ANN

常见的向量数据库包括ChromaDB、Milvus、Pinecone、Weaviate，它们针对高维向量的近似最近邻（ANN）搜索进行了专门优化

向量数据库的核心操作是近似最近邻搜索（ANN），通过HNSW、IVF等索引算法将相似度计算加速到毫秒级响应

Vector databases convert code snippets into high-dimensional embedding vectors and perform Approximate Nearest Neighbor (ANN) searches, enabling on-demand memory without expanding the context window.

Approximate nearest neighbor (ANN) algorithms such as HNSW and IVF achieve order-of-magnitude speed improvements by sacrificing a small amount of precision.

In the offline phase of the traditional RAG process, documents are chunked and converted into vectors via an embedding model and stored in a vector database; in the online phase, similar document chunks are retrieved using an Approximate Nearest Neighbor (ANN) algorithm.

Approximate nearest neighbor search (ANN) uses algorithms such as HNSW or IVF, trading a small loss in recall for millisecond-level response, returning the semantically nearest candidate set rather than the factually most relevant documents.

Approximate nearest neighbor search (ANN) reduces retrieval complexity from O(N) for exact nearest neighbor to approximately O(log N) at the cost of a small amount of recall, making millisecond-level retrieval possible under registries of tens of thousands of entries.

Retrieve-then-Plan (RtP) is currently the dominant approach in the industry's tool discovery field; its process is: first embed-encode the user query, retrieve semantically similar candidate tools via approximate nearest neighbor search, then inject them into the prompt for the LLM to perform planning.

ANN indexes (especially graph-structured HNSW) are difficult to delete from in place efficiently, so a compromise of 'soft delete + periodic merge' is usually adopted.

The core trade-off of ANN indexes (such as HNSW, IVF-PQ) lies in the triangular relationship among recall, memory and build time.

Approximate nearest neighbor (ANN) index structures (such as HNSW and IVF) need to be rebuilt or tuned after the data distribution changes, otherwise recall will decline.

An ANN index is bound to a distance metric; HNSW organizes the nearest-neighbor graph according to a certain metric at build time, and switching to another metric usually requires rebuilding the index.

HNSW is a hierarchical navigable small world index structure that belongs to the approximate nearest neighbor (ANN) strategy, trading a small amount of recall accuracy for order-of-magnitude speed improvements.

The cost of multi-vector approaches is that each document requires storing multiple vectors, making index sizes typically several to tens of times larger than single-vector approaches and placing higher demands on vector database storage and ANN search performance.

Commonly used distance metrics for vector retrieval include cosine similarity and dot product; practical systems typically employ approximate nearest neighbor (ANN) index structures such as HNSW or IVF to trade a small amount of precision for speed.

ANN solutions trade a slight loss in accuracy for orders-of-magnitude improvements in retrieval speed, returning the most similar results in milliseconds even at scales of millions to billions of vectors.

Vector index efficiency issues are typically addressed by approximate nearest neighbor (ANN) algorithm libraries, with common solutions including FAISS, Annoy, and the graph-based HNSW algorithm.

Some cross-platform AI note-taking tools support semantic search, meaning users can query historical meeting content directly using natural language questions, a capability that can only be fully leveraged when data is centralized.

Hybrid retrieval, which combines the precision of keyword retrieval with the semantic recall of vector retrieval, has become the de facto standard for modern search engines.

The paper proposes combining ANN-based AI with probability-wave-based 'entangled brain simulation' to advance the development of 'Human-like Processing Units' (HPUs).