Semantic Search
A retrieval method based on vector embedding technology that maps queries and documents into a high-dimensional vector space and finds semantically similar content by computing vector similarity, enabling matches even when the literal wording differs.
Core Facts
Timeline (last 90 days)
Using a vector database like Milvus can achieve semantic matching, whereas storing information in MySQL or Redis cannot be recalled directly through semantic means.
Traditional semantic retrieval usually only performs a single round of similarity ranking between the target theorem and candidate declarations, ignoring the multi-hop dependency relations among declarations, and therefore easily misses supporting lemmas that lie deep in the dependency chain but are highly relevant to the proof.
In a SEC filing retrieval project, natural-language semantic queries were 3.4 times faster than the 256-character Boolean strings analysts had previously written.
Semantic retrieval (vector search over stored knowledge) and state recovery (loading a checkpointed workflow) solve different problems; vector search can surface relevant context, but should never be the sole mechanism for restoring the exact state of an in-progress task.
For game projects, the retrieval unit is often not uniformly split text chunks but entities with semantic boundaries, so in practice a hybrid recall of "symbolic retrieval + semantic retrieval" is often used.
Modern search systems usually combine lexical ranking with other signals rather than replacing BM25, and BM25's reliability on exact matches is still difficult for vector retrieval to fully replace.
Pure semantic retrieval is insensitive to proper nouns and ignores temporal information, making it unable to distinguish the write time of memories.
Semantic retrieval is far more accurate than keyword matching.
Semantic search, compared to traditional tag- or metadata-based retrieval, can understand object relationships, scene atmosphere, and even emotional tone within images.
The limitation of semantic similarity retrieval is that semantic similarity does not imply logical relevance.
1 more timeline events
All Facts (12)
Text is encoded by an Embedding model into floating-point vectors of 768 to 3072 dimensions, stored in a vector database, and similarity retrieval is completed at millisecond speed via approximate nearest neighbor algorithms (HNSW, IVF, etc.).
65%UnverifiedUsing a vector database like Milvus can achieve semantic matching, whereas storing information in MySQL or Redis cannot be recalled directly through semantic means.
50%UnverifiedTraditional semantic retrieval usually only performs a single round of similarity ranking between the target theorem and candidate declarations, ignoring the multi-hop dependency relations among declarations, and therefore easily misses supporting lemmas that lie deep in the dependency chain but are highly relevant to the proof.
50%UnverifiedIn a SEC filing retrieval project, natural-language semantic queries were 3.4 times faster than the 256-character Boolean strings analysts had previously written.
50%UnverifiedSemantic retrieval (vector search over stored knowledge) and state recovery (loading a checkpointed workflow) solve different problems; vector search can surface relevant context, but should never be the sole mechanism for restoring the exact state of an in-progress task.
50%UnverifiedFor game projects, the retrieval unit is often not uniformly split text chunks but entities with semantic boundaries, so in practice a hybrid recall of "symbolic retrieval + semantic retrieval" is often used.
50%UnverifiedModern search systems usually combine lexical ranking with other signals rather than replacing BM25, and BM25's reliability on exact matches is still difficult for vector retrieval to fully replace.
50%UnverifiedPure semantic retrieval is insensitive to proper nouns and ignores temporal information, making it unable to distinguish the write time of memories.
50%UnverifiedSemantic retrieval is far more accurate than keyword matching.
50%UnverifiedSemantic search, compared to traditional tag- or metadata-based retrieval, can understand object relationships, scene atmosphere, and even emotional tone within images.
50%UnverifiedThe limitation of semantic similarity retrieval is that semantic similarity does not imply logical relevance.
50%Unverified智能体记忆系统需要支持语义检索，通常依赖向量嵌入与相似度检索
50%