diff --git a/README.md b/README.md index 530c4c1c7e..dff0ed0991 100644 --- a/README.md +++ b/README.md @@ -367,7 +367,7 @@ Inner shortcode Tags let you display badges, usually below a headline. This is mainly used for pointing out if a feature is only available in the -GenAI Suite, the Data Platform, the Arango Managed Platform (AMP), or multiple +AI Services, the Data Platform, the Arango Managed Platform (AMP), or multiple of them. See [Environment remarks](#environment-remarks) for details. It is also used for [Edition remarks](#edition-remarks) in content before @@ -677,15 +677,15 @@ Pages and sections about features that are only available in certain environment such as in ArangoDB Shell should indicate where they are available using the `tag` shortcode. -Features exclusive to the Data Platform, GenAI Data Platform, +Features exclusive to the Data Platform, AI Services Data Platform, Arango Managed Platform (AMP), and ArangoDB generally don't need to be tagged because they are in dedicated parts of the documentation. However, if there are subsections with different procedures, each can be tagged accordingly. -In the GenAI Data Platform only: +In the AI Services Data Platform only: ```markdown -{{< tag "GenAI Data Platform" >}} +{{< tag "AI Services Data Platform" >}} ``` In the Arango Managed Platform only: diff --git a/site/content/ai-services/_index.md b/site/content/ai-services/_index.md new file mode 100644 index 0000000000..0b5897e9f8 --- /dev/null +++ b/site/content/ai-services/_index.md @@ -0,0 +1,36 @@ +--- +title: AI Services +menuTitle: AI Services +weight: 2 +description: >- + A comprehensive AI solution that transforms your data into intelligent knowledge graphs with GraphRAG capabilities, applies advanced machine learning with GraphML, and provides enterprise-grade tools for analytics, natural language querying, and AI-powered insights, all through an intuitive web interface +--- + +## What's included + +AI Services are comprised of two major components: + +- [**GraphRAG**](./graphrag/_index.md): A complete solution for extracting entities + from text files to create a knowledge graph that you can then query with a + natural language interface. +- [**GraphML**](./graphml/_index.md): Apply machine learning to graphs for link prediction, + classification, and similar tasks. + +Each component has an intuitive graphical user interface integrated into the +Arango Data Platform web interface, guiding you through the process. + +Alongside these components, you also get the following additional features: + +- [**Graph Analytics**](graph-analytics.md): Run graph algorithms such as PageRank + on dedicated compute resources. +- [**Jupyter notebooks**](notebook-servers.md): Run a Jupyter kernel in the platform for hosting + interactive notebooks for experimentation and development of applications + that use ArangoDB as their backend. +- **Public and private LLM support**: Use public LLMs such as OpenAI + or private LLMs with [Triton Inference Server](reference/triton-inference-server.md). +- [**MLflow integration**](reference/mlflow.md): Use the popular MLflow as a model registry for private LLMs + or to run machine learning experiments as part of the Arango Data Platform. +- **Application Programming Interfaces**: Use the underlying APIs of the + AI Services and build your own integrations. See the + [API reference](https://arangoml.github.io/platform-dss-api/GenAI-Service/proto/index.html) documentation + for more details. diff --git a/site/content/gen-ai/graph-analytics.md b/site/content/ai-services/graph-analytics.md similarity index 96% rename from site/content/gen-ai/graph-analytics.md rename to site/content/ai-services/graph-analytics.md index 3108fb1fbc..94eb642d60 100644 --- a/site/content/gen-ai/graph-analytics.md +++ b/site/content/ai-services/graph-analytics.md @@ -17,7 +17,7 @@ and network flow analysis. ArangoDB offers a feature for running algorithms on your graph data, called Graph Analytics Engines (GAEs). It is available on request for the [Arango Managed Platform (AMP)](https://dashboard.arangodb.cloud/home?utm_source=docs&utm_medium=cluster_pages&utm_campaign=docs_traffic) -and included in the [ArangoDB Platform](../data-platform/about/_index.md). +and included in the [Arango Data Platform](../data-platform/_index.md). Key