Unverified50% confidenceFactExact time
When a local knowledge base answers questions, it annotates the cited sources, specifying which section of the uploaded document the content comes from—an advantage over querying a large model directly.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedSkill 中的 references 目录可注入领域知识文档，类似 RAG 的本地知识库，让 Agent 回答有据可查70% similarUnverifiedThe references directory is essentially a local knowledge base; when an Agent executes a Skill, it loads relevant document content into the context window, which is closely related to the RAG retrieval-augmented generation mechanism.68% similarUnverifiedAn inverted index maps terms to the list of documents containing those terms and is the core data structure of full-text search engines.65% similarVerifiedRAG（检索增强生成）的核心思想是在大模型生成回答之前，先从外部知识库中检索相关文档片段作为上下文注入Prompt64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985375API
curl https://kongchang.com/api/v1/knowledge/claims/985375MCP
get_claim(id=985375)