Discover what’s new in the world of graph technology this week, including a Dgraph acquisition, a new fork of Kuzu, the release of Gephi Lite, and more.

Today, we’re announcing the integration of Amazon Neptune Analytics with GraphStorm, a scalable, open-source graph machine learning (ML) library built for enterprise-scale applications. This integration brings together Neptune’s high-performance graph analytics engine and GraphStorm’s flexible ML pipeline, making it easier for customers to build intelligent applications powered by graph-based insights. With this launch, customers can train graph neural networks (GNNs) using GraphStorm and bring their learned representations—such as node embeddings, classifications, and link predictions—into Neptune Analytics. Once loaded, these enriched graphs can be queried interactively and analyzed using built-in algorithms like community detection or similarity search, enabling a powerful feedback loop between ML and human analysis. This integration supports a wide range of use cases, from detecting fraud and recommending content, to improving supply chain intelligence, understanding biological networks, or enhancing customer segmentation. GraphStorm simplifies model training with a high-level command-line interface (CLI) and supports advanced use cases via its Python API. Neptune Analytics, optimized for low-latency analysis of billion-scale graphs, allows developers and analysts to explore multi-hop relationships, analyze graph patterns, and perform real-time investigations. By combining graph ML with fast, scalable analytics, Neptune and GraphStorm help teams move from raw relationships to real insights—whether they’re uncovering hidden patterns, ranking risks, or personalizing experiences. To learn more about using GraphStorm with Neptune Analytics, visit the blog post.

Summer has drawn to a close here in Utrecht, where I live in the Netherlands. In two weeks, I’ll be attending AWS Community Day 2025, hosted at the Kinepolis Jaarbeurs Utrecht on September 24. The single-day event will bring together over 500 cloud practitioners from across the Netherlands, featuring 25 breakout sessions across five technical […]

Today, AWS announces Context Ontology Accelerator, an open source accelerator that helps organizations build an ontology of their business — a machine-readable model of their products, customers, policies, and the rules that define how they operate so AI agents make accurate, consistent, explainable, and auditable decisions. Context Ontology Accelerator connects to your structured and/or unstructured data sources, and uses AI to draft an ontology; your domain experts review, edit, and approve every element of it. The approved ontology is stored in a knowledge graph you own, expressed in open W3C standards so it works with any standards-based tooling, and any agent can consume it through the included Model Context Protocol (MCP) server. Organizations building AI agents need more trust in their agents' decisions, with outputs they can explain and audit. The context those agents require — entities, rules, policies, relationships — is scattered across dozens of systems with conflicting schemas and naming conventions. Teams spend months reconciling definitions and encoding them into prompts and point integrations, and because the results are not traceable, teams block agents from moving from proof-of-concept to production. Context Ontology Accelerator reduces what would take months of manual ontology authoring into days — from connecting data to serving governed answers to agents. Context Ontology Accelerator is available today on GitHub under Apache 2.0. The initial release uses Amazon Neptune as the graph store, Amazon OpenSearch Serverless as the vector store, and foundation models hosted on Amazon Bedrock; deploy it yourself or engage AWS Professional Services. Context Ontology Accelerator’s managed, user-defined ontology capability will become a fully managed feature native to AWS Context. Customers who get started with Context Ontology Accelerator to create ontologies will be able to use and manage them with AWS Context. To learn more, read the https://aws.github.io/context-ontology-accelerator/.

Today, we’re announcing the integration of Amazon Neptune Database with GraphStorm, a scalable, open-source graph machine learning (ML) library built for enterprise-scale applications. This brings together Neptune’s OLTP (Online transaction processing) graph capabilities with GraphStorm’s scalable inference engine, making it easier for customers to deploy graph ML in latency-sensitive, transactional environments. With this integration, developers can train GNN models using GraphStorm and deploy them as real-time inference endpoints that directly query Neptune for subgraph neighborhoods on demand. Predictions—such as node classifications or link predictions—can then be returned in sub-second timeframes, closing the loop between transactional graph updates and ML-driven decisions. This integration unlocks use cases such as fraud detection and prevention, where organizations can make real-time decisions based on complex relationships among accounts, devices, and transactions; dynamic recommendations, where systems can instantly adapt to user behavior using live graph context; and graph-based risk scoring, where risk assessments are continuously updated as the graph evolves. Customers can also combine real-time inference results with graph analytics queries for deeper operational insights, enabling ML feedback loops directly within graph applications. This feature is available in all regions where Amazon Neptune Database is available. To learn more and try the integration yourself, check out our announcement blog: https://aws.amazon.com/blogs/machine-learning/modernize-fraud-prevention-graphstorm-v0-5-for-real-time-inference/ 

