Posts tagged “RAG” (2 results)
Clear filter ×
Token Optimization
How to Split Long Texts Into Chunks Without Breaking Your AI Application
Chunking is one of those things that seems simple until you do it wrong and your AI starts giving weird answers. Here is how to do it properly and what to avoid.
Jun 9 · 6 min read
Tutorials
What The Hell Is RAG and How Does It Affect Token Usage in AI Applications
RAG lets AI models answer questions using your own documents. Here is how it works, why it matters, and what it does to your token counts and costs.
Jun 9 · 6 min read