RAG

Tag: RAG

5 posts tagged "RAG".

Wed Feb 25 2026 08:00:00 GMT+0800 (中国标准时间)

Tuning FastGPT KBs — from 0.62 to 0.89 accuracy, step by step

FastGPT defaults give ~60% retrieval accuracy. Tuned right it reaches ~90%. Step-by-step measurements for chunking, augmentation, reranking.

Wed Apr 15 2026 08:00:00 GMT+0800 (中国标准时间)

KB preparation in practice — from Notion / Lark / Confluence to RAG

A bad KB ruins any LLM budget. End-to-end repeatable pipeline — export, clean, chunk, augment, evaluate — with Python.

Wed Apr 08 2026 08:00:00 GMT+0800 (中国标准时间)

How to evaluate your RAG quality — 5 metrics, 3 toolkits

"Feels better than last week" is not measurement. Five quantitative RAG metrics and three open-source evaluators.

Tue May 12 2026 08:00:00 GMT+0800 (中国标准时间)

2026 Chinese embedding benchmark — bge-m3, Conan, m3e, bce, OpenAI

Same Chinese KB, same real support questions — five embedding models compared on retrieval accuracy, speed and cost.

Fri Apr 17 2026 08:00:00 GMT+0800 (中国标准时间)

Case · How a healthcare provider built RAG with zero PHI leakage

An internet hospital launched AI health consultations. The hardest part — PHI must never reach the LLM. Their 3-tier KB + Pipeline redaction + audit architecture.