Tag: llm
All the articles with the tag "llm".
-
Your RAG Is Bad Because Your Chunking Is Bad
A year into production RAG, the retrieval problems teams keep blaming on the model are almost always chunking, metadata, and document structure. Concrete fixes, with the splitting code I actually run.
-
Llama 2 Is Here. Should You Self-Host?
The week Llama 2 dropped, half my inbox asked whether to pull inference in-house. The break-even math, the GPU scarcity, and the on-call tax nobody puts in the spreadsheet.
-
Building a RAG Pipeline Before LangChain Was Cool
A production retrieval pipeline over a few hundred thousand internal documents, hand-rolled in early 2023. The model is the easy part. Retrieval is where the quality lives or dies.
-
Everyone Wants ChatGPT in Their Product. Most Should Wait.
Weeks after ChatGPT launched, every exec wants it shipped into the product. Here is the production math most teams have not done yet, and the short list of who should not wait.