Best of Neo4j — 2025

1. 1
   Article

   neo4j·1y

   LLM Knowledge Graph Builder Back-End Architecture and API Overview

   Explores the back-end architecture and API design of the Neo4j LLM Knowledge Graph Builder. Utilizes Python and FastAPI to create a scalable system that processes various document sources, integrates LangChain for generative AI, and employs vector embeddings for semantic analysis. The resulting knowledge graphs, stored in Neo4j, enhance information retrieval and content summarization. This modular approach supports AI-driven conversational interfaces and advanced data interactions.

   101
2. 2
   Article

   neo4j·1y

   LLM Knowledge Graph Builder Front-End Architecture and Integration

   The Neo4j LLM Knowledge Graph Builder offers a user-friendly interface to upload various data sources and generate graphs using LLMs. Built with React, styled-components, and Tailwind CSS, the application ensures seamless real-time data updates via SSEs. Users can easily connect to Neo4j, upload files, generate and visualize knowledge graphs, and interact through a chat interface. Key features include schema adjustments, node de-duplication, and post-processing jobs for refined graph management. The tool is designed for intuitive usability, handling large datasets efficiently, and providing explainable AI interactions.

   68
3. 3
   Article

   neo4j·1y

   LLM Knowledge Graph Builder — First Release of 2025

   The LLM Knowledge Graph Builder enhances retrieval-augmented generation (RAG) by transforming unstructured data into a structured knowledge graph. It imports documents, splits them into chunks, generates text embeddings, and uses various language models to extract entities and their relationships. The latest update introduces several features such as community summaries, parallel retrievers, and expanded model support, improving user experience and data interaction. The tool supports multiple retrievers running in parallel, guided extraction instructions, and includes metrics for retriever evaluation.

   39

   1
4. 4
   Article

   Towards AI·1y

   Building Graph RAG for structured and unstructured data.

   RAG (Retriever-Augmented Generation) architecture helps solve the issue of missing contextualization in LLMs (Large Language Models) without the need for fine-tuning. While Vector RAGs offer some contextualization, graph-based RAGs capture more intricate relationships, making them more effective. This post discusses how to build knowledge graphs from both unstructured data (like PDFs) and structured data (like CSVs) using tools such as Langchain and Neo4j. It also outlines steps for extracting text, chunking documents, constructing graphs, and querying the graph databases using LLMs.

   29
5. 5
   Article

   AI·49w

   Real-Time Knowledge Graph for Product insights with LLM taxonomy understanding

   Learn how to build a knowledge graph for product recommendations using product taxonomy and complementary taxonomy. This approach uses LLMs to extract and map product-related data for enhanced insights and recommendations, supported by CocoIndex software with integration to Neo4j for visualization.

   28
6. 6
   Article

   Faun·27w

   Deploying a Complete RAG Ecosystem with a Single Command: My Ultimate Docker Stack

   A comprehensive Docker Compose stack that deploys a complete RAG (Retrieval-Augmented Generation) infrastructure with a single command. The setup includes Ollama for local LLM execution, Qdrant for vector search, MongoDB for document storage, Redis for caching, Neo4j for knowledge graphs, Keycloak for authentication, and n8n for workflow automation. The stack can be configured for CPU-only, GPU-accelerated, or external API usage, with automated setup scripts that handle dependencies and provide instant access to all services. Neo4j integration enables advanced relationship mapping between documents and entities, enriching context beyond traditional vector search.

   15
7. 7
   Article

   neo4j·1y

   Building AI Agents With the Google Gen AI Toolbox and Neo4j Knowledge Graphs

   Learn to build agentic applications by integrating database-based tools with the Google Gen AI Toolbox and Neo4j knowledge graphs. Discover the concept of agentic architectures, how they differ from traditional retrieval-augmented generation (RAG), and the benefits of using knowledge graphs for better context and execution in AI systems. The post includes practical examples and setups for using the Gen AI Toolbox with various databases, including Neo4j, and showcases an investment research agent managing complex queries and tool calls.

   13
8. 8
   Article

   Daily Dose of Data Science | Avi Chawla | Substack·45w

   Build a Shared Memory for Claude Desktop and Cursor

   Learn how to create a shared memory system between Claude Desktop and Cursor using Graphiti MCP server. The setup involves deploying a local Docker container with Neo4j database and configuring both AI tools to connect to the same MCP server, enabling context sharing and cross-operation between the two platforms.

   12
9. 9
   Video

   Programmers are also human·35w

   That one guy in tech meetings

   A humorous dialogue depicting a common tech meeting scenario where one participant repeatedly suggests buzzword solutions like microservices, Kubernetes, and Rust regardless of context, while others try to have a productive discussion about refactoring and system improvements.

   11

   1
10. 10
    Article

    Medium·31w

    How Python + GraphDB Transforms ETF and Company Relationship Analysis

    Demonstrates how to use Python and Neo4j graph database to analyze relationships between ETFs and their holdings. Shows data collection from Financial Modeling Prep API, database setup, and visualization techniques to uncover hidden patterns in financial data. Includes practical examples of querying ETF portfolios, identifying overlapping holdings, and discovering investment insights through graph visualization.

    10