Open ~/.bash_profile
in your favorite editor and add the following content to the bottom.
# Git branch in prompt.
parse_git_branch() {
git branch 2> /dev/null | sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
import pytest | |
from kata import process_input | |
def test_process_input(): | |
grid_area = [5, 5] | |
current_pos = [1, 2] | |
current_direction = 0 | |
movement = 'LMLMLMLMM' |
""" | |
L - 90 deg left | |
R - 90 deg right | |
M - move forward | |
N | |
W E | |
S | |
NS - Y |
import os | |
import json | |
import sys | |
import time | |
import threading | |
import redis | |
import tkinter as tk | |
import azure.cognitiveservices.speech as speechsdk | |
from openai import OpenAI |
I created this Proof of Concept (PoC) and video demonstrate how prompt routing can be used to make ChatGPT dynamically | |
select the targeted prompt, achieving better results. The concept involves categorizing the initial prompt using ChatGPT | |
and then selecting a more specific prompt based on the tag to resend targeted prompt to ChatGPT. This PoC showcases the | |
efficiency we can gain when using speech recognition and AI tools in development. I will release the code-assist tool on | |
GitHub once I have more free time to clean up the code. If we have a set of well-tested prompts for different types of | |
specific tasks, I believe this tooling approach can help us increase our productivity by skipping a few steps in our | |
repetitious daily work tasks than just code generation. Editing code, issuing commands (with safety checks), and | |
automated scope-down online search are the next steps to multiply work productivity. | |
Video Demo: Code generation and editing via streaming speech recognition |