• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
• RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Generic RAG embeddings underperform on code; these retrieval models report 0.71 Recall@k against 0.61 for the next best and cut input tokens 47%, which matters as frontier quality degrades past roughly 50k tokens of context.

• articleFast Agentic Search
• articleCompact
• articleRelace Apply 3
• articleRelace Repos

• articleVITAL-RAG: Invariance Race for Context Allocation in Coding AgentsZijian Lu, Yonghua Lu, Mingcai Chen, Yiping Zuo, Xin He, Weijun Wang, Weibei Fan
• articleBetter Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code CompletionBaoyi Wang, Xingliang Wang, Guochang Li, Chen Zhi, Junxiao Han, Xinkui Zhao, Nan Wang, Shuiguang Deng, Jianwei Yin
• articleCodeGrep: An RL-Trained Retrieval Agent for LLM Coding AgentsWuya Chen, Yihao yang, Yang Cao, Yue Lin

Checking sign-in…

Loading comments…