features: @@ -40,11 +40,11 @@ How to perform the steps is detailed in the subsequent sections. {{< tabs "platforms" >}} -{{< tab "ArangoDB Platform" >}} +{{< tab "Arango Data Platform" >}} 1. Determine the approximate size of the data that you will load into the GAE and ensure the machine to run the engine on has sufficient memory. The data as well as the temporarily needed space for computations and results needs to fit in memory. -2. [Start a `graphanalytics` service](#start-a-graphanalytics-service) via the GenAI service +2. [Start a `graphanalytics` service](#start-a-graphanalytics-service) via the AI service that manages various Platform components for graph intelligence and machine learning. It only takes a few seconds until the engine service can be used. The engine runs adjacent to the pods of the ArangoDB Core. @@ -88,9 +88,9 @@ Single server deployments using ArangoDB version 3.11 are not supported. {{< tabs "platforms" >}} -{{< tab "ArangoDB Platform" >}} -You can use any of the available authentication methods the ArangoDB Platform -supports to start and stop `graphanalytics` services via the GenAI service as +{{< tab "Arango Data Platform" >}} +You can use any of the available authentication methods the Arango Data Platform +supports to start and stop `graphanalytics` services via the AI service as well as to authenticate requests to the [Engine API](#engine-api). - HTTP Basic Authentication @@ -129,30 +129,30 @@ setting in ArangoGraph: The interface for managing the engines depends on the environment you use: -- **ArangoDB Platform**: [GenAI service](#genai-service) +- **Arango Data Platform**: [AI service](#ai-service) - **ArangoGraph**: [Management API](#management-api) -### GenAI service +### AI service -{{< tag "GenAI Data Platform" >}} +{{< tag "AI Services Data Platform" >}} -GAEs are deployed and deleted via the [GenAI service](services/gen-ai.md) -in the ArangoDB Platform. +GAEs are deployed and deleted via the [AI service](reference/gen-ai.md) +in the Arango Data Platform. If you use cURL, you need to use the `-k` / `--insecure` option for requests if the Platform deployment uses a self-signed certificate (default). #### Start a `graphanalytics` service -`POST /gen-ai/v1/graphanalytics` +`POST /ai/v1/graphanalytics` -Start a GAE via the GenAI service with an empty request body: +Start a GAE via the AI service with an empty request body: ```sh # Example with a JWT session token ADB_TOKEN=$(curl -sSk -d '{"username":"root", "password": ""}' -X POST https://127.0.0.1:8529/_open/auth | jq -r .jwt) -Service=$(curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X POST https://127.0.0.1:8529/gen-ai/v1/graphanalytics) +Service=$(curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X POST https://127.0.0.1:8529/ai/v1/graphanalytics) ServiceID=$(echo "$Service" | jq -r ".serviceInfo.serviceId") if [[ "$ServiceID" == "null" ]]; then echo "Error starting gral engine" @@ -164,21 +164,21 @@ echo "$Service" | jq #### List the services -`POST /gen-ai/v1/list_services` +`POST /ai/v1/list_services` -You can list all running services managed by the GenAI service, including the +You can list all running services managed by the AI service, including the `graphanalytics` services: ```sh -curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X POST https://127.0.0.1:8529/gen-ai/v1/list_services | jq +curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X POST https://127.0.0.1:8529/ai/v1/list_services | jq ``` #### Stop a `graphanalytics` service -Delete the desired engine via the GenAI service using the service ID: +Delete the desired engine via the AI service using the service ID: ```sh -curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X DELETE https://127.0.0.1:8529/gen-ai/v1/service/$ServiceID | jq +curl -sSk -H "Authorization: bearer $ADB_TOKEN" -X DELETE https://127.0.0.1:8529/ai/v1/service/$ServiceID | jq ``` ### Management API @@ -309,12 +309,12 @@ curl -H "Authorization: bearer $ARANGO_GRAPH_TOKEN" -X DELETE "$BASE_URL/engines {{< tabs "platforms" >}} -{{< tab "ArangoDB Platform" >}} +{{< tab "Arango Data Platform" >}} To determine the base URL of the engine API, use the base URL of the Platform deployment and append `/gral/`, e.g. `https://127.0.0.1:8529/gral/arangodb-gral-tqcge`. -The service ID