mostlyai-mock 0.0.11__py3-none-any.whl → 0.1.0__py3-none-any.whl

mostlyai/mock/__init__.py

@@ -15,4 +15,4 @@
 from mostlyai.mock.core import sample
 
 __all__ = ["sample"]
-__version__ = "0.0.11"  # Do not set this manually. Use poetry version [params].
+__version__ = "0.1.0"  # Do not set this manually. Use poetry version [params].

mostlyai/mock/core.py

@@ -25,7 +25,7 @@ import pandas as pd
 from pydantic import BaseModel, Field, RootModel, create_model, field_validator, model_validator
 from tqdm import tqdm
 
-SYSTEM_PROMPT = f"""
+SYSTEM_PROMPT = """
 You are a specialized synthetic data generator designed to create
 highly realistic, contextually appropriate data based on schema definitions. Your task is to:
 
@@ -264,8 +264,8 @@ def _create_table_prompt(
 
         prompt += f"## Context Table Primary Key: `{primary_keys[fk.referenced_table]}`\n\n"
 
-        prompt += f"## Context Table Data:\n\n"
-        prompt += f"{context_data.to_json(orient='records', indent=2)}\n\n"
+        prompt += "## Context Table Data:\n\n"
+        prompt += f"{context_data.to_json(orient='records', date_format='iso', indent=2)}\n\n"
 
     # add non-context table names, primary keys and data
     if foreign_keys and len(foreign_keys) > 1:
@@ -278,8 +278,10 @@ def _create_table_prompt(
 
             prompt += f"## Non-Context Table Primary Key: `{primary_keys[fk.referenced_table]}`\n\n"
 
-            prompt += f"## Non-Context Table Data:\n\n"
-            prompt += f"{non_context_data[fk.referenced_table].to_json(orient='records', indent=2)}\n\n"
+            prompt += "## Non-Context Table Data:\n\n"
+            prompt += (
+                f"{non_context_data[fk.referenced_table].to_json(orient='records', date_format='iso', indent=2)}\n\n"
+            )
 
     # add instructions
     prompt += "\n## Instructions:\n\n"
@@ -302,8 +304,8 @@ def _create_table_prompt(
             "Don't copy previous rows in the output. "
             "Don't pay attention to the number of previous rows; there might have been more generated than provided.\n\n"
         )
-    prompt += f"Do not use code to generate the data.\n\n"
-    prompt += f"Return the full data as a JSON string.\n"
+    prompt += "Do not use code to generate the data.\n\n"
+    prompt += "Return the full data as a JSON string.\n"
 
     return prompt
 
@@ -384,12 +386,12 @@ def _create_table_rows_generator(
                 for i in range(0, len(data), batch_size):
                     yield data.iloc[i : i + batch_size]
 
-    # ensure model supports response_format and json schema
-    supported_params = litellm.get_supported_openai_params(model=llm_config.model)
-    assert "response_format" in supported_params
-    assert litellm.supports_response_schema(llm_config.model), (
-        "The model does not support structured output / JSON mode."
-    )
+    if not llm_config.model.startswith("litellm_proxy/"):
+        # ensure model supports response_format and json schema (this check does not work with litellm_proxy)
+        supported_params = litellm.get_supported_openai_params(model=llm_config.model) or []
+        assert "response_format" in supported_params and litellm.supports_response_schema(llm_config.model), (
+            "The model does not support structured output / JSON mode."
+        )
 
     # derive context data (if first foreign key is present) and harmonize sample size accordingly
     context_data: pd.DataFrame | None = None
@@ -398,6 +400,7 @@ def _create_table_rows_generator(
         assert generated_data is not None
         assert context_table_name in generated_data
         context_data = generated_data[context_table_name]
+        batch_size = 1  # generate one sequence at a time
         sample_size = len(context_data)
 
     # derive non-context data (if more than one foreign key is present)

mostlyai/mock/mcp_server.py

@@ -2,13 +2,14 @@ import os
 import tempfile
 
 import pandas as pd
-from fastmcp import Context, FastMCP
+from fastmcp import FastMCP
 
 from mostlyai import mock
 
 SAMPLE_MOCK_TOOL_DESCRIPTION = f"""
-This tool is a proxy to the `mostlyai.mock.sample` function.
-It returns a dictionary. The keys are the table names, the values are the Paths to the generated CSV files.
+Generate mock data by prompting an LLM.
+
+This tool is a proxy to the `mostlyai.mock.sample` function, but returns a dictionary of paths to the generated CSV files.
 