Today, AWS announces Context Ontology Accelerator, an open source accelerator that helps organizations build an ontology of their business — a machine-readable model of their products, customers, policies, and the rules that define how they operate so AI agents make accurate, consistent, explainable, and auditable decisions. Context Ontology Accelerator connects to your structured and/or unstructured data sources, and uses AI to draft an ontology; your domain experts review, edit, and approve every element of it. The approved ontology is stored in a knowledge graph you own, expressed in open W3C standards so it works with any standards-based tooling, and any agent can consume it through the included Model Context Protocol (MCP) server. Organizations building AI agents need more trust in their agents' decisions, with outputs they can explain and audit. The context those agents require — entities, rules, policies, relationships — is scattered across dozens of systems with conflicting schemas and naming conventions. Teams spend months reconciling definitions and encoding them into prompts and point integrations, and because the results are not traceable, teams block agents from moving from proof-of-concept to production. Context Ontology Accelerator reduces what would take months of manual ontology authoring into days — from connecting data to serving governed answers to agents. Context Ontology Accelerator is available today on GitHub under Apache 2.0. The initial release uses Amazon Neptune as the graph store, Amazon OpenSearch Serverless as the vector store, and foundation models hosted on Amazon Bedrock; deploy it yourself or engage AWS Professional Services. Context Ontology Accelerator’s managed, user-defined ontology capability will become a fully managed feature native to AWS Context. Customers who get started with Context Ontology Accelerator to create ontologies will be able to use and manage them with AWS Context. To learn more, read the documentation.

Today, we are excited to announce the launch of a new feature in Graph Explorer that enables users to write and execute native Gremlin and openCypher queries directly within the interface. This enhancement empowers data scientists, developers, and database administrators to seamlessly interact with their graph databases using their preferred query language, eliminating the need for additional tools or interfaces. With this update, users can now leverage the full expressive power of both Gremlin and openCypher to traverse complex relationships, perform advanced pattern matching, and extract valuable insights from their graph data while enjoying the intuitive visual environment of Graph Explorer. To get started, create a new Notebook from the Amazon Neptune console, and start the Graph Explorer from the Notebook actions menu. You can also contribute to the graph-explorer GitHub project here. For more information on how graph-explorer works with Amazon Neptune, see the Amazon Neptune User Guide.

Today, we are announcing a new capability that NetworkX now supports Neptune Analytics as a graph store. With this release, developers can continue to use familiar NetworkX APIs while automatically offloading graph algorithm workloads to Neptune’s scalable, high-performance analytics engine. This makes it simple to scale graph computations on demand without refactoring code, combining the ease of local development with the performance and elasticity of a fully managed AWS service. Previously, when datasets grew beyond the limits of a local environment, users had to turn to third-party services—rebuilding their graph models to fit proprietary formats, exporting and importing data, and learning entirely new systems. With the new nx-neptune integration, developers only need an AWS account and credentials; the solution automatically handles graph data modeling, data movement (Zero-ETL), and infrastructure management. It provisions a Neptune Analytics instance, runs the requested algorithm, returns results directly to the user, and then tears down the infrastructure for a cost-effective, serverless-like experience—all without requiring the user to leave their familiar Python workflow. NetworkX is a widely used open-source Python library for creating, analyzing, and visualizing complex graphs. It offers an extensive collection of graph algorithms and utilities, making it a popular choice among researchers, data scientists, and developers for prototyping and experimenting with graph-based applications. To learn more about the Neptune–NetworkX Integration, visit the documentation.

Today, we are excited to announce support for Stop/Start in Amazon Neptune Analytics, a new capability that enables organizations to pause and resume their graph workloads on demand,helping reduce costs during idle periods without losing data or configuration. Many customers use Neptune Analytics for periodic graph workloads such as fraud detection, recommendation engines, or research simulations that run periodically. Until now, customers had to choose between keeping their Neptune Analytics graphs online even when not in use or deleting and recreating them each time they were needed. This approach was not only expensive, but also time-consuming, requiring manual infrastructure management, repeated data imports, and updates to downstream pipelines to accommodate each newly created graph. This adds significant operational overhead and complexity to their analytics workflows. With Stop/Start, customers can now pause a graph workload via the AWS Console, CLI, or API, and resume it later with a single action. While the graph is stopped, they pay only 10% of the normal compute cost, and all data and settings are preserved without needing to delete or rebuild graphs. This feature is particularly valuable for cost-conscious startups, research teams, and enterprises with analytics workloads. It simplifies lifecycle management and unlocks experimentation at lower price points. Stop/Start for Neptune Analytics is available in all commercial regions where Neptune Analytics is offered. You can start using this feature today via the Neptune Analytics console, AWS CLI, or AWS SDKs. To learn more, visit the documentation and the pricing page.

Today, we are excited to announce support for Stop/Start in Amazon Neptune Analytics, a new capability that enables organizations to pause and resume their graph workloads on demand,helping reduce costs during idle periods without losing data or configuration. Many customers use Neptune Analytics for periodic graph workloads such as fraud detection, recommendation engines, or research simulations that run periodically. Until now, customers had to choose between keeping their Neptune Analytics graphs online even when not in use or deleting and recreating them each time they were needed. This approach was not only expensive, but also time-consuming, requiring manual infrastructure management, repeated data imports, and updates to downstream pipelines to accommodate each newly created graph. This adds significant operational overhead and complexity to their analytics workflows. With Stop/Start, customers can now pause a graph workload via the AWS Console, CLI, or API, and resume it later with a single action. While the graph is stopped, they pay only 10% of the normal compute cost, and all data and settings are preserved without needing to delete or rebuild graphs. This feature is particularly valuable for cost-conscious startups, research teams, and enterprises with analytics workloads. It simplifies lifecycle management and unlocks experimentation at lower price points. Stop/Start for Neptune Analytics is available in all commercial regions where Neptune Analytics is offered. You can start using this feature today via the Neptune Analytics console, AWS CLI, or AWS SDKs. To learn more, visit https://docs.aws.amazon.com/neptune-analytics/latest/userguide/managing.html and https://aws.amazon.com/neptune/pricing/.

Amazon Neptune Database, a fully managed graph database service, now supports Public Endpoints, allowing developers to connect directly to Neptune databases from their development desktops without complex networking configurations. With Public Endpoints, developers can securely access their Neptune databases from outside the VPC, eliminating the need for VPN connections, bastion hosts, or other networking configurations. This feature streamlines the development process while maintaining security through existing controls like IAM authentication, VPC security groups, and encryption in transit. Public Endpoints can be enabled for new or existing Neptune clusters, with engine version 1.4.6 or above, through the AWS Management Console, AWS CLI, or AWS SDK. When enabled, Neptune generates a publicly accessible endpoint that developers can use with standard Neptune connection methods from their development machines. This feature is available at no additional cost beyond standard Neptune pricing and is available today in all AWS Regions where Neptune Database is offered. To learn more, visit the https://docs.aws.amazon.com/neptune/latest/userguide/intro.html.

Amazon Neptune Database, a fully managed graph database service, now supports Public Endpoints, allowing developers to connect directly to Neptune databases from their development desktops without complex networking configurations. With Public Endpoints, developers can securely access their Neptune databases from outside the VPC, eliminating the need for VPN connections, bastion hosts, or other networking configurations. This feature streamlines the development process while maintaining security through existing controls like IAM authentication, VPC security groups, and encryption in transit. Public Endpoints can be enabled for new or existing Neptune clusters, with engine version 1.4.6 or above, through the AWS Management Console, AWS CLI, or AWS SDK. When enabled, Neptune generates a publicly accessible endpoint that developers can use with standard Neptune connection methods from their development machines. This feature is available at no additional cost beyond standard Neptune pricing and is available today in all AWS Regions where Neptune Database is offered. To learn more, visit the Amazon Neptune documentation.

Today, we’re announcing the integration of Amazon Neptune Database with GraphStorm, a scalable, open-source graph machine learning (ML) library built for enterprise-scale applications. This brings together Neptune’s OLTP (Online transaction processing) graph capabilities with GraphStorm’s scalable inference engine, making it easier for customers to deploy graph ML in latency-sensitive, transactional environments. With this integration, developers can train GNN models using GraphStorm and deploy them as real-time inference endpoints that directly query Neptune for subgraph neighborhoods on demand. Predictions—such as node classifications or link predictions—can then be returned in sub-second timeframes, closing the loop between transactional graph updates and ML-driven decisions. This integration unlocks use cases such as fraud detection and prevention, where organizations can make real-time decisions based on complex relationships among accounts, devices, and transactions; dynamic recommendations, where systems can instantly adapt to user behavior using live graph context; and graph-based risk scoring, where risk assessments are continuously updated as the graph evolves. Customers can also combine real-time inference results with graph analytics queries for deeper operational insights, enabling ML feedback loops directly within graph applications. This feature is available in all regions where Amazon Neptune Database is available. To learn more and try the integration yourself, check out our announcement blog: Modernize fraud prevention: GraphStorm v0.5 for real-time inference for a full walk-through.

Amazon Neptune Analytics is now available in the AWS Canada (Central) and Australia (Sydney) Regions. You can now create and manage Neptune Analytics graphs in the AWS Canada (Central) and Australia (Sydney) Regions and run advanced graph analytics and vector similarity search. Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds. To analyze graph data quickly and easily, Neptune Analytics stores large graph datasets in memory. It supports a library of optimized graph analytic algorithms, low-latency graph queries, and vector search capabilities within graph traversals. Neptune Analytics is an ideal choice for investigatory, exploratory, or data-science workloads that require fast iteration for data, analytical and algorithmic processing, or vector search on graph data. It complements Amazon Neptune Database, a popular managed graph database. To perform intensive analysis, you can load the data from a Neptune Database graph or snapshot into Neptune Analytics. You can also load graph data that's stored in Amazon S3. To get started, you can create a new Neptune Analytics graphs using the AWS Management Console, or AWS CLI. For more information on pricing and region availability, refer to the Neptune pricing page and AWS Region Table.

Today, we’re announcing the integration of Amazon Neptune Analytics with Cognee, a leading agentic memory framework designed to help AI agents structure, retrieve, and reason over information. With this launch, customers can use Neptune as the graph store behind Cognee’s memory layer, enabling long-term memory and reasoning capabilities for agentic AI applications. This integration allows Cognee users to store and query memory graphs at scale, unlocking advanced use cases where AI agents become more personalized and effective over time by learning from ongoing interactions. Neptune supports multi-hop graph reasoning and hybrid retrieval across graph, vector, and keyword modalities—helping Cognee deliver richer, more context-aware AI experiences. Cognee enables a self-improving memory system that helps developers build cost-efficient, personalized generative AI applications. To learn more about the Neptune–Cognee integration, visit the User Guide and the sample notebook.

Today, we are excited to announce the launch of a new feature in Graph Explorer that enables users to write and execute native Gremlin and openCypher queries directly within the interface. This enhancement empowers data scientists, developers, and database administrators to seamlessly interact with their graph databases using their preferred query language, eliminating the need for additional tools or interfaces. With this update, users can now leverage the full expressive power of both Gremlin and openCypher to traverse complex relationships, perform advanced pattern matching, and extract valuable insights from their graph data while enjoying the intuitive visual environment of Graph Explorer. To get started, create a new Notebook from the Amazon Neptune console, and start the Graph Explorer from the Notebook actions menu. You can also contribute to the graph-explorer GitHub project https://github.com/aws/graph-explorer. For more information on how graph-explorer works with Amazon Neptune, see the https://docs.aws.amazon.com/neptune/latest/userguide/notebooks-graph-explorer.html.  