is returned by the call to the GenAI service for +The service ID is returned by the call to the AI service for [starting the `graphanalytics` service](#start-a-graphanalytics-service). You can also list the service IDs like so: diff --git a/site/content/gen-ai/graph-to-ai.md b/site/content/ai-services/graph-to-ai.md similarity index 68% rename from site/content/gen-ai/graph-to-ai.md rename to site/content/ai-services/graph-to-ai.md index b8bee3415d..009cdc0b37 100644 --- a/site/content/gen-ai/graph-to-ai.md +++ b/site/content/ai-services/graph-to-ai.md @@ -1,17 +1,16 @@ --- -title: Generative Artificial Intelligence (GenAI) and Data Science -menuTitle: GenAI & Data Science +title: From Graph to AI +menuTitle: From Graph to AI weight: 25 description: >- ArangoDB's set of tools and technologies enables analytics, machine learning, - and GenAI applications powered by graph data + and AI applications powered by graph data aliases: - data-science/overview --- -- [Link to 3.12](../arangodb/3.12/aql/_index.md) {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -21,7 +20,7 @@ data science applications. The core database system includes multi-model storage of information with scalable graph and information retrieval capabilities that you can directly use for your research and product development. -ArangoDB also offers a dedicated GenAI Suite, using the database core +ArangoDB also offers dedicated AI Services, using the database core as the foundation for higher-level features. Whether you want to turbocharge generative AI applications with a GraphRAG solution or apply analytics and machine learning to graph data at scale, ArangoDB covers these needs. @@ -33,45 +32,6 @@ engineering space can make use of ArangoDB's set of tools and technologies that enable analytics and machine learning on graph data. --> -## GenAI Suite - -The GenAI Suite is comprised of two major components: - -- [**GraphRAG**](#graphrag): A complete solution for extracting entities - from text files to create a knowledge graph that you can then query with a - natural language interface. -- [**GraphML**](#graphml): Apply machine learning to graphs for link prediction, - classification, and similar tasks. - -Each component has an intuitive graphical user interface integrated into the -ArangoDB Platform web interface, guiding you through the process. - -Alongside these components, you also get the following additional features: - -- [**Graph Visualizer**](../data-platform/graph-visualizer.md): A web-based tool for exploring your graph data with an - intuitive interface and sophisticated querying capabilities. -- [**Jupyter notebooks**](notebook-servers.md): Run a Jupyter kernel in the platform for hosting - interactive notebooks for experimentation and development of applications - that use ArangoDB as their backend. -- **Public and private LLM support**: Use public LLMs such as OpenAI - or private LLMs with [Triton Inference Server](services/triton-inference-server.md). -- [**MLflow integration**](services/mlflow.md): Use the popular MLflow as a model registry for private LLMs - or to run machine learning experiments as part of the ArangoDB Platform. -- [**Adapters**](../ecosystem/adapters/_index.md): Use ArangoDB together with cuGraph, NetworkX, - and other data science tools. -- **Application Programming Interfaces**: Use the underlying APIs of the - GenAI Suite services and build your own integrations. See the - [API reference](https://arangoml.github.io/platform-dss-api/GenAI-Service/proto/index.html) documentation - for more details. - -## Other tools and features - -The ArangoDB Platform includes the following features independent of the -GenAI Suite: - -- [**Graph Analytics**](graph-analytics.md): Run graph algorithms such as PageRank - on dedicated compute resources. - ## From graph to AI This section classifies the complexity of the queries you can answer with diff --git a/site/content/gen-ai/graphml/_index.md b/site/content/ai-services/graphml/_index.md similarity index 99% rename from site/content/gen-ai/graphml/_index.md rename to site/content/ai-services/graphml/_index.md index c1262bbdcc..a636fe9901 100644 --- a/site/content/gen-ai/graphml/_index.md +++ b/site/content/ai-services/graphml/_index.md @@ -8,7 +8,7 @@ aliases: - arangographml --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} diff --git a/site/content/gen-ai/graphml/notebooks-api.md b/site/content/ai-services/graphml/notebooks-api.md similarity index 99% rename from site/content/gen-ai/graphml/notebooks-api.md rename to site/content/ai-services/graphml/notebooks-api.md index f34d9121b6..1c30cd27f3 100644 --- a/site/content/gen-ai/graphml/notebooks-api.md +++ b/site/content/ai-services/graphml/notebooks-api.md @@ -9,7 +9,7 @@ aliases: - ../arangographml/getting-started - ../arangographml-getting-started-with-arangographml --- -The ArangoDB Platform provides an easy-to-use & scalable interface to run +The Arango Data Platform provides an easy-to-use & scalable interface to run Graph Machine Learning on ArangoDB data. Since all the orchestration and Machine Learning logic is managed by ArangoDB, all that is typically required are JSON specifications outlining individual processes to solve a Machine Learning task. @@ -80,7 +80,7 @@ news sources, and locations are interconnected into a large graph. ![Example Event](../../images/ArangoML_open_intelligence_visualization.png) The [`arango-datasets`](../../arangodb/3.12/components/tools/arango-datasets.md) Python package -allows you to load pre-defined datasets into ArangoDB Platform. It comes pre-installed in the +allows you to load pre-defined datasets into Arango Data Platform. It comes pre-installed in the GraphML notebook environment. ```py diff --git a/site/content/gen-ai/graphml/quickstart.md b/site/content/ai-services/graphml/quickstart.md similarity index 85% rename from site/content/gen-ai/graphml/quickstart.md rename to site/content/ai-services/graphml/quickstart.md index db81915e98..e9d0cd164f 100644 --- a/site/content/gen-ai/graphml/quickstart.md +++ b/site/content/ai-services/graphml/quickstart.md @@ -3,14 +3,14 @@ title: How to get started with GraphML menuTitle: Quickstart weight: 5 description: >- - You can use GraphML straight within the ArangoDB Platform, via the web interface + You can use GraphML straight within the Arango Data Platform, via the web interface or via Notebooks aliases: - ../arangographml/deploy --- ## Web interface versus Jupyter Notebooks -The ArangoDB Platform provides enterprise-ready Graph Machine Learning in two options, +The Arango Data Platform provides enterprise-ready Graph Machine Learning in two options, tailored to suit diverse requirements and preferences: - Using the web interface - In a scriptable manner, using the integrated Jupyter Notebooks and the HTTP API for GraphML @@ -20,7 +20,7 @@ tailored to suit diverse requirements and preferences: {{< tabs "graphml-setup" >}} {{< tab "Web Interface" >}} -The web interface of the ArangoDB Platform allows you to create, configure, and +The web interface of the Arango Data Platform allows you to create, configure, and run a full machine learning workflow for GraphML. To get started, see the [Web interface for GraphML](ui.md) page. {{< /tab >}} diff --git a/site/content/gen-ai/graphml/ui.md b/site/content/ai-services/graphml/ui.md similarity index 98% rename from site/content/gen-ai/graphml/ui.md rename to site/content/ai-services/graphml/ui.md index 8c4e43024e..042e7e9936 100644 --- a/site/content/gen-ai/graphml/ui.md +++ b/site/content/ai-services/graphml/ui.md @@ -1,5 +1,5 @@ --- -title: How to use GraphML in the ArangoDB Platform web interface +title: How to use GraphML in the Arango Data Platform web interface menuTitle: Web Interface weight: 10 description: >- @@ -19,10 +19,10 @@ giving you a clear path from data to prediction: ## Create a GraphML project -To create a new GraphML project using the ArangoDB Platform web interface, follow these steps: +To create a new GraphML project using the Arango Data Platform web interface, follow these steps: 1. From the left-hand sidebar, select the database where you want to create the project. -2. In the left-hand sidebar, click **GenAI Suite** to open the GraphML project management interface, then click **Run GraphML**. +2. In the left-hand sidebar, click **AI Services** to open the GraphML project management interface, then click **Run GraphML**. ![Create GraphML Project](../../images/create-graphml-project-ui.png) 3. In the **GraphML projects** view, click **Add new project**. 