A curated list of awesome resources for AI engineers
- Anthropic courses
- LLM Bootcamp (Spring 2023) (from The Full Stack)
- OpenAI Cookbook
- Patterns for Building LLM-based Systems & Products (from Eugene Yan, 2023)
- Pinecone learning center
- Prompt Engineering Guide
- RAG Techniques (from Nir Diamant)
- Vector databases (four blog posts series from Prashanth Rao)
- What We've Learned From A Year of Building with LLMs (from Applied LLMs)
- Gradient Dissent (from Weights & Biases)
- High Agency (from Humanloop)
- Latent Space
- No Priors
- Vanishing Gradients
- A Hacker's Guide to Language Models (talk by Jeremy Howard)
- The Brief History of AI Agents (2023-2024) (talk by swyz)
- How to Construct Domain Specific LLM Evaluation Systems (talk by Hamel Husain and Emil Sedgh)
- All the Hard Stuff Nobody Talks About when Building Products with LLMs (from Honeycomb / Phillip Carter)
- Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge) (from Eugene Yan)
- How to Interview and Hire ML/AI Engineers (from Eugene Yan)
- LLM Evaluation doesn't need to be complicated (from Phil Schmid)
- LLM Powered Autonomous Agents (from Lilian Weng)
- Observability for Large Language Models (from Phillip Carter; paywall)
- Prompt Engineering (from Lilian Weng)
- Successful language model evals (from Jason Wei)
- The Rise of the AI Engineer (from Swyx & Alessio Fanelli)
- Your AI Product Needs Evals (from Hamel Husain)
- What AI Engineers Should Know About Search (from Doug Turnbell)
- AI Engineering (by Chip Huyen, Early Release)
- Building LLMs for Production: Enhancing LLM Abilities and Reliability with Prompting, Fine-Tuning, and RAG (by Louis-François Bouchard and Louie Peters)
- LLM Engineer's Handbook (by Paul Iusztin and Maxime Labonne)
- Prompt Engineering for LLMs (by John Berryman & Albert Ziegler, Early Release)
- Build a Large Language Model (From Scratch) - book by Sebastian Raschka.
- Building Recommendation Systems in Python and JAX (book by Bryan Bischof & Hector Yee)
- GPU Mode Discord (formerly CUDA Mode)
- GPU Mode YouTube videos (formerly CUDA Mode)
- Designing Machine Learning Systems (book by Chip Huyen)
- fast.ai courses
- Neural Networks - Zero to Hero (videos from Andrej Karpathy)
- Awesome AI engineering
- Awesome AI engineering reads
- Awesome LLM planning and reasoning
- Awesome LLM resources
- Awesome RAG
- LangChain - "LangChain is a framework for developing applications powered by large language models (LLMs)".
- LlamaIndex - "LlamaIndex is the leading data framework for building LLM applications".
- Guardrails - "Adding guardrails to large language models".
- LiteLLM - "Call all LLM APIs using the OpenAI format".
- Instructor - "Structured LLM Outputs".
- Outlines - "Outlines provides ways to control the generation of language models to make their output more predictable".
- Evaluate (from HuggingFace) - "A library for easily evaluating machine learning models and datasets".
- Langfuse — "Traces, evals, prompt management and metrics to debug and improve your LLM application".
- LangSmith - "LangSmith is an all-in-one developer platform for every step of the LLM-powered application lifecycle, whether you’re building with LangChain or not".
- Inspect - "An open-source framework for large language model evaluations".
- Weights & Biases Weave — "W&B Weave is here to help developers build and iterate on their AI applications with confidence."
- fasthtml - "The fastest way to create an HTML app".
- Gradio - "Build & Share Delightful Machine Learning Apps".
- Streamlit - "A faster way to build and share data apps".
- text-generation-inference from HuggingFace - "A Rust, Python and gRPC server for text generation inference. Used in production at Hugging Face to power Hugging Chat, the Inference API and Inference Endpoint".
- vLLM - "vLLM is a fast and easy-to-use library for LLM inference and serving".
- Axolotl - "Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures".