GenAI and GraphRAG

large language model

A model trained on text to predict the next token, and so to generate language.

Also written: LLM, LLMs

Lessons that use this term

The lesson and course links below open in a new tab.

110 lessons use this term. The 40 with the highest term density are listed here.

Neo4j & GenerativeAI Fundamentals79 mentions

  • RAG PipelineIntegrating Neo4j with Generative AIof a RAG (Retrieval-Augmented Generation) pipeline to provide context to a LLM17 mentions
  • ConsiderationsGenerative AIWhile GenAI and LLMs provide a lot of potential, you should also be14 mentions
  • What is Generative AIGenerative AIwill focus on text-generating models, specifically Large Language Models (LLMs11 mentions
  • GenAI FrameworksIntegrating Neo4j with Generative AIto help you integrate Neo4j with generative AI and large language models (LLMs6 mentions
  • ContextGenerative AIYou can improve the accuracy of responses from LLMs by providing context in your5 mentions
  • Creating Knowledge GraphsKnowledge Graphsyou can use the text analysis capabilities of Large Language Models (LLMs) to help automate knowledge graph6 mentions
  • GraphRAGRetrieval Augmented Generation (RAG)the strengths of graph databases to provide relevant and useful context to LLMs7 mentions

Constructing Knowledge Graphs with Neo4j GraphRAG for Python45 mentions

Neo4j and Generative AI Workshop87 mentions

  • What is Generative AIGenerative AIwill focus on text-generating models, specifically Large Language Models (LLMs23 mentions
  • What is an Agent?AgentsAn AI agent is a system that combines a Large Language Model (LLM) with the ability to take actions in the real7 mentions
  • Constructing knowledge graphsKnowledge Graph Constructionthe process of constructing knowledge graphs from unstructured text using an LLM12 mentions
  • Extracting a schema from textKnowledge Graph Constructiona knowledge graph and retrievers to extract information from the graph using LLMs5 mentions
  • Text to Cypher retrieverRetrievalresponse includes the Cypher statement that the LLM generated and the results from executing the5 mentions
  • GraphRAG for PythonGenerative AIand implement simple applications that use GraphRAG to provide context to LLM4 mentions
  • Vector + Cypher retrieverRetrievalthis workshop, your Python code creates embeddings through the hosted LLM access you set up in the first module, as you will see in the task8 mentions

Using Neo4j with LangChain30 mentions

  • Neo4j integrationNeo4j and LangChainpopular framework for building applications powered by large language models (LLMs6 mentions
  • SchemaText to CypherThe LLM generates Cypher queries based on the schema of the5 mentions
  • Cypher QA Chain with GraphCypherQAChainText to Cypherrequires the graph connection and an LLM model to generate the Cypher query and7 mentions
  • Cypher GenerationText to Cypherspecific data or business rules, you can provide specific instructions to the LLM when generating the6 mentions
  • Simple LangChain AgentNeo4j and LangChainCreate an LLM and5 mentions

Building Knowledge Graphs with LLMs59 mentions

Introduction to Vector Indexes and Unstructured Data10 mentions

  • Turning data into knowledgeImporting unstructured datacan use a knowledge graph to give context and ground an LLM, giving it access to structured data beyond its initial training3 mentions

Build a Knowledge Graph MCP Server Workshop26 mentions

  • Add a Text-to-Cypher ToolCreating an MCP ServerText-to-Cypher uses a large language model (LLM) to write a Cypher query from a question in plain10 mentions
  • Connect a Python AgentUsing an Agentconnects to your MCP server, gives your tools to an LLM, and runs the tools that the LLM7 mentions
  • What is an AgentUsing an Agentagent is an application built around a large language model (LLM) that can use5 mentions

Build an MCP Server in Python with FastMCP24 mentions

  • Advanced MCP FeaturesIntegration and Advanced Featuresallows your tools to call the LLM during4 mentions
  • Building PromptsBuilding Database-Connected Featuresbuilt tools that LLMs can call and resources that clients can3 mentions

Building Agents in Neo4j Aura23 mentions

  • Creating Cypher Template toolsBuilding an Agentdefine the query once and the LLM extracts parameter values from the user's question and runs6 mentions

Building GraphRAG TypeScript MCP tools28 mentions

  • Advanced MCP FeaturesIntegration and Advanced Featuresallows your tools to call the LLM during4 mentions
  • Building MCP serversGetting Started with MCPdata at runtime, and they generate the JSON Schema descriptions that tell the LLM what each parameter11 mentions
  • Using ResourcesBuilding Database-Connected Featuresyou have provided access to your Neo4j database through tools, which allow the LLM to query the database dynamically based on a fixed set of6 mentions

Hands-on GenAI Workshop15 mentions

  • AgentsA tour of Aura!["A flowchart of an agent: user input, LLM reasoning, tool selection, tool execution, and the final10 mentions

All glossary terms