mostlyai-mock 0.0.12__py3-none-any.whl → 0.1.1__py3-none-any.whl

mostlyai/mock/__init__.py

@@ -15,4 +15,4 @@
 from mostlyai.mock.core import sample
 
 __all__ = ["sample"]
-__version__ = "0.0.12"  # Do not set this manually. Use poetry version [params].
+__version__ = "0.1.1"  # Do not set this manually. Use poetry version [params].

mostlyai/mock/core.py

@@ -18,7 +18,6 @@ import json
 from collections import deque
 from collections.abc import Generator
 from enum import Enum
-import os
 from typing import Any, Literal, Type
 
 import litellm
@@ -26,7 +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:
 
@@ -265,7 +264,7 @@ 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 += "## 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
@@ -279,8 +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', date_format='iso', 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"
@@ -303,8 +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
 
@@ -387,7 +388,7 @@ def _create_table_rows_generator(
 
     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 [])
+        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."
         )
@@ -431,7 +432,7 @@ def _create_table_rows_generator(
             if non_context_data
             else None
         )
-        prompt = _create_table_prompt(
+        llm_prompt = _create_table_prompt(
             name=name,
             prompt=prompt,
             columns=columns,
@@ -442,7 +443,7 @@ def _create_table_rows_generator(
             non_context_data=non_context_batch,
             previous_rows=list(previous_rows),
         )
-        messages = [{"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": prompt}]
+        messages = [{"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": llm_prompt}]
 
         response = litellm.completion(messages=messages, **litellm_kwargs)
         rows_stream = yield_rows_from_json_chunks_stream(response)

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__}
 """
 
@@ -45,14 +43,7 @@ def 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 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-0.0.12.dist-info → mostlyai_mock-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-mock
-Version: 0.0.12
+Version: 0.1.1
 Summary: Synthetic Mock Data
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-mock
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-mock
@@ -225,7 +225,7 @@ tables = {
         ],
     }
 }
-df = sample(tables=tables, sample_size=10, model="openai/gpt-4.1")
+df = mock.sample(tables=tables, sample_size=10, model="openai/gpt-4.1")
 print(df)
 #    employee_id             name  boss_id                      role
 # 0            1  Sandra Phillips     <NA>                 President
@@ -269,30 +269,3 @@ 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"]`
-
-
-## LiteLLM Proxy Server
-
-In order to consume LiteLLM Proxy Server, the user must:
-- Set `LITELLM_PROXY_API_KEY` and `LITELLM_PROXY_API_BASE`
-- Prefix the `model` with LiteLLM Proxy Server provider: `litellm_proxy`. For example, `litellm_proxy/openai/gpt-4.1-nano`
-
-```python
-from mostlyai import mock
-import os
-
-os.environ["LITELLM_PROXY_API_BASE"] = "https://litellm-proxy-production-7a86.up.railway.app/"
-tables = {
-    "guests": {
-        "prompt": "Guests of an Alpine ski hotel in Austria",
-        "columns": {
-            "name": {"prompt": "first name and last name of the guest", "dtype": "string"},
-        },
-    }
-}
-df = mock.sample(tables=tables, sample_size=10, model="litellm_proxy/mostlyai/openai/gpt-4.1-nano")
-
-print(df)
-```
-
-Read more [here](https://docs.litellm.ai/docs/providers/litellm_proxy).

mostlyai_mock-0.1.1.dist-info/RECORD

@@ -0,0 +1,8 @@
+mostlyai/mock/__init__.py,sha256=rwv3TboU77Sn6Py635JgvQu64d_R2s1Nc0dIDDbHAZA,714
+mostlyai/mock/core.py,sha256=MEDVp_woSXlD0JanS3ocxWBa_XilpaWzPhsvNzTZuX0,30138
+mostlyai/mock/mcp_server.py,sha256=Vp0bWzE8wUyA6k4PHLa0TbkuI9s07E48xPrAUgf_5qU,1563
+mostlyai_mock-0.1.1.dist-info/METADATA,sha256=tY5BvODgzoiqox8yS8ISfxWtVB1wbch1KNW8CikRImc,12713
+mostlyai_mock-0.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mostlyai_mock-0.1.1.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
+mostlyai_mock-0.1.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mostlyai_mock-0.1.1.dist-info/RECORD,,

mostlyai_mock-0.0.12.dist-info/RECORD

@@ -1,8 +0,0 @@
-mostlyai/mock/__init__.py,sha256=EzC1pduN2tfMeNk5Q4DHpNCZ8Erlo4KdsEoiZSq76GY,715
-mostlyai/mock/core.py,sha256=OpVipCV-7t9WtdQ7NDs2Nl58Y_9jsLhwqT8vFrQKgLM,30115
-mostlyai/mock/mcp_server.py,sha256=FqtgGdtuncpLcPySQk2V2RXASFvfV27rqlrnXnmSE7M,2311
-mostlyai_mock-0.0.12.dist-info/METADATA,sha256=O7ACxfwzQE7M8pipE1kLwf-sdWkIaAZzBfHFOS1vwA8,13526
-mostlyai_mock-0.0.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mostlyai_mock-0.0.12.dist-info/entry_points.txt,sha256=XDbppUIAaCWW0nresVep8zb71pkzZuFA16jCBHq8CU8,61
-mostlyai_mock-0.0.12.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mostlyai_mock-0.0.12.dist-info/RECORD,,