neo4j

该论文研究在图数据库中直接进行图神经网络的训练与推理，展示使用Cypher执行采样、特征检索和完整前向传播的可行性，优化后训练速度提升约2.5倍，推理速度比冷加载图到内存快10倍以上。

The article proposes an improved method for massive parallel imports in Neo4j, using hash-based partitioning and the k-1 coloring algorithm to avoid deadlock and lock contention during data loading.

This webinar provides a practical engineering-focused approach to building a semantic layer on Neo4j using ontology, emphasizing benefits for AI-driven applications and data consistency.

An Anthropic lead engineer's 8-step pipeline transforms chaotic data into a self-updating graph, boosting productivity by 42% and winning a $1.2M bonus.

Promotion of the book 'Graph Algorithms for Data Science' which teaches graph algorithms and their applications using Neo4j, covering topics like knowledge graphs, social network analysis, and node embeddings.

A talk from WeAreDevelopers World Congress 2026 on modeling organizations as graphs to reveal hidden networks where work actually happens, alongside related videos on graph databases, knowledge graphs, and developer conferences.

This article provides a practical guide to building a GraphRAG system using LangExtract, Neo4j, Qdrant, and Ollama, combining entity extraction, knowledge graphs, and vector search for context-aware retrieval.

A developer shares an architecture using Neo4j knowledge graphs with typed entities and deduplication to solve the problem of AI agents forgetting entity identity across sessions, moving beyond flat files and vector stores.

A new open-source tool called Writ uses a hybrid retrieval pipeline with BM25, ONNX vectors, and Neo4j graph traversals to provide context rules for AI coding agents, reducing token bloat by 726x and enforcing plan approval via bash hooks.

The authors detail their experience building a code indexing system, concluding that graph-based retrieval with LLM-generated semantics outperforms vector embeddings and pure AST parsing. They open-sourced the system, Bytebell, which uses Neo4j to store semantic context for efficient and precise code retrieval.