Amazon Neptune Database now supports R7i database instances powered by custom 4th Generation Intel Xeon Scalable processors. R7i instances offer larger instance sizes, up to 48xlarge and features an 8:1 ratio of memory to vCPU, and the latest DDR5 memory. These instances are now available in the following AWS Regions: US East (N. Virginia, Ohio), US West (N. California, Oregon), Asia Pacific (Jakarta, Mumbai, Seoul, Singapore, Sydney, Tokyo), Canada (Central), and Europe (Frankfurt, Ireland, London, Paris, Spain, Stockholm), and engine versions 1.4.3 or above. Amazon Neptune is a fast, reliable, fully managed graph database service that makes it easier to build and run applications that work with highly connected datasets. Compared to previous generation R6i instances, the R7i instances deliver up to 15% better price performance, powering your graph use cases such as fraud graphs, knowledge graphs, customer 360 graphs, and security graphs. You can launch R7i instances for Neptune using the AWS Management Console or using the AWS CLI. Upgrading a Neptune cluster to R7i instances requires a simple instance type modification for Neptune engine versions 1.4.3 or higher. For more information on pricing and regional availability, refer to the Amazon Neptune pricing page.

https://aws.amazon.com/neptune/ now supports R7i database instances powered by custom 4th Generation Intel Xeon Scalable processors. R7i instances offer larger instance sizes, up to 48xlarge and features an 8:1 ratio of memory to vCPU, and the latest DDR5 memory. These instances are now available in the following AWS Regions: US East (N. Virginia, Ohio), US West (N. California, Oregon), Asia Pacific (Jakarta, Mumbai, Seoul, Singapore, Sydney, Tokyo), Canada (Central), and Europe (Frankfurt, Ireland, London, Paris, Spain, Stockholm), and engine versions 1.4.3 or above. Amazon Neptune is a fast, reliable, fully managed graph database service that makes it easier to build and run applications that work with highly connected datasets. Compared to previous generation R6i instances, the R7i instances deliver up to 15% better price performance, powering your graph use cases such as fraud graphs, knowledge graphs, customer 360 graphs, and security graphs. You can launch R7i instances for Neptune using the https://console.aws.amazon.com/neptune/ or using the https://awscli.amazonaws.com/v2/documentation/api/latest/reference/neptune/index.html. Upgrading a Neptune cluster to R7i instances requires a simple instance type modification for Neptune engine versions 1.4.3 or higher. For more information on pricing and regional availability, refer to the https://aws.amazon.com/neptune/pricing/.  

Today, we’re announcing the integration of Amazon Neptune with Zep, an open-source memory server for LLM applications. Zep enables developers to persist, retrieve, and enrich user interaction history, providing long-term memory and context for AI agents. With this launch, customers can now use Neptune Database or Neptune Analytics as the underlying graph store and Amazon Open Search as the text-search store for Zep’s memory system, enabling graph-powered memory retrieval and reasoning. This integration makes it easier to build LLM agents with long-term memory, context, and reasoning. Zep users can now store and query memory graphs at scale, unlocking multi-hop reasoning and hybrid retrieval across graph, vector, and keyword modalities. By combining Zep’s memory orchestration with Neptune’s graph-native knowledge representation, developers can build more personalized, context-aware, and intelligent LLM applications. Zep helps applications remember user interactions, extract structured knowledge, and reason across memory—making it easier to build LLM agents that improve over time. To learn more about the Neptune–Zep integration, check the sample Notebook.

https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html is now available in the AWS Canada (Central) and Australia (Sydney) Regions. You can now create and manage Neptune Analytics graphs in the AWS Canada (Central) and Australia (Sydney) Regions and run advanced graph analytics and vector similarity search. Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds. To analyze graph data quickly and easily, Neptune Analytics stores large graph datasets in memory. It supports a library of optimized graph analytic algorithms, low-latency graph queries, and vector search capabilities within graph traversals. Neptune Analytics is an ideal choice for investigatory, exploratory, or data-science workloads that require fast iteration for data, analytical and algorithmic processing, or vector search on graph data. It complements https://docs.aws.amazon.com/neptune/latest/userguide/intro.html, a popular managed graph database. To perform intensive analysis, you can load the data from a Neptune Database graph or snapshot into Neptune Analytics. You can also load graph data that's stored in Amazon S3. To get started, you can create a new Neptune Analytics graphs using the https://ca-central-1.console.aws.amazon.com/neptune/home?region=ca-central-1#analytics-graphs:, https://docs.aws.amazon.com/cli/latest/reference/neptune-graph/. For more information on pricing and region availability, refer to the https://aws.amazon.com/neptune/pricing/ and https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/. 

