HeyCloud

Measuring the stubbornness of LLMs

How much LLMs prefer to hallucinate vs answer from RAG data

Quick comments on Llama3

Agent Oriented Programming: A Framework for building LLM Agents

How to build and orchestrate autonomous LLM agents

Long Context vs RAG: The Final Take.

Will large context LLMs kill the need for RAG architecture?

🎁 We massively reduced our OpenAI bill with this trick

This weekend, I am not sending you an article but just a little insight to reduce your OpenAI bill if you are using JSON data. This is what we did at HeyCloud and allowed us to significantly reduce our bill.

Building an Enterprise-Grade RAG with Open Source LLMs - Overview

First article of our series on how to build an Enterprise-Grade RAG with open source LLMs

Attack Vectors on RAG Applications

Security threats on RAG apps and how to mitigate them

Text splitting (chunking) for RAG applications

How to split text for your RAG applications in a way to preserve semantics

Resources to keep up with AI (LLM+RAG) progress

Free resources to stay up to date with AI/LLMs/RAG progress

Cheaper & faster RAG with a SQL layer

How to build a cheaper and faster Retrieval Augmented Generation system