PacktPublishing / LLM-Engineers-Handbook

The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

https://github.com/PacktPublishing/LLM-Engineers-Handbook

garak

garak checks if an LLM can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses.

https://github.com/NVIDIA/garak

LAMBDA

A local AI-powered email automation system that learns from your email style and creates draft responses for every unread email in your (Gmail) inbox.

https://github.com/zycyc/LAMBDA

Final Encoding in RPython Interpreters

The article discusses implementing a final encoding approach in RPython for interpreter design, focusing on a Brainfk interpreter as an example. It explores the benefits of using final encoding over initial encoding, including potential performance improvements and a different architectural approach to building interpreters in RPython.

https://pypy.org/posts/2024/11/guest-post-final-encoding-in-rpython.html

open-notebook

An Open Source implementation of Notebook LM with more flexibility and features.

https://github.com/lfnovo/open-notebook

Python Tutorial: Stock Trading Bot

This tutorial teaches how to build a stock trading bot using Django and TimescaleDB, covering data extraction from APIs, analysis, and automated recommendations. It integrates Celery for background processing and demonstrates advanced database queries in Django, showcasing the power of time series data handling for various applications beyond stock market analysis.

https://www.youtube.com/watch?v=O3O1z5hTdUM

boltz

Democratizing Biomolecular Interaction Modeling.

https://github.com/jwohlwend/boltz

FireDucks

Compiler Accelerated DataFrame Library for Python with fully-compatible pandas API.

https://fireducks-dev.github.io/

letta-ai / letta

Letta (formerly MemGPT) is a framework for creating LLM services with memory.

https://github.com/letta-ai/letta

Ollama Course – Build AI Apps Locally

Learn how to set up and use Ollama to build powerful AI applications locally. This hands-on course covers pulling and customizing models, REST APIs, Python integrations, and real-world projects like a Grocery List Organizer, RAG System, and an AI Recruiter Agency. Perfect for developers and AI enthusiasts ready to bring their ideas to life with local LLMs.

https://www.youtube.com/watch?v=GWB9ApTPTv4

bionemo-framework

A framework for building and adapting AI models in drug discovery at scale.

https://github.com/NVIDIA/bionemo-framework

The Best No-Nonsense VSCode Setup for Python Devs

Setting up VSCode for Python development doesn't have to be a headache! This video walks you through a complete and practical VSCode setup that tackles common pain points—like missing imports, mismatched Python versions, and pytest issues with finding tests.

https://www.youtube.com/watch?v=PwGKhvqJCQM

Promptic

Promptic aims to be the "requests" of LLM development -- the most productive and pythonic way to build LLM applications.

https://github.com/knowsuchagency/promptic

Abusing Talon to use my eye tracker in a project

The author describes how they used Talon, a voice control software, to access eye tracker data for a game project. They created a Python script within Talon to expose eye gaze data via a local web server, allowing integration with a Rust program

https://ntietz.com/blog/abusing-talon-eyetracker/

Hiding a message in my PyTorch weights

This post explains how to embed an arbitrary message into a tensor that contains floating-point numbers, and how to detect the presence of such a message.

https://blog.gabornyeki.com/2024-11-hiding-a-message-in-my-pytorch-weights/

Let's build a AI Photo Generator with Python and FastAPI

This course teaches how to fine-tune the Flux AI model using Replicate to create personalized image generation. It also covers building a FastAPI service to access and utilize this model efficiently.

https://www.youtube.com/watch?v=lV82LDKT16A

ridgeplot

Beautiful ridgeline plots in Python.

https://github.com/tpvasconcelos/ridgeplot

fast-graphrag

Streamlined and promptable Fast GraphRAG framework designed for interpretable, high-precision, agent-driven retrieval workflows.

https://github.com/circlemind-ai/fast-graphrag