Amazon Neptune Database is now available in the Europe (Zurich) Region on engine versions 1.4.5.0 and later. You can now create Neptune clusters using R5, R5d, R6g, R6i, X2iedn, T4g, and T3 instance types in the AWS Europe (Zurich) Region. Amazon Neptune Database is a fast, reliable, and fully managed graph database as a service that makes it easy to build and run applications work with highly connected datasets. You can build applications using Apache TinkerPop Gremlin or openCypher on the Property Graph model, or using the SPARQL query language on W3C Resource Description Framework (RDF). Neptune also offers enterprise features such as high availability, automated backups, and network isolation to help customers quickly deploy applications to production. To get started, you can create a new Neptune cluster using the AWS Management Console, AWS CLI, or a quickstart AWS CloudFormation template. For more information on pricing and region availability, refer to the Neptune pricing page and AWS Region Table.

https://aws.amazon.com/neptune/ Database is now available in the Europe (Zurich) Region on engine versions 1.4.5.0 and later. You can now create Neptune clusters using R5, R5d, R6g, R6i, X2iedn, T4g, and T3 instance types in the AWS Europe (Zurich) Region. Amazon Neptune Database is a fast, reliable, and fully managed graph database as a service that makes it easy to build and run applications work with highly connected datasets. You can build applications using Apache TinkerPop Gremlin or openCypher on the Property Graph model, or using the SPARQL query language on W3C Resource Description Framework (RDF). Neptune also offers enterprise features such as high availability, automated backups, and network isolation to help customers quickly deploy applications to production. To get started, you can create a new Neptune cluster using the https://console.aws.amazon.com/neptune, https://awscli.amazonaws.com/v2/documentation/api/latest/reference/neptune/create-db-cluster.html, or a https://docs.aws.amazon.com/neptune/latest/userguide/get-started-create-cluster.html#get-started-cfn-create AWS CloudFormation template. For more information on pricing and region availability, refer to the https://aws.amazon.com/neptune/pricing/ and https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/.

https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html is now available in the Asia Pacific (Mumbai) Region. You can now create and manage Neptune Analytics graphs in the Asia Pacific (Mumbai) Region and run advanced graph analytics. Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds. To analyze graph data quickly and easily, Neptune Analytics stores large graph datasets in memory. It supports a library of optimized graph analytic algorithms, low-latency graph queries, and vector search capabilities within graph traversals. Neptune Analytics is an ideal choice for investigatory, exploratory, or data-science workloads that require fast iteration for data, analytical and algorithmic processing, or vector search on graph data. It complements Amazon Neptune Database, a popular managed graph database. To perform intensive analysis, you can load the data from a Neptune Database graph or snapshot into Neptune Analytics. You can also load graph data that's stored in Amazon S3. To get started, you can create a new Neptune Analytics graphs using the https://ap-south-1.console.aws.amazon.com/neptune/home?region=ap-south-1#analytics-graphs:, or AWS CLI. For more information on pricing and region availability, refer to the https://aws.amazon.com/neptune/pricing/.

Today, we are announcing the support of Bring Your Own Knowledge Graph (BYOKG) for Retrieval-Augmented Generation (RAG) using the open-source GraphRAG Toolkit. This new capability allows customers to connect their existing knowledge graphs to large language models (LLMs), enabling Generative AI applications that deliver more accurate, context-rich, and explainable responses grounded in trusted, structured data. Previously, customers who wanted to use their own curated graphs for RAG had to build custom pipelines and retrieval logic to integrate graph queries into generative AI workflows. With BYOKG support, developers can now directly leverage their domain-specific graphs, such as those stored in Amazon Neptune Database or Neptune Analytics, through the GraphRAG https://github.com/awslabs/graphrag-toolkit. This makes it easier to operationalize graph-aware RAG, reducing hallucinations and improving reasoning over multi-hop and temporal relationships. For example, a fraud investigation assistant can query a financial services company’s knowledge graph to surface suspicious transaction patterns and provide analysts with contextual explanations. Similarly, a telecom operations chatbot can detect that a series of linked cell towers are consistently failing, trace the dependency paths to affected network switches, and then guide technicians using SOP documents on how to resolve the issue. Developers simply configure the GraphRAG Toolkit with their existing graph data source, and it will orchestrate retrieval strategies that use graph queries alongside vector search to enhance generative AI outputs. To learn more and get started, visit the GraphRAG https://github.com/awslabs/graphrag-toolkit/tree/main/byokg-rag.