mostlyai-mock 0.1.14__py3-none-any.whl → 0.1.16__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__ = "0.1.16"  # 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(
@@ -647,6 +645,24 @@ async def _worker(
                 "stream": True,
             }
 
+            # support for openai reasoning models
+            model_only = llm_config.model.split("/")[-1] if "/" in llm_config.model else llm_config.model
+            reasoning_effort = (
+                "low"
+                if (model_only.startswith("o") and (model_only[1:].isdigit() or model_only[1:].split("-")[0].isdigit()))
+                else "minimal"
+                if (
+                    model_only.startswith("gpt-")
+                    and model_only.split("-")[1].isdigit()
+                    and int(model_only.split("-")[1]) >= 5
+                )
+                else None
+            )
+
+            if reasoning_effort:
+                litellm_kwargs.pop("top_p")
+                litellm_kwargs["reasoning_effort"] = reasoning_effort
+
             # construct messages
             system_prompt = _create_system_prompt(llm_output_format)
             user_prompt = _create_table_prompt(
@@ -715,7 +731,7 @@ 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:
@@ -1118,7 +1134,7 @@ async def _sample_common(
     tables: dict[str, dict],
     sample_size: int | dict[str, int] = 4,
     existing_data: dict[str, pd.DataFrame] | None = None,
-    model: str = "openai/gpt-4.1-nano",
+    model: str = "openai/gpt-5-nano",
     api_key: str | None = None,
     temperature: float = 1.0,
     top_p: float = 0.95,
@@ -1166,7 +1182,7 @@ def sample(
     tables: dict[str, dict],
     sample_size: int | dict[str, int] = 4,
     existing_data: dict[str, pd.DataFrame] | None = None,
-    model: str = "openai/gpt-4.1-nano",
+    model: str = "openai/gpt-5-nano",
     api_key: str | None = None,
     temperature: float = 1.0,
     top_p: float = 0.95,
@@ -1181,11 +1197,12 @@ 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.
@@ -1195,9 +1212,9 @@ def sample(
             Default is None.
         model (str): The LiteLLM chat completion model to be used.
             Examples include:
-            - `openai/gpt-4.1-nano` (default; fast, and smart)
-            - `openai/gpt-4.1-mini` (slower, but smarter)
-            - `openai/gpt-4.1` (slowest, but smartest)
+            - `openai/gpt-5-nano` (default; fast, and smart)
+            - `openai/gpt-5-mini` (slower, but smarter)
+            - `openai/gpt-5` (slowest, but smartest)
             - `gemini/gemini-2.0-flash`
             - `gemini/gemini-2.5-flash-preview-04-17`
             - 'groq/gemma2-9b-it`
@@ -1235,7 +1252,7 @@ def sample(
             },
         }
     }
-    df = mock.sample(tables=tables, sample_size=10, model="openai/gpt-4.1-nano")
+    df = mock.sample(tables=tables, sample_size=10, model="openai/gpt-5-nano")
     ```
 
     Example of generating mock data for multiple tables (with PK/FK relationships):
@@ -1298,7 +1315,7 @@ def sample(
             ],
         },
     }
-    data = mock.sample(tables=tables, sample_size=2, model="openai/gpt-4.1")
+    data = mock.sample(tables=tables, sample_size=2, model="openai/gpt-5")
     df_customers = data["customers"]
     df_warehouses = data["warehouses"]
     df_orders = data["orders"]
@@ -1327,7 +1344,7 @@ def sample(
     enriched_df = mock.sample(
         tables=tables,
         existing_data={"patients": existing_df},
-        model="openai/gpt-4.1-nano"
+        model="openai/gpt-5-nano"
     )
     enriched_df
     ```
@@ -1382,7 +1399,7 @@ def sample(
             "customers": existing_customers,
             "orders": existing_orders,
         },
-        model="openai/gpt-4.1-nano"
+        model="openai/gpt-5-nano"
     )
     df_customers = data["customers"]
     df_orders = data["orders"]
@@ -1414,7 +1431,7 @@ async def _asample(
     tables: dict[str, dict],
     sample_size: int | dict[str, int] = 4,
     existing_data: dict[str, pd.DataFrame] | None = None,
-    model: str = "openai/gpt-4.1-nano",
+    model: str = "openai/gpt-5-nano",
     api_key: str | None = None,
     temperature: float = 1.0,
     top_p: float = 0.95,

mostlyai/mock/mcp_server.py

@@ -56,7 +56,7 @@ async def mock_data(
     *,
     tables: dict[str, dict],
     sample_size: int,
-    model: str = "openai/gpt-4.1-nano",
+    model: str = "openai/gpt-5-nano",
     api_key: str | None = None,
     temperature: float = 1.0,
     top_p: float = 0.95,

{mostlyai_mock-0.1.14.dist-info → mostlyai_mock-0.1.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-mock
-Version: 0.1.14
+Version: 0.1.16
 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 🔮
@@ -92,7 +95,7 @@ tables = {
 df = mock.sample(
     tables=tables,   # provide table and column definitions
     sample_size=10,  # generate 10 records
-    model="openai/gpt-4.1-nano",  # select the LLM model (optional)
+    model="openai/gpt-5-nano",  # select the LLM model (optional)
 )
 print(df)
 #   nationality                 name  gender  age date_of_birth        checkin_time is_vip  price_per_night  room_number
@@ -173,7 +176,7 @@ tables = {
 data = mock.sample(
     tables=tables,
     sample_size=2,
-    model="openai/gpt-4.1",
+    model="openai/gpt-5",
     n_workers=1,
 )
 print(data["customers"])
@@ -229,7 +232,7 @@ tables = {
         ],
     }
 }
-df = mock.sample(tables=tables, sample_size=10, model="openai/gpt-4.1", n_workers=1)
+df = mock.sample(tables=tables, sample_size=10, model="openai/gpt-5", n_workers=1)
 print(df)
 #   employee_id              name boss_id                   role
 # 0        B0-1      Patricia Lee    <NA>              President
@@ -270,7 +273,7 @@ existing_guests = pd.DataFrame({
 df = mock.sample(
     tables=tables,
     existing_data={"guests": existing_guests},
-    model="openai/gpt-4.1-nano"
+    model="openai/gpt-5-nano"
 )
 print(df)
 #   guest_id           name nationality  gender  age  room_number is_vip
@@ -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-0.1.16.dist-info/RECORD

@@ -0,0 +1,8 @@
+mostlyai/mock/__init__.py,sha256=XEezyGjkXQBReW_ORi83H2WEVhLolDDLbGjxA2g2yEs,715
+mostlyai/mock/core.py,sha256=FTF0BfJowxNHm_L0RpTk6BhS1mXzvjELP-3Z96aFVMQ,62454
+mostlyai/mock/mcp_server.py,sha256=uDLg0SeMPV2VZhXviM-F769W0xlmhGwlmQiQhY0Q-Ik,2365
+mostlyai_mock-0.1.16.dist-info/METADATA,sha256=CT6lcz2cAq5W-u3VjQLr_Dg8VbuEtU-JlvsXg5OsKTk,14297
+mostlyai_mock-0.1.16.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mostlyai_mock-0.1.16.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
+mostlyai_mock-0.1.16.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mostlyai_mock-0.1.16.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,,