+    "torch>=2.5.1; sys_platform != 'linux'",
 ]
 
 [dependency-groups]
@@ -69,9 +73,9 @@ docs = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/mostly-ai/mostlyai-engine"
-Documentation = "https://mostly-ai.github.io/mostlyai-engine/"
-Source = "https://github.com/mostly-ai/mostlyai-engine"
+homepage = "https://github.com/mostly-ai/mostlyai-engine"
+repository = "https://github.com/mostly-ai/mostlyai-engine"
+documentation = "https://mostly-ai.github.io/mostlyai-engine/"
 
 [tool.uv]
 default-groups = ["test", "dev", "docs"]
@@ -89,7 +93,7 @@ explicit = true
 
 [tool.uv.sources]
 torch = [
-  { index = "pytorch-cpu", extra = "cpu", marker = "sys_platform != 'darwin'" },
+  { index = "pytorch-cpu", extra = "cpu", marker = "sys_platform == 'linux'"},
 ]
 
 [tool.hatch.build.targets.sdist]