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

daveebbelaar

from typing import Any, Dict, List, Type

import instructor
from anthropic import Anthropic
from config.settings import get_settings
from openai import OpenAI
from pydantic import BaseModel, Field


class LLMFactory:

disler

Minimal Prompt Chainables

Sequential prompt chaining in one method with context and output back-referencing.

Files

• main.py - start here - full example using MinimalChainable from chain.py to build a sequential prompt chain
• chain.py - contains zero library minimal prompt chain class
• chain_test.py - tests for chain.py, you can ignore this
• requirements.py - python requirements

Setup

disler

Setup

0. Create a new directory with these three files (requirements.txt, main.py, README.md)
1. python -m venv venv
2. source venv/bin/activate
3. pip install -r requirements.txt
4. python main.py
5. Update main() to run the example prompt chains

disler

What is an AI Coding Assistant?

If the coding assistant can't run ITERATIVE CRUD on ALL of your code, it's not a True AI Coding Assistant (TACA)

Standards for TRUE AI Coding Assistants

1. Must work on existing codebases
2. Must have a file context mechanism
3. Must be iteratively controllable

VYV7

//---------------------------------------------------------
// Executor function is called right away when a promise is created
// Start a long running process here
// (HTTP requests, storing data to a database etc.)
const promiseExecutor = (resolve, reject) => {
    setTimeout( () => {
        if (1) {
            resolve('Promise resolved') // called if things went well
        } else {
            reject('Promise rejected')  // called if things went bad