Unverified50% confidenceTradeoffExact time
llms-full.txt is intended for readers who want the entire corpus in one go; for a documentation site it may reach 40,000 words and is often truncated before useful chapters are reached; the default strategy is to use the compact llms.txt as a map and llms-full.txt to serve readers who explicitly ask for the full volume.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedllms.txt is a site description file proposed in 2024, placed in the domain root directory, listing a site's most important pages, summaries and purposes in Markdown format, for large language model crawlers to understand the site structure.66% similarUnverifiedNotebook LM is based on a Retrieval-Augmented Generation (RAG) architecture, which splits user documents into text chunks, vectorizes them, and stores them in an internal vector database.58% similarUnverified滚动压缩是一种有损压缩策略，利用LLM对历史消息进行摘要，将数千token对话浓缩为数百token，借鉴了数据库领域Log Compaction的思想58% similarVerifiedRAG addresses the limitation of large models' knowledge cutoff dates by splitting private documents into text chunks, converting them into vector representations stored in a vector database, and injecting retrieved relevant content into the Prompt.58% similarVerifiedEmbedding models map text to a high-dimensional semantic space typically of 768 to 4096 dimensions, and vector databases commonly use HNSW and IVF approximate nearest neighbor indexing algorithms.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021119API
curl https://kongchang.com/api/v1/knowledge/claims/1021119MCP
get_claim(id=1021119)