Expired60% confidenceFactExact time
Simple keyword-matching content filtering solutions can be bypassed by users through synonym substitution, pinyin input, Unicode obfuscation, prompt injection, and other methods.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Agent Middleware: Adding Interceptors to Model Calls
bilibili老陈说编程6/14/2026
Related Claims
UnverifiedHybrid retrieval combining keyword search with vector search can compensate for the coverage blind spots of pure semantic retrieval.70% similarUnverifiedSemantic search converts text into high-dimensional vectors and finds the most relevant conclusions by computing cosine similarity, allowing queries phrased in different ways to match semantically equivalent results.65% similarUnverified用户提问时问题被转换为向量，通过余弦相似度算法找到语义最相近的文档片段，这是语义检索优于传统关键词检索的根本原因65% similarUnverifiedSemantic caching converts queries into vector embeddings and calculates cosine similarity to identify semantically equivalent queries, which can reduce actual API call volume by 30%–70%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47005API
curl https://kongchang.com/api/v1/knowledge/claims/47005MCP
get_claim(id=47005)