jeffmylife

fyi this walkthrough is an ai summary so it might not be perfect

🚀 Build an Authenticated Remote MCP Server with Clerk & Next.js

Welcome to the ultimate guide for building a remote Model Context Protocol (MCP) server that requires authentication! We'll use Clerk for user management, Next.js for our frontend, and Cloudflare Workers for our MCP server. By the end, you'll have Claude Desktop connecting to your authenticated MCP server that can access Gmail on behalf of your users.

🎯 What We're Building

Imagine this: You tell Claude "Check my latest emails from my boss" and Claude seamlessly:

jeffmylife

LangChain with Tools and Chat History: A Guide

Welcome to this guide on using LangChain with tools and chat history management. This guide will explain how to set up and use tools with LangChain, manage chat history, and handle tool interactions within your conversation flow.

Table of Contents

1. Overview
2. Setting Up Your Environment
3. Tools Overview
4. Handling Chat History
5. Message Flow with Tools

jeffmylife

import argparse
import json
import os
import statistics
import time
from statistics import mean, stdev
from typing import List, Dict

import plotext as plt
from litellm import completion

jeffmylife

Natural Language Time Parser using LLM

A Python utility that converts natural language time expressions into structured datetime objects using LLMs. Perfect for parsing user inputs like "next Tuesday", "in a few months", or "sometime next summer".

Features:

• Converts natural language to precise dates
• Handles relative time expressions
• Season awareness
• Configurable word translations (e.g., "few" = 3-4, "several" = 5-6)
• Returns structured output with confidence indicators

jeffmylife

import pandas as pd


def sample_dataframe(df, date_column, N):
    """
    Samples a pandas DataFrame to achieve a balanced representation across different date groups.

    This function ensures that smaller date groups (those with counts less than an average size)
    are fully represented in the sample. Larger date groups are sampled uniformly to contribute
    towards a total sample size of N. If the initial sampling process results in a total sample size

jeffmylife

.phony: all

all: push

# configuration setup
PROJECT_FILE_NAME=project.yml
CONFIG := python3 -c "import yaml; import json; from pathlib import Path; print(json.dumps(yaml.safe_load(Path(\"$(PROJECT_FILE_NAME)\").read_text())))"
OS := $(shell python3 -c "import platform; print(platform.system())")

# defaults

jeffmylife

import re
import asyncio
from io import BytesIO
import time
from pathlib import Path
from PIL import Image

import aiohttp
import requests

jeffmylife

## NOTE: I wouldn't run this script by itself. 


# install vina 
tar xzvf autodock_vina_1_1_2_mac_64bit.tar.gz
cd autodock_vina_1_1_2_mac_catalina_64bit
./installer.sh
mv bin/vina /usr/local/bin

# test 

jeffmylife

import itertools
from operator import itemgetter

def aliasinate(lst, sep=';') -> dict:
    '''
    Parameters
    ----------
    lst : list
        List of strings containing aliases in any order or combination. 
    

jeffmylife

import csv
import json
import os

import boto3
import botocore.response
from pprint import pprint

MINIMUN_REMAINING_TIME_MS = int(os.getenv('MINIMUM_REMAINING_TIME_MS') or 10000)