RAG from scratch series - part 1

The blog post discusses dissatisfaction with GitHub Actions due to its limitations in managing complex workflows, especially in monorepo setups with certain features like pull request checks and workflow reusability. Several issues have been highlighted, along with alternatives for GitHub Actions.

This is a blog post about using the OpenAI Batch API which allows users to batch process large language model requests, significantly reducing costs by up to 50% but requiring additional infrastructure and maintenance considerations.

This blog post discusses the challenges of extracting structured information from unstructured documents using Large Language Models (LLMs). With the recent release of structured output by OpenAI, developers can now pass a JSON schema and get back a response that conforms to it.

The second part in the blog series of how to build a RAG (Retrieval Augmented Generation) system from scratch. Aimed at beginners, the blog will introduce you to foundational concepts and pieces which are needed to build such a system. The blog comes with code and step by step implementation

A list of learning materials for software engineers that want to start working on Generative AI projects. The materials and concepts are categorized from beginner to more advanced with explanations on why each concept is important.