jamesmurdza

1. As Simple as Possible, but No Simpler
2. Bugs Are Contagious
3. A Good Name Is the Best Documentation
4. Generalization Takes Three Examples
5. The First Lesson of Optimization Is Don’t Optimize
6. Code Reviews Are Good for Three Reasons
7. Eliminate Failure Cases
8. Code That Isn’t Running Doesn’t Work
9. Write Collapsible Code
10. Localize Complexity

jamesmurdza

FROM ubuntu:22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive \
    DEBIAN_PRIORITY=high \
    PIP_DEFAULT_TIMEOUT=100 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    PIP_NO_CACHE_DIR=1

# Basic system setup

jamesmurdza

OpenAI

from openai import OpenAI

client = OpenAI()

tools = [{
    "type": "function",
    "function": {

jamesmurdza

class MistralBaseProvider(OpenAIBaseProvider):

    def create_function_def(self, name, details, properties, required):
        # Wrap all descriptions to avoid Mistral validation error.
        details["description"] = {"type": "string", "description": details.get("description")}
        return super().create_function_def(name, details, properties, required)
    
    def call(self, messages, functions=None):
        # Make the last message a prefix if its role is assistant.
        if messages and messages[-1].get("role") == "assistant":

jamesmurdza

server {
    listen 443 ssl;
    server_name api.sandbox.gitwit.dev;
    ssl_certificate /etc/letsencrypt/live/api.sandbox.gitwit.dev/fullchain.pem; # managed by Certbot
    ssl_certificate_key /etc/letsencrypt/live/api.sandbox.gitwit.dev/privkey.pem; # managed by Certbot


    location / {
        proxy_pass http://localhost:4000;
        proxy_http_version 1.1;

jamesmurdza

1. Update the System
sudo apt update
sudo apt upgrade

jamesmurdza

from dotenv import load_dotenv
from crewai import Agent, Task  
from crewai_e2b_python.code_interpreter_tool import E2BCodeInterpreterTool
import json

load_dotenv()

def main():

    # Initialize the code interpreter tool

jamesmurdza

***Code Interpreting...
!pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup

# Fetch the Hacker News homepage
url = 'https://news.ycombinator.com/'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')

jamesmurdza

00:00:02 hey everyone today we're going to be doing cnns or convolutional neural networks

doing cnns or convolutional neural networks and uh those are neural network models designed for processing structured grid data like images

00:00:06 cnns are neural networks that can be used to classify or detect images

networks that can be used to classify or detect images, and that's about all i know. passing it to naid. yeah, just like the simple.

00:00:24 the idea for cnns was inspired by biological networks, similar to simple neural networks