Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

Vector RAG excels at finding facts stated within a single passage, but struggles when answering multi-hop relational questions ("Which customer contracts are indirectly impacted if supplier X is delayed?") or global sensemaking questions across an entire document collection. This course covers Knowledge-Graph-enhanced RAG, the Microsoft GraphRAG architecture (community detection and hierarchical summaries) and hybrid vector + property graph retrieval on Neo4j.

Participants build an ontology-guided graph from both structured records and unstructured documents, while learning how to control extraction cost and decide when GraphRAG is worth the complexity.

Who Should Attend?

  • AI engineers building solutions over interconnected enterprise domains (supply chain, legal, compliance, IT assets)
  • Data scientists and data architects combining knowledge graphs, Neo4j and RAG
  • Technical teams working on multi-document synthesis and enterprise knowledge management
  • Prerequisite: RAG and embedding fundamentals, Python and basic database querying experience

Key Takeaways

  • Identify multi-hop and corpus-wide sensemaking queries where vector-only RAG fails
  • Extract schema-constrained entities and relationships from text using LLMs and domain ontologies
  • Apply entity resolution to merge duplicate nodes across structured and unstructured sources
  • Combine vector similarity entry points with k-hop graph traversal in Neo4j / property graphs
  • Manage indexing token costs and incremental updates across Microsoft GraphRAG and LightRAG patterns

Curriculum

Why GraphRAG? Limits of Vector Similarity and Graph Thinking
  • Similarity vs connectedness: multi-hop relational queries and global corpus questions
  • Two primary paradigms: Property Graph + Vector traversal vs hierarchical community GraphRAG
Ontology Design, Entity/Relation Extraction and Entity Resolution
  • Schema-guided LLM extraction to constrain node types and relationship predicates
  • Entity resolution and disambiguation across documents and structured master data
Hybrid Vector + Graph Retrieval on Neo4j and Property Graphs
  • Lexical graph modelling (Document -> Chunk -> Entity) and vector entry-point lookup
  • k-hop subgraph expansion and parameterized Text-to-Cypher retrieval patterns
Community Detection and Global Search (Microsoft GraphRAG & LightRAG)
  • Hierarchical Leiden community detection and pre-computed community summaries
  • Local Search, Global Map-Reduce Search and lower-cost LightRAG alternatives
Production Realities: Indexing Cost, Incremental Updates and Permissions
  • Reducing graph extraction costs with SLMs and specialized NER/RE models (GLiNER)
  • Incremental graph updates and enforcing document-level permissions over community summaries
Lab: Building a GraphRAG Pipeline over Enterprise Docs and Records
  • Constructing a hybrid knowledge graph from internal documents and relational tables
  • Benchmarking multi-hop question accuracy against vector-only RAG

Other Courses in This Category

  • RAG Evaluation and Quality Assurance: Golden Datasets, LLM-as-a-Judge and CI/CD

    Replacing ”vibe checks” in RAG with systematic evaluation: golden dataset curation, synthetic test generation, RAGAS/DeepEval/Promptfoo pipelines, CI/CD quality gates and production monitoring.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Retrieval and Generation Metrics for RAG Systems

    Hands-on programme covering information retrieval metrics (Recall@k, Precision@k, MRR, NDCG@k) and generation metrics (Faithfulness, Answer Relevance, Context Precision, Citation F1) with statistical testing.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Production RAG Architecture: Scaling, Freshness, Security and Operations

    Scaling RAG from prototype to production: event-driven incremental ingestion, zero-downtime re-indexing, multi-tier caching, security controls, latency SLAs and LLMOps observability.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Building an Enterprise Knowledge Assistant: Architecture and Implementation

    End-to-end engineering programme for building an enterprise knowledge assistant across SharePoint, Confluence, Jira and internal docs with multi-turn memory, citations, permissions and feedback loops.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Text-to-SQL and Conversational Analytics over Enterprise Databases

    Engineering Text-to-SQL and conversational analytics systems that translate natural-language business questions into accurate SQL queries, tables and charts over PostgreSQL, BigQuery, Snowflake and SQL Server.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Semantic Layers and Governed Metric Definitions for Text-to-SQL and AI Analytics

    Preventing inconsistent numbers in AI analytics by grounding LLMs in a governed semantic layer (Cube, dbt Semantic Layer, YAML metric definitions, canonical joins and business glossaries).

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View

Get in touch