Unverified50% confidenceDecision RuleExact time
For the conclusion that graph indexing saves about 10x tokens compared to file-by-file exploration, it is advisable to test it yourself against the scale of your own codebase rather than directly trusting vendors' benchmark data.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在文件数量不过千的个人知识库场景下，结构化Markdown索引比向量数据库检索更稳定、可解释性更强70% similarUnverifiedFor small, well-organized internal corpora (a few hundred files rather than millions), plain Markdown with grep search is faster and easier to understand than building retrieval infrastructure.66% similarUnverified父子块策略将文档同时索引为大块和小块，检索时用小块精准定位，生成时返回大块提供完整上下文64% 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.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1040818API
curl https://kongchang.com/api/v1/knowledge/claims/1040818MCP
get_claim(id=1040818)