 Present the result nicely to the user, in Markdown format. Example:
 
@@ -16,10 +17,7 @@ Mock data can be found under the following paths:
 - `/tmp/tmpl41bwa6n/players.csv`
 - `/tmp/tmpl41bwa6n/seasons.csv`
 
-
-What comes after the `=============================` is the documentation of the `mostlyai.mock.sample` function.
-
-=============================
+== mostlyai.mock.sample DocString ==
 {mock.sample.__doc__}
 """
 
@@ -37,7 +35,7 @@ def _store_locally(data: dict[str, pd.DataFrame]) -> dict[str, str]:
 
 
 @mcp.tool(description=SAMPLE_MOCK_TOOL_DESCRIPTION)
-def sample_mock_data(
+def mock_data(
     *,
     tables: dict[str, dict],
     sample_size: int,
@@ -45,14 +43,7 @@ def sample_mock_data(
     api_key: str | None = None,
     temperature: float = 1.0,
     top_p: float = 0.95,
-    ctx: Context,
 ) -> dict[str, str]:
-    # Notes:
-    # 1. Returning DataFrames directly results in converting them into truncated string.
-    # 2. The logs / progress bars are not propagated to the MCP Client. There is a dedicated API to do that (e.g. `ctx.info(...)`)
-    # 3. MCP Server inherits only selected environment variables (PATH, USER...); one way to pass LLM keys is through client configuration (`mcpServers->env`)
-    # 4. Some MCP Clients, e.g. Cursor, do not like Unions or Optionals in type hints
-    ctx.info(f"Generating mock data for `{len(tables)}` tables")
     data = mock.sample(
         tables=tables,
         sample_size=sample_size,
@@ -62,7 +53,6 @@ def sample_mock_data(
         top_p=top_p,
         return_type="dict",
     )
-    ctx.info(f"Generated mock data for `{len(tables)}` tables")
     locations = _store_locally(data)
     return locations
 

{mostlyai_mock-0.0.11.dist-info → mostlyai_mock-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-mock
-Version: 0.0.11
+Version: 0.1.0
 Summary: Synthetic Mock Data
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-mock
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-mock
@@ -268,4 +268,4 @@ 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": ["--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"]`

mostlyai_mock-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+mostlyai/mock/__init__.py,sha256=ozv-XYJlW9RYYfDXVWDKJxMxqEif6MOC0HXCY3nX0eA,714
+mostlyai/mock/core.py,sha256=g00md01vP-xyI6FKDUB-PCCzOmtpeN8Bm8jXQEwclJA,30130
+mostlyai/mock/mcp_server.py,sha256=Vp0bWzE8wUyA6k4PHLa0TbkuI9s07E48xPrAUgf_5qU,1563
+mostlyai_mock-0.1.0.dist-info/METADATA,sha256=rbHAHWTMQDrcJjio0DT8_sstVaVa7B0NGPMqACFoXUY,12708
+mostlyai_mock-0.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mostlyai_mock-0.1.0.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
+mostlyai_mock-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mostlyai_mock-0.1.0.dist-info/RECORD,,

mostlyai_mock-0.0.11.dist-info/RECORD

@@ -1,8 +0,0 @@
-mostlyai/mock/__init__.py,sha256=fDLeoKXZggBnsgC_lhC7-O_DltAbc-Wea0QL0xgsjtY,715
-mostlyai/mock/core.py,sha256=p5VAsRppzAc4P8FqKEunfQ3cPjImUU2cEc6yqHJVhMg,29884
-mostlyai/mock/mcp_server.py,sha256=F4O49tK2NJV-N53gxbJRNk24-lx5b2YgaUaojQhNAqQ,2318
-mostlyai_mock-0.0.11.dist-info/METADATA,sha256=tApgQujSIyaH_jutE-_m3-3L8sqm1nXrSrxmzOW-d6M,12680
-mostlyai_mock-0.0.11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mostlyai_mock-0.0.11.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
-mostlyai_mock-0.0.11.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mostlyai_mock-0.0.11.dist-info/RECORD,,