mostlyai-mock 0.1.14__py3-none-any.whl → 0.1.15__py3-none-any.whl

mostlyai/mock/__init__.py

@@ -15,4 +15,4 @@
 from mostlyai.mock.core import sample
 
 __all__ = ["sample"]
-__version__ = "0.1.14"  # Do not set this manually. Use poetry version [params].
+__version__ = "0.1.15"  # Do not set this manually. Use poetry version [params].

mostlyai/mock/core.py

@@ -40,10 +40,10 @@ class LLMOutputFormat(str, Enum):
 
 
 class LLMConfig(BaseModel):
-    model: str = "openai/gpt-4.1-nano"
-    api_key: str | None = None
-    temperature: float = 1.0
-    top_p: float = 0.95
+    model: str
+    api_key: str | None
+    temperature: float
+    top_p: float
 
 
 class MockConfig(RootModel[dict[str, "TableConfig"]]):
@@ -270,8 +270,7 @@ async def _sample_table(
 
 
 def _create_system_prompt(llm_output_format: LLMOutputFormat) -> str:
-    return f"""
-You are a specialized data generator designed to create highly realistic, contextually appropriate data based on schema definitions.
+    return f"""You are a specialized data generator designed to create highly realistic, contextually appropriate data based on schema definitions.
 
 Your task is to:
 
@@ -289,8 +288,7 @@ appropriate content. For dates and timestamps, ensure logical chronology. Always
 across tables.
 
 When enriching existing data, carefully analyze the patterns and relationships in the existing columns \
-to generate compatible and realistic values for the missing columns.
-"""
+to generate compatible and realistic values for the missing columns."""
 
 
 def _create_table_prompt(
@@ -715,7 +713,7 @@ async def _worker(
             if do_repeat_task:
                 # allow 10 retries across all workers before propagating the exception to the orchestrator
                 await retry_queue.put(1)
-                if retry_queue.qsize() < 10:
+                if retry_queue.qsize() <= 10:
                     # put task back to the front of the batch queue
                     await batch_queue.put((batch_idx, task))
                 else:
@@ -1181,11 +1179,12 @@ def sample(
     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 is advised to limit mocking to small datasets for performance reasons (rows * cols < 1000).
     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.
+            Note: Avoid using double quotes (`"`) and other special characters in column names.
         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.

{mostlyai_mock-0.1.14.dist-info → mostlyai_mock-0.1.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-mock
-Version: 0.1.14
+Version: 0.1.15
 Summary: Synthetic Mock Data
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-mock
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-mock
@@ -24,13 +24,16 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Typing :: Typed
 Requires-Python: >=3.10
-Requires-Dist: fastmcp<3.0.0,>=2.0.0
 Requires-Dist: litellm>=1.67.0
 Requires-Dist: numpy>=1.26.3
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyarrow>=14.0.0
 Requires-Dist: pydantic<3.0.0,>=2.0.0
 Requires-Dist: tenacity>=9.1.2
+Provides-Extra: litellm-proxy
+Requires-Dist: litellm[proxy]>=1.67.0; extra == 'litellm-proxy'
+Provides-Extra: mcp
+Requires-Dist: fastmcp<3.0.0,>=2.0.0; extra == 'mcp'
 Description-Content-Type: text/markdown
 
 # Synthetic Mock Data 🔮
@@ -285,18 +288,18 @@ This repo comes with MCP Server. It can be easily consumed by any MCP Client by
 
 ```json
 {
-  "mcpServers": {
-      "mostlyai-mock-mcp": {
-          "command": "uvx",
-          "args": ["--from", "mostlyai-mock", "mcp-server"],
-          "env": {
-              "OPENAI_API_KEY": "PROVIDE YOUR KEY",
-              "GEMINI_API_KEY": "PROVIDE YOUR KEY",
-              "GROQ_API_KEY": "PROVIDE YOUR KEY",
-              "ANTHROPIC_API_KEY": "PROVIDE YOUR KEY"
-          }
-      }
-  }
+    "mcpServers": {
+        "mostlyai-mock-mcp": {
+            "command": "uvx",
+            "args": ["--from", "mostlyai-mock[mcp]", "mcp-server"],
+            "env": {
+                "OPENAI_API_KEY": "PROVIDE YOUR KEY",
+                "GEMINI_API_KEY": "PROVIDE YOUR KEY",
+                "GROQ_API_KEY": "PROVIDE YOUR KEY",
+                "ANTHROPIC_API_KEY": "PROVIDE YOUR KEY"
+            }
+        }
+    }
 }
 ```
 
@@ -306,5 +309,5 @@ For example:
 
 Troubleshooting:
 1. If the MCP Client fails to detect the MCP Server, provide the absolute path in the `command` field, for example: `/Users/johnsmith/.local/bin/uvx`
-2. To debug MCP Server issues, you can use MCP Inspector by running: `npx @modelcontextprotocol/inspector -- uvx --from mostlyai-mock mcp-server`
-3. In order to develop locally, modify the configuration by replacing `"command": "uv"` (or use the full path to `uv` if needed) and `"args": ["--directory", "/Users/johnsmith/mostlyai-mock", "run", "mcp-server"]`
+2. To debug MCP Server issues, you can use MCP Inspector by running: `npx @modelcontextprotocol/inspector -- uvx --from mostlyai-mock[mcp] mcp-server`
+3. In order to develop locally, modify the configuration by replacing `"command": "uv"` (or use the full path to `uv` if needed) and `"args": ["--directory", "/Users/johnsmith/mostlyai-mock", "run", "--extra", "mcp", "mcp-server"]`

mostlyai_mock-0.1.15.dist-info/RECORD

@@ -0,0 +1,8 @@
+mostlyai/mock/__init__.py,sha256=uv2DLnOleN6BNMfAMleXJCPcOZvM_tMTRy5njUIKDag,715
+mostlyai/mock/core.py,sha256=JDJ9nVpRR2WochxumSdQS96zak0OV1frkJOwlQsPVBw,61715
+mostlyai/mock/mcp_server.py,sha256=0Vn1jmrdNAvUZSviaaU7Lhn7L7iHFyd8kGFigM0-4s0,2367
+mostlyai_mock-0.1.15.dist-info/METADATA,sha256=OG3NRdCcH2qycRQ5HrzyLtJwtl74lRw5Py1JtqfB2YI,14305
+mostlyai_mock-0.1.15.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mostlyai_mock-0.1.15.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
+mostlyai_mock-0.1.15.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mostlyai_mock-0.1.15.dist-info/RECORD,,

mostlyai_mock-0.1.14.dist-info/RECORD

@@ -1,8 +0,0 @@
-mostlyai/mock/__init__.py,sha256=MLHwi5g6_lAEd8cDEISbVdRWmorOVAQ6IoMm8BsRpqg,715
-mostlyai/mock/core.py,sha256=JdWHix-Pp0s---b_Z3f2ui7J7LSl4_r_gPP0z8UHKY8,61663
-mostlyai/mock/mcp_server.py,sha256=0Vn1jmrdNAvUZSviaaU7Lhn7L7iHFyd8kGFigM0-4s0,2367
-mostlyai_mock-0.1.14.dist-info/METADATA,sha256=PHiUTSEvevYTPVvsMGT-kilTDwaEgIEL0T8Vr56PSiY,14123
-mostlyai_mock-0.1.14.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mostlyai_mock-0.1.14.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
-mostlyai_mock-0.1.14.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mostlyai_mock-0.1.14.dist-info/RECORD,,