mostlyai-mock 0.1.6__py3-none-any.whl → 0.1.7__py3-none-any.whl

mostlyai/mock/__init__.py

@@ -15,4 +15,4 @@
 from mostlyai.mock.core import sample
 
 __all__ = ["sample"]
-__version__ = "0.1.6"  # Do not set this manually. Use poetry version [params].
+__version__ = "0.1.7"  # Do not set this manually. Use poetry version [params].

mostlyai/mock/core.py

@@ -737,7 +737,7 @@ def _build_execution_plan(config: MockConfig) -> list[str]:
 def sample(
     *,
     tables: dict[str, dict],
-    sample_size: int | dict[str, int] = 10,
+    sample_size: int | dict[str, int] = 4,
     existing_data: dict[str, pd.DataFrame] | None = None,
     model: str = "openai/gpt-4.1-nano",
     api_key: str | None = None,
@@ -748,12 +748,20 @@ def sample(
     """
     Generate mock data from scratch or enrich existing data by prompting an LLM.
 
+    While faker and numpy are useful to create fake data, this utility is unique as it allows
+    the creation of coherent, realistic multi-table tabular mock data
+    or the enrichment of existing datasets with new, context-aware columns.
+
+    It is particularly useful for quickly simulating production-like datasets for testing or prototyping purposes.
+    It is advised to limit mocking to small datasets for performance reasons (rows * cols < 100).
+    It might take a couple of minutes for bigger datasets.
+
     Args:
         tables (dict[str, dict]): The table specifications to generate mock data for. See examples for usage.
         sample_size (int | dict[str, int]): The number of rows to generate for each subject table.
             If a single integer is provided, the same number of rows will be generated for each subject table.
             If a dictionary is provided, the number of rows to generate for each subject table can be specified individually.
-            Default is 10. Ignored if existing_data is provided.
+            Default is 4. Ignored if existing_data is provided.
             If a table has a foreign key, the sample size is determined by the corresponding foreign key prompt. If nothing specified, a few rows per parent record are generated.
         existing_data (dict[str, pd.DataFrame] | None): Existing data to augment. If provided, the sample_size argument is ignored.
             Default is None.

{mostlyai_mock-0.1.6.dist-info → mostlyai_mock-0.1.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-mock
-Version: 0.1.6
+Version: 0.1.7
 Summary: LLM-generated Mock Data
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-mock
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-mock

mostlyai_mock-0.1.7.dist-info/RECORD

@@ -0,0 +1,8 @@
+mostlyai/mock/__init__.py,sha256=Cmo4Ko8-X41gSewcEpNTTvw7bpRUrtn6B5Cmnwric-Q,714
+mostlyai/mock/core.py,sha256=L-PbOTSIR1cfBeMZL8-v5k7VhxBfKAoyw230soBwQWc,42754
+mostlyai/mock/mcp_server.py,sha256=kWMIjKCwnvYfjY8B2IdP4JNs8ik_8jA6ISCDqrG9utc,2137
+mostlyai_mock-0.1.7.dist-info/METADATA,sha256=6tLpoqLx-LOI-Cr_O_xWm4LI5PBfa4nt1FkrqdNIpQA,13918
+mostlyai_mock-0.1.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mostlyai_mock-0.1.7.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
+mostlyai_mock-0.1.7.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mostlyai_mock-0.1.7.dist-info/RECORD,,

mostlyai_mock-0.1.6.dist-info/RECORD

@@ -1,8 +0,0 @@
-mostlyai/mock/__init__.py,sha256=8UddMHmwpfwSb7ChuVNvIaWNLTlWkN0Cxh63CskmtBw,714
-mostlyai/mock/core.py,sha256=NFfyucqjT3iC9lqfu4dPmRnYizxtfFH1Tf3KHRRxHvg,42242
-mostlyai/mock/mcp_server.py,sha256=kWMIjKCwnvYfjY8B2IdP4JNs8ik_8jA6ISCDqrG9utc,2137
-mostlyai_mock-0.1.6.dist-info/METADATA,sha256=RMYEgGG4P3WfhavNC_4ph6dTCtumqQ3uA-swot9WKyc,13918
-mostlyai_mock-0.1.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mostlyai_mock-0.1.6.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
-mostlyai_mock-0.1.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mostlyai_mock-0.1.6.dist-info/RECORD,,