This topic summarizes best practices for Graph Database.
|
Description |
Reference |
|
Get started with PolarDB Graph Database. Learn its core concepts and how to use it. |
|
|
Use the Graph Database plugin in PolarDB to quickly import hundreds of millions of nodes and edges. This method avoids performance bottlenecks caused by queries during edge insertion. |
Graph analytics based on PolarDB: Quickly import data to a graph from a table |
|
Use a Data Transfer Service (DTS) task to create a real-time synchronization link that synchronizes data from other databases to PolarDB Graph Database. |
|
|
Use the Graph Database plugin in PolarDB to run graph queries on a public insurance dataset. This example shows how to identify abnormal claims and fraud rings in an insurance claims scenario. |
Graph analytics based on PolarDB: A practical guide to insurance data analytics |
|
Use the Graph Database plugin in PolarDB to identify relationships between fraudulent transactions with graph queries. Calculate the Jaccard similarity between transactions to trigger fraud alerts. |
|
|
Build a retrieval-augmented generation (RAG) system with PolarDB, Qwen, and LangChain. This system combines a knowledge graph and vector retrieval to improve question-and-answer quality. |
GraphRAG: Best practices for knowledge graphs and LLMs based on PolarDB, Qwen, and LangChain |
|
PolarDB uses the Mem0 framework to integrate vector and graph database engines. This integration enables an AI agent to store and retrieve user preferences and history across sessions, delivering a true long-term memory experience. This design addresses the common limitation of Large Language Models (LLMs) forgetting conversation history due to context limits, thereby improving service continuity. |
Graph analytics based on PolarDB: A one-stop solution for AI agent long-term memory |