smgpulse007/smgpulse007-first-assistant

public

Published on 5/1/2025

My First Assistant

This is an example custom assistant that will help you complete the Python onboarding in VS Code. After trying it out, feel free to experiment with other blocks or create your own custom assistant.

Rules

Prompts

Models

Context

Models

Learn more

Claude 3.7 Sonnet

anthropic

chat

edit

200kinput·8.192koutput

Claude 3.5 Haiku

anthropic

apply

summarize

chat

200kinput·8.192koutput

Claude 3.5 Sonnet

anthropic

chat

edit

apply

200kinput·8.192koutput

Rules

Learn more

You are a Python coding assistant. You should always try to - Use type hints consistently - Write concise docstrings on functions and classes - Follow the PEP8 style guide

You are an experienced data scientist who specializes in Python-based
data science and machine learning. You use the following tools:
- Python 3 as the primary programming language
- PyTorch for deep learning and neural networks
- NumPy for numerical computing and array operations
- Pandas for data manipulation and analysis
- Jupyter for interactive development and visualization
- Conda for environment and package management
- Matplotlib for data visualization and plotting

Docs

Learn more

Pythonhttps://docs.python.org/3/

Streamlithttps://docs.streamlit.io

SQLAlchemyhttps://docs.sqlalchemy.org/en/20

NumPyhttps://numpy.org/doc/stable/

Pandashttps://pandas.pydata.org/docs/

PyTorchhttps://pytorch.org/docs/stable/index.html

Prompts

Learn more

Write Cargo test

Write unit test with Cargo

Use Cargo to write a comprehensive suite of unit tests for this function

Schema for Pre-Compiled Weekly Metrics

MS SQL Server Schema for Pre-Compiled Weekly Metrics

/****** Script for SelectTopNRows command from SSMS  ******/
SELECT TOP (1000) [WeekStartDate]
      ,[WeekEndDate]
      ,[Model]
      ,[GroupingType]
      ,[TotalCases]
      ,[Accuracy]
      ,[Precision]
      ,[Recall]
      ,[F1Score]
      ,[AUCROC]
      ,[BrierScore]
      ,[TruePositives]
      ,[FalsePositives]
      ,[FalseNegatives]
      ,[TrueNegatives]
      ,[WorstCategory]
      ,[WorstCategoryAccuracy]
      ,[BestCategory]
      ,[BestCategoryAccuracy]
      ,[CalibrationError]
      ,[EvaluationDate]
  FROM [MLPreprocessing].[MM].[WeeklyModelMetrics]
  Sample Data:
    WeekStartDate	WeekEndDate	Model	GroupingType	TotalCases	Accuracy	Precision	Recall	F1Score	AUCROC	BrierScore	TruePositives	FalsePositives	FalseNegatives	TrueNegatives	WorstCategory	WorstCategoryAccuracy	BestCategory	BestCategoryAccuracy	CalibrationError	EvaluationDate
    2024-04-28	2024-05-04	LOS	AdmitDate	19	0.5789	0.3750	0.5000	0.4286	0.5577	0.4643	3	5	3	8	NULL	NULL	NULL	NULL	0.5537	2025-04-30 15:21:18.607

Sample Data and Schema for Missing Run IDs

A sample prompt

/****** Script for SelectTopNRows command from SSMS  ******/
SELECT TOP (1000) [Last_ExistingId]
      ,[Next_ExistingId]
      ,[Num_MissingIds]
      ,[MissingId]
      ,[Status]
      ,[Insert_Datetime]
      ,[Total_MissingIds]
      ,[TotalMissingIds_Success_Status]
      ,[Missed_On_Date]
  FROM [MLPreprocessing].[MM].[Missing_Run_IDs]

  Last_ExistingId	Next_ExistingId	Num_MissingIds	MissingId	Status	Insert_Datetime	Total_MissingIds	TotalMissingIds_Success_Status	Missed_On_Date
70959	70963	3	70960	 Failure	2025-04-29 15:27:27.220	279	7	2025-03-15
70959	70963	3	70961	 Failure	2025-04-29 15:27:27.220	279	7	2025-03-15
70959	70963	3	70962	 Failure	2025-04-29 15:27:27.220	279	7	2025-03-15

Working DockerFile for streamlit production apps

A sample prompt

This is an example dockerfile from a similar dockerized application running on production.
# Use the official lightweight Python 3.11 image
FROM python:3.11-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    ACCEPT_EULA=Y \
    SQL_SERVER=default_server \
    SQL_DATABASE=default_database \
    SQL_USERNAME=default_user \
    SQL_PASSWORD=default_password \
    MLFLOW_TRACKING_URI=http://mlflow:5000

# Install system dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    build-essential unixodbc-dev curl gnupg2 && \
    curl https://packages.microsoft.com/keys/microsoft.asc | apt-key add - && \
    curl https://packages.microsoft.com/config/debian/10/prod.list > /etc/apt/sources.list.d/mssql-release.list && \
    apt-get update && ACCEPT_EULA=Y apt-get install -y msodbcsql17 && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

# Set the working directory
WORKDIR /app

# Copy and install requirements first
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir streamlit==1.28.0 && \
    pip list | grep streamlit

# Create necessary directories
RUN mkdir -p /app/data

# Copy the rest of the application files
COPY . .

# List files to debug
RUN echo "Files in container:" && ls -la /app

# Expose Streamlit port
EXPOSE 8501

# Run the Streamlit app
CMD ["python", "-m", "streamlit", "run", "dashboard.py", "--server.port=8501", "--server.address=0.0.0.0"]

Context

Learn more

@code

Reference specific functions or classes from throughout your project

@docs

Reference the contents from any documentation site

@diff

Reference all of the changes you've made to your current branch

@terminal

Reference the last command you ran in your IDE's terminal and its output

@problems

Get Problems from the current file

@folder

Uses the same retrieval mechanism as @Codebase, but only on a single folder

@codebase

Reference the most relevant snippets from your codebase

@file

Reference any file in your current workspace

@url

Reference the markdown converted contents of a given URL

@commit

@currentFile

Reference the currently open file

@repo-map

Reference the outline of your codebase

Data

Learn more

No Data configured

MCP Servers

Learn more

No MCP Servers configured