Best of Neo4j — 2024

1. 1
   Article

   neo4j·2y

   Graph vs. Vector RAG — Benchmarking, Optimization Levers, and a Financial Analysis Example

   Exploring the use of graph and vector search in retrieval-augmented generation (RAG) systems, focusing on their application in financial analysis. Discusses the differences between graph and vector search, optimization levers for graph search, and the combination of both methods in RAG. Highlights the benefits of graph databases for modeling complex relationships and dependencies, as well as the limitations and complementarity of vector search. Demonstrates the application of graph and vector search in a financial report RAG example.

   46
2. 2
   Article

   neo4j·2y

   Turn Your CSVs Into Graphs Using LLMs

   The post explores how large language models (LLMs) can assist in creating data models from CSV files for use in Neo4j, emphasizing iterative approaches to avoid data complexity distractions. It discusses using LangChain, prompt engineering for generating consistent outputs, and converting CSV data into Cypher statements for Neo4j. The post also highlights important considerations like adding unique identifiers and creating data import scripts, offering a step-by-step methodology to streamline the process.

   31
3. 3
   Article

   Changelog·2y

   Migrating from PHP to Go with Matthew Boyle & Chris Shepherd (Go Time #316)

   Matthew Boyle and Chris Shepherd share their experience migrating from PHP to Go in Curve and Cloudflare.

   30

   2
4. 4
   Article

   neo4j·2y

   Build a Knowledge Graph-based Agent With Llama 3.1, NVIDIA NIM, and LangChain

   Learn how to build a knowledge graph-based agent using Llama 3.1, NVIDIA NIM, and LangChain to retrieve structured data from the FDA Adverse Event Reporting System (FAERS). This implementation leverages dynamic query generation to ensure consistent and robust querying of the knowledge graph. Get insights on setting up a Neo4j database, configuring Llama 3.1 with function-calling support, and defining tools that dynamically generate Cypher statements to fetch relevant information about drug side effects.

   26
5. 5
   Article

   neo4j·2y

   Get Started With GraphRAG: Neo4j’s Ecosystem Tools

   Neo4j’s GraphRAG Ecosystem Tools provide open-source resources to enhance GenAI applications using knowledge graphs. GraphRAG addresses issues like hallucination and lack of domain-specific context by combining retrieval-augmented generation with structured and semi-structured data. The tools include the LLM Knowledge Graph Builder for transforming unstructured text into knowledge graphs, and NeoConverse for generating Cypher graph queries from natural language questions. These tools integrate seamlessly with various programming languages and frameworks, making it easier to build and optimize GenAI applications.

   26
6. 6
   Article

   Towards Data Science·1y

   Building Knowledge Graphs with LLM Graph Transformer

   This post explores building knowledge graphs using the LLM Graph Transformer from LangChain. It covers techniques for extracting structured data from unstructured text to create knowledge graphs, highlighting the advantages and challenges of both tool-based and prompt-based modes. The guide includes steps for setting up a Neo4j environment, defining graph schemas, and ensuring consistency in extraction. Additionally, it addresses how to import graph documents into databases like Neo4j for further analysis and application.

   24

   1
7. 7
   Article

   neo4j·2y

   New GraphAcademy Course: Building Knowledge Graphs With LLMs

   Discover how to build and query knowledge graphs using large language models (LLMs) in the new GraphAcademy course. Learn to convert unstructured data into structured, insightful graphs using Neo4j LLM Graph Builder and Python. This hands-on course covers setting schemas, interpreting results, and developing retrievers, requiring a solid understanding of Neo4j, LLM integration, and Cypher.

   24
8. 8
   Article

   Towards Data Science·2y

   Everything You Need to Know About Graph Databases & Neo4j

   Graph databases, with Neo4j being the most prominent example, offer significant advantages for modeling and accessing relationship data compared to traditional relational databases. They are particularly useful in complex scenarios such as uncovering connections in the Panama Papers, managing airport operations, and optimizing public transport routes. Neo4j, known for its ease of use, performance, and extensibility, has evolved significantly since its inception and now supports various practical applications while catering to developers with tools like the Cypher query language.

   24

   1
9. 9
   Article

   neo4j·2y

   LLM Knowledge Graph Builder: From Zero to GraphRAG in Five Minutes

   The LLM Knowledge Graph Builder by Neo4j transforms unstructured data into knowledge graphs using machine learning models and a no-code interface. It supports various data sources, including PDFs, web pages, and YouTube videos. The application identifies entities, constructs graphs, and provides an intuitive web interface for interaction. Users can visualize the generated graphs and query data using a Retrieval-Augmented Generation (RAG) chatbot.

   24
10. 10
    Article

    neo4j·2y

    Detecting Bank Fraud With Neo4j: The Power of Graph Databases

    Financial institutions are facing significant losses due to increasingly sophisticated fraud schemes. Traditional detection methods fall short, but Neo4j, a graph database, offers advanced solutions through entity link analysis. By identifying and mitigating fraud rings in real-time, Neo4j helps banks enhance their fraud detection capabilities, reduce losses, and improve security. The article provides practical Cypher queries for identifying shared information, assessing financial risks, and analyzing total credit limits among fraud rings. Neo4j's ability to visualize complex relationships further aids in speeding up investigations and improving decision-making.

    22

    1
11. 11
    Article

    Machine Learning News·2y

    Top Open Source Graph Databases

    Graph databases have gained popularity for storing and analyzing highly related data. They offer advantages such as high flexibility and performance. Some popular open-source graph databases include Neo4j, ArangoDB, and Dgraph.

