disler

Prompt Chaining with QwQ, Qwen, o1-mini, Ollama, and LLM

Here we explore prompt chaining with local reasoning models in combination with base models. With shockingly powerful local models like QwQ and Qwen, we can build some powerful prompt chains that let us tap into their capabilities in a immediately useful, local, private, AND free way.

Explore the idea of building prompt chains where the first is a powerful reasoning model that generates a response, and then use a base model to extract the response.

Play with the prompts and models to see what works best for your use cases. Use the o1 series to see how qwq compares.

Setup

• Bun (to run bun run chain.ts ...)

cookienommienom

import discord
from discord.ext import commands
from sqlalchemy import create_engine, Column, Integer, String, Boolean
from sqlalchemy.orm import sessionmaker, declarative_base
import stripe
from fastapi import FastAPI, Request, HTTPException
import uvicorn
import asyncio

# Set up the database

0xdevalias

Web App Tech Stack Things

Table of Contents

• From GitHub Issues
  • Configure prettier
  • Set up .editorconfig
  • Set up husky + lint-staged to run eslint / prettier
• Conventional Commits, Conventional Changelog, Semantic Release, release.yml, semantic.yml, Commitlint, Commitizen, etc

RibomBalt

from fastapi import FastAPI, Depends, BackgroundTasks, Request
from typing import Annotated, AsyncIterator
from pydantic import BaseModel, Field
from uuid import uuid4
from contextlib import asynccontextmanager
import random
import asyncio

app = FastAPI()

Karan071

from fastapi import FastAPI, HTTPException, UploadFile, Form
from fastapi.middleware.cors import CORSMiddleware
from prisma import Prisma
from deepface import DeepFace
import numpy as np
from io import BytesIO
from PIL import Image, UnidentifiedImageError
import json
import os
import base64

supersational

while true; do
  osascript -e '
tell application "System Events"
    if exists process "Claude" then
        tell process "Claude"
            if exists button "Allow for This Chat" of group 2 of group 1 of group 2 of group 1 of UI element "Claude" of group 1 of group 1 of group 1 of group 1 of window "Claude" then
                click button "Allow for This Chat" of group 2 of group 1 of group 2 of group 1 of UI element "Claude" of group 1 of group 1 of group 1 of group 1 of window "Claude"
                log "clicked allow button"
            end if
        end tell

disler

Four Level framework for prompt engineering

Watch the breakdown here in a Q4 2024 prompt engineering update video

LLM library

Ollama

Level 1: Ad hoc prompt

• Quick, natural language prompts for rapid prototyping
• Perfect for exploring model capabilities and behaviors

timothywarner

🚀 GitHub Copilot Tips for Healthcare Teams

A curated collection of best practices, tips, and resources to help healthcare professionals and development teams unlock the full potential of GitHub Copilot. Designed for sensitive environments, this guide highlights actionable advice, insightful articles, and compliance-minded practices. 🌟

📋 Table of Contents

1. 💡 Why GitHub Copilot for Healthcare?
2. 🔧 Quick Setup and Best Practices
3. 🧑‍⚕️ Healthcare-Specific Use Cases
4. ⚖️ Compliance and Security Best Practices
5. 🤝 Connect with Me

Mockapapella

-- Auto Commit Message
local M = {}

function M.generate_commit_message()
  local api_key = os.getenv 'ANTHROPIC_API_KEY'
  if not api_key then
    vim.api.nvim_echo({ {
      'ANTHROPIC_API_KEY environment variable is not set',
      'ErrorMsg',
    } }, true, {})

Mockapapella

-- Helper function to get total line count of a file
local function get_file_line_count(file_path)
  local file = io.open(file_path, 'r')
  if not file then
    return 0
  end
  local line_count = 0
  for _ in file:lines() do
    line_count = line_count + 1
  end