TigerGraph
ResourcesPathfinderDiscord(opens in a new tab)
ResourcesPathfinderDiscord(opens in a new tab)
Resources

Everything, In One Wall

Videos, courses, hands-on tutorials, docs, and blog posts. One place for every phase of learning.

TigerGraph
ResourcesPathfinderDiscord(opens in a new tab)

© 2026 Tiger Graph Dev Hub. All rights reserved.

  • Privacy Policy|
  • Terms of Service

Applied · 2

Clear all
  • Glossary
  • #GraphRAG and AI

Levels

  • All Resources
  • Beginner
  • Intermediate
  • Advanced

Categories

  • Videos514
  • Docs644
  • Glossary50
  • Blog posts222

Assets

  • Definition36
  • Tutorial113
  • How-to guide319
  • Reference312

Tags

  • #Fraud and AML
  • #Entity resolution
  • #Recommendations
  • #GraphRAG and AI
  • #Graph machine learning
  • #Search
  • #Network analysis
  • #Performance and scale
  • #Running TigerGraph
  • #Evaluating graph

7 resources

NewestOldest
3 Col Grid2 Col GridList
Concept
ConceptApr 10, 2026

Multimodal Embeddings

Multimodal embeddings are vector representations that allow different types of inputs, such as text and images, to be compared in the same space. Instead of creating separate representations for each format, a model maps text, images, or other inputs into a shared embedding space. When two items land close together in

Code & samples
126
  • Graph Resources52
  • Concept
    109
  • Troubleshooting12
  • Security advisory4
  • Runbook
  • Article173
  • Case study26
  • Talk298
  • Release note24
  • Demo114
  • Webinar12
  • Event12
  • Report24
  • Discover
    Definition
    DefinitionApr 6, 2026

    Embedding

    An embedding in machine learning is a way to represent complex information as numbers so a system can compare items consistently. This matters because many real-world inputs, such as language, images, audio, and behavior patterns, contain rich, nuanced information whose meaning isn’t adequately captured by a set of fields in a

    Discover
    Definition
    DefinitionApr 6, 2026

    Vector Search

    Vector search is a way of finding information based on similarity instead of exact matches. Traditional search systems look for the same words you typed. Vector search looks for items that are similar in meaning or behavior, even if they do not use the same words or phrases. It works by

    Discover
    Definition
    DefinitionFeb 8, 2026

    Retrieval-Augmented Generation (RAG)

    Retrieval-augmented generation (RAG) is an AI application framework that improves AI responses by first retrieving supplemental data from trusted data sources to provide the generative model a relevant foundation of information to work with. In many enterprise stacks, RAG AI is the shorthand for that retrieval-plus-generation workflow. That small shift

    Discover
    Concept
    BeginnerConceptSep 19, 2025

    Contextual Reasoning in Graph AI

    Contextual reasoning in graph AI is the ability of an AI system to interpret data as part of a connected network of relationships. Instead of evaluating attributes in a vacuum, contextual reasoning analyzes how entities relate to one another. This lets you see more characteristics and influences, leading

    Discover
    Concept
    ConceptApr 4, 2025

    GraphRAG

    GraphRAG (Graph Retrieval-Augmented Generation) enhances traditional RAG by embedding knowledge graphs into the LLM inference process. Rather than retrieving isolated documents or embeddings, the system traverses a graph to extract entities, relationships, behaviors, and rules—providing context that’s structured, traversable, and explainable. In contrast to flat vector stores, wh

    Discover
    Concept
    ConceptApr 4, 2025

    Knowledge Graph LLM

    A Knowledge Graph LLM combines two essential components for building intelligent, trustworthy AI systems: a knowledge graph and a large language model (LLM). The knowledge graph provides structured meaning—it encodes entities (such as people, products, or accounts), relationships (such as ownership, sequence, or influence), and the semantics that define

    Discover