    21

    2
12. 12
    Article

    Machine Learning News·2y

    The Neo4j LLM Knowledge Graph Builder: An AI Tool that Creates Knowledge Graphs from Unstructured Data

    Neo4j LLM Knowledge Graph Builder is an AI tool that transforms unstructured data into detailed knowledge graphs using advanced machine learning models like OpenAI, Gemini, and Llama3. It supports various data formats including PDFs, web pages, and video transcripts. The tool allows users to customize the extraction schema and offers advanced querying techniques such as GraphRAG. It can be deployed on Google Cloud Run or locally using Docker Compose and is integrated with the LangChain framework for enhanced data retrieval.

    20
13. 13
    Article

    Scott Logic·2y

    Building a Multi Agent Chatbot Without LangChain

    Developers are working on InferGPT, a personalized chatbot that knows its users and offers tailored responses. Instead of relying on LangChain, the team opted for React, FastAPI, and Neo4j to create a multi-agent system where each agent solves specific tasks using a large language model (LLM) and various tools. The backend design emphasizes minimizing LLM overuse, with traditional strategies connecting agents. This project aims to enhance the chatbot's engagement by inferring user preferences and involves iterative testing and future improvements in user interaction and agent creation.

    18
14. 14
    Article

    Real Python·2y

    Build an LLM RAG Chatbot With LangChain – Real Python

    Learn how to build custom chatbots using LangChain with Neo4j for retrieval-augmented generation (RAG). Deploy your chatbot with FastAPI and Streamlit.

    18
15. 15
    Article

    neo4j·2y

    GraphRAG Field Guide: Navigating the World of Advanced RAG Patterns

    GraphRAG refers to a set of Retrieval Augmented Generation (RAG) patterns using a graph structure for improved data retrieval. The post introduces various GraphRAG patterns, categorized into basic, intermediate, and advanced levels, each requiring unique pre-processing and graph patterns. GraphRAG techniques often leverage relationships within data to enhance retrieval effectiveness, usually involving client-side data structures and Python code. The post also encourages contribution to an open-source GraphRAG Pattern Catalog and provides resources for further learning and implementation.

    16

    1
16. 16
    Article

    neo4j·2y

    LangChain Neo4j Starter Kit

    The LangChain Neo4j Starter Kit is a tool for Python developers that showcases how to generate GenAI answers using a Neo4j Graph Database. It combines technologies such as Neo4j, FastAPI, OpenAI, and LangChain.

    16
17. 17
    Article

    neo4j·2y

    Needle StarterKit 2.0: Templates, Chatbot, and More!

    Needle StarterKit 2.0 is a comprehensive library for Neo4j front-end applications that includes new templates and components, such as cybersecurity, movie recommendation, and e-commerce. It aims to accelerate development by providing ready-to-use templates and components that can be customized or extended.

    16
18. 18
    Article

    neo4j·2y

    GraphRAG — The Card Game. GraphRAG explained with an imaginary…

    GraphRAG is explained using a hypothetical quiz game where players, acting as chatbots, answer trivia questions using different methods: standard, RAG, and GraphRAG. GraphRAG reduces hallucinations and improves answers by leveraging graph databases like Neo4j to find relevant documents. The game metaphor demonstrates how GraphRAG enhances chatbot precision by connecting clues through relationships in a graph database.

    15
19. 19
    Article

    Hacker News·2y

    getzep/graphiti: Build and query dynamic, temporally-aware Knowledge Graphs

    Graphiti builds dynamic, temporally aware Knowledge Graphs that manage evolving relationships between entities over time. It supports the ingestion of both unstructured and structured data and offers hybrid search functionality combining semantic and full-text search. Designed for scalability, Graphiti can handle large datasets and is tailored for applications in sales, customer service, health, and finance. Essential requirements include Python 3.10+, Neo4j 5.21+, and an OpenAI API key for LLM inference and embedding.

    15
20. 20
    Article

    Towards Data Science·2y

    Integrating Microsoft GraphRAG into Neo4j

    Learn how to integrate Microsoft GraphRAG with Neo4j to store and analyze data, along with implementing local and global retrievers using LangChain and LlamaIndex. Steps include configuration of knowledge graph extraction, importing data into Neo4j, and setting up retrievers. Uses dataset 'A Christmas Carol' to demonstrate the process. Code available on GitHub.

    15
21. 21
    Article

    neo4j·2y

    Visualizing Graph Data with Neo4j Bloom (ScoobyGraph, Part 3)

    This post explores how to visualize graph data using Neo4j Bloom, particularly focusing on a Scooby Doo graph database. It covers the creation and formatting of graph visualizations, adding categories and relationships, and utilizing graph pattern searches and custom queries. Additionally, the post discusses how to filter, animate, and expand the graph to uncover deeper insights. Instructions for importing pre-built perspectives and employing custom scene actions are also included.

    14
22. 22
    Article

    neo4j·2y

    GenAI Starter Kit: Build an Application with Spring AI in Java

    Learn how to build a GenAI application with Spring AI in Java using the Spring AI starter kit project. Explore the features of Spring AI and its integration with Neo4j for storing and querying vectors.

    14
23. 23
    Article

    neo4j·1y

    🐘 Relational Database-to-Graph Querying in Less Than 5 Minutes

    Learn how to import data from a PostgreSQL database to a Neo4j graph database using the updated import capabilities in Aura. The post guides you through setting up a PostgreSQL data source, generating a graph model, and running the import job. It also provides examples of queries to explore the imported data, using the Chinook music dataset as a case study for practical application.

    13
24. 24
    Article

    neo4j·2y

    Unleashing the Power of NLP with LlamaIndex and Neo4j: A Starter Kit

    Unlock the true potential of natural language processing with the LlamaIndex Neo4j Integration Starter Kit. Learn how to store and query documents, utilize LlamaIndex's powerful indexing capabilities, and leverage the graph database querying of Neo4j. The starter kit also includes a FastAPI application for interactive NLP applications.

    13