Knowledge Graphs and LLMs: Fine-Tuning vs. Retrieval-Augmented Generation
Sep 11 15 mins read
Explore the pros and cons of fine-tuning versus retrieval-augmented generation (RAG) for overcoming large language model (LLM) limitations. Read more →
Explore the pros and cons of fine-tuning versus retrieval-augmented generation (RAG) for overcoming large language model (LLM) limitations. Read more →
Learn how combing vectors and graphs boosts AI’s ability to reason, helping uncover deeper insights and create smarter queries for complex data. Read more →
Learn how to enhance GraphRAG applications with hybrid retrieval using the Neo4j GraphRAG Package for Python, combining vector and full-text search. Read more →
Neo4j is going GA with Rust extensions for the Neo4j Python driver. Read more →
The HTTPS-based Query API is now GA for Aura and self-managed customers. Read more →
Announcing the general availability of Neo4j Change Data Capture (CDC) and Neo4j Connector for Confluent and Apache Kafka 5.1. Read more →
Explore running a Neo4j client on a Commodore 64, blending retro computing with modern database technology for a unique learning experience. Read more →
Boost write performance in Neo4j with parallel execution of Cypher subqueries, enabling faster data processing and more efficient graph updates. Read more →
Create a Neo4j GraphRAG workflow using LangChain and LangGraph, combining graph queries, vector search, and dynamic prompting for advanced RAG. Read more →
Learn Neo4j GraphRAG Python package's capabilities and how to further customize and improve your applications by using the other included retrievers. Read more →
Learn how to simultaneously ingest data into Milvus and Neo4j for a powerful RAG agent with LangChain, optimizing vector and graph database capabilities. Read more →
Integrate Microsoft's GraphRAG with Neo4j, using LangChain and LlamaIndex for advanced retrieval in just a few steps. Explore detailed code examples. Read more →
Constructing knowledge graphs from text has been a fascinating area of research for quite some time. With the advent of large language models (LLMs), this field has gained more mainstream attention. However, LLMs can be quite costly. An alternative approach… Read more →
Learn an easy way to set up a Neo4j cluster on your local Mac using k3d and K3s in this step-by-step walkthrough. Read more →
Learn to use Llama 3.1 native function-calling capabilities to retrieve structured data from a knowledge graph to power your RAG applications. Read more →
Explore how Neo4j enhances entity resolution with embeddings for string edit distances, improving accuracy and efficiency in data processing. Read more →
Explore how graph databases transforms risk management in organizations, enhancing understanding and reducing redundancy. Read more →
Explore how to visualize graph databases and interact with Neo4j Bloom using the ScoobyGraph example. Read more →
Learn how to use Cypher queries to upload the data straight from Python using a library called pyneoinstance. Read more →
Learn how to turn your tabular data into a graph using Cypher commands through this demonstration with Scooby-Doo dataset. Read more →
Discover a simple way to query Neo4j through your favorite HTTP client with Neo4j Query API. Read more →
Learn a low-code approach to combine Neo4j Bloom graph visualization with OTX to enable powerful visual threat investigations. Read more →
The Neo4j GenAI Package for Python equips you with the tools to efficiently manage retrieval and generation processes in a RAG setup. Read more →
Learn how to use unstructured.io for PDF document parsing, extracting, and ingestion into the Neo4j graph database for GenAI applications. Read more →
Chemical reactions are represented visually as a graph. Let's explore them in the Neo4j Graph Database. Read more →