skills.rest
Shadylukin
ShadylukinCOMMUNITY
Explore all skills by this author →
Website𝕏@AckroydLukinGitHub

neumann-vector

Build HNSW vector indexes and run similarity queries with COSINE, EUCLIDEAN, and DOT_PRODUCT metrics.

74|6|Updated Dec 23, 2025
Search Tags:#indexing#embeddings#rag#hnsw#vector-search#similarity-search#semantic-retrieval
One-click install
npx skills add https://github.com/Shadylukin/Neumann --skill neumann-vector
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neumann-vector
Source: https://github.com/Shadylukin/Neumann/tree/main/.claude/skills/neumann-vector
Command: npx skills add https://github.com/Shadylukin/Neumann --skill neumann-vector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provide a clear, operational guide for storing embeddings, building HNSW indexes, and performing fast approximate nearest neighbor queries so developers can implement similarity search, RAG retrieval, and semantic caching without ad hoc tooling.

Core Features & Use Cases

  • Vector storage model: Keyed embeddings stored in a dedicated vector engine with optional collection namespaces and sharded locking for concurrent writes.
  • ANN search with HNSW: Explicit index build step for fast SIMILAR queries supporting COSINE, EUCLIDEAN, and DOT_PRODUCT metrics.
  • Cross-engine patterns: Combine vector similarity with graph traversal and semantic caching to power RAG, agent memory, and similarity-aware graph operations.
  • Performance & safety tips: Guidance on batch loading, index build timing, consistent dimensionality, and using collections for multi-tenant isolation.

Quick Start

Store embeddings, build the HNSW index, and run a SIMILAR query to retrieve top-k results for your application.

Frequently Asked Questions about neumann-vector

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a scalable vector search index for RAG retrieval?▼

To build scalable vector search, store embeddings with consistent dimensionality, perform bulk inserts, and explicitly build an HNSW index to enable fast approximate nearest neighbor queries for RAG retrieval.

What similarity metrics are supported for HNSW vector search?▼

HNSW vector search supports COSINE, EUCLIDEAN, and DOT_PRODUCT similarity metrics for calculating vector distances during semantic retrieval and similarity-based caching operations.

When do I need to explicitly build the HNSW index during an embedding pipeline?▼

You must explicitly build the HNSW index after completing bulk vector inserts to ensure fast approximate nearest neighbor queries function correctly during similarity-based retrieval operations.

Can I use vector search collections for multi-tenant isolation?▼

Yes, you can use dedicated collection namespaces within the vector engine to achieve multi-tenant isolation, keeping tenant-specific embeddings separated while maintaining concurrent write safety.

How does cross-engine vector similarity work with graph queries?▼

Cross-engine workflows combine vector similarity search with graph traversal to power similarity-aware graph operations, enabling complex retrieval patterns for agent memory and advanced RAG applications.

What are the limitations when using HNSW for semantic caching?▼

HNSW requires consistent vector dimensionality across all stored embeddings and an explicit index build step after bulk inserts, meaning dimensional mismatches or unbuilt indexes will prevent semantic caching queries from working.

Related Skills

Explore More Software Engineering Skills→
haJ1thaJ1t

embedding-manager

Generate and store dense and sparse embeddings for similarity search.

Community
Advanced
edangx100edangx100
1

ranking

Rank retrieved documents by similarity_score or distance with thresholds and top-k selection.

Community
Basic
nmdranmdra
26

notebrain-assistant

Index and query Obsidian markdown vaults with ChromaDB for semantic retrieval and graph analysis.

Community
Advanced
zechenzhangAGIzechenzhangAGI
11.5k

faiss

Perform billion-scale k-NN similarity search with FAISS index types and GPU acceleration.

Community
Intermediate