4. The **Create ML project** modal opens. Enter a **Name** for your machine learning project. diff --git a/site/content/ai-services/graphrag/_index.md b/site/content/ai-services/graphrag/_index.md new file mode 100644 index 0000000000..5fea31289b --- /dev/null +++ b/site/content/ai-services/graphrag/_index.md @@ -0,0 +1,60 @@ +--- +title: GraphRAG +menuTitle: GraphRAG +weight: 5 +description: >- + ArangoDB's GraphRAG solution combines graph-based retrieval-augmented generation + with Large Language Models (LLMs) for turbocharged AI solutions +aliases: + llm-knowledge-graphs +--- +{{< tip >}} +The Arango Data Platform & AI Services are available as a pre-release. To get +exclusive early access, [get in touch](https://arangodb.com/contact/) with +the ArangoDB team. +{{< /tip >}} + +## Transform unstructured documents into intelligent knowledge graphs + +ArangoDB's GraphRAG solution enables organizations to extract meaningful insights +from their document collections by creating knowledge graphs that capture not just +individual facts, but the intricate relationships between concepts across documents. +This approach goes beyond traditional RAG systems by understanding document +interconnections and providing both granular detail-level responses and high-level +conceptual understanding. + +- **Intelligent document understanding**: Automatically extracts and connects knowledge across multiple document sources +- **Contextual intelligence**: Maintains relationships between concepts, enabling more accurate and comprehensive responses +- **Multi-level insights**: Provides both detailed technical answers and strategic high-level understanding +- **Seamless knowledge access**: Natural language interface for querying complex document relationships + +## Key benefits for enterprise applications + +- **Cross-document relationship intelligence**: +Unlike traditional RAG systems that treat documents in isolation, ArangoDB's GraphRAG +pipeline detects and leverages references between documents and chunks. This enables +more accurate responses by understanding how concepts relate across your entire knowledge base. + +- **Multi-level understanding architecture**: +The system provides both detailed technical responses and high-level strategic insights +from the same knowledge base, adapting response depth based on query complexity and user intent. + +- **Reference-aware knowledge graph**: +GraphRAG automatically detects and maps relationships between document chunks while +maintaining context of how information connects across different sources. + +- **Dynamic knowledge evolution**: +The system learns and improves understanding as more documents are added, with +relationships and connections becoming more sophisticated over time. + + +## What's next + +- **[GraphRAG Enterprise Use Cases](use-cases.md)**: Understand the business value through real-world scenarios. +- **[GraphRAG Technical Overview](technical-overview.md)**: Dive into the architecture, services, and implementation details. +- **[GraphRAG Web Interface](web-interface.md)**: Try GraphRAG using the interactive web interface. +- **[GraphRAG Tutorial using integrated Notebook servers](tutorial-notebook.md)**: Follow hands-on examples and implementation guidance via Jupyter Notebooks. + +For deeper implementation details, explore the individual services: +- **[Importer Service](../reference/importer.md)**: Transform documents into knowledge graphs. +- **[Retriever Service](../reference/retriever.md)**: Query and extract insights from your knowledge graphs. diff --git a/site/content/gen-ai/graphrag/_index.md b/site/content/ai-services/graphrag/technical-overview.md similarity index 92% rename from site/content/gen-ai/graphrag/_index.md rename to site/content/ai-services/graphrag/technical-overview.md index 8588300420..846ef4f164 100644 --- a/site/content/gen-ai/graphrag/_index.md +++ b/site/content/ai-services/graphrag/technical-overview.md @@ -1,15 +1,14 @@ --- -title: GraphRAG -menuTitle: GraphRAG -weight: 5 +title: GraphRAG Technical Overview +menuTitle: Technical Overview +weight: 15 description: >- - ArangoDB's GraphRAG solution combines graph-based retrieval-augmented generation - with Large Language Models (LLMs) for turbocharged GenAI solutions -aliases: - llm-knowledge-graphs + Technical overview of ArangoDB's GraphRAG solution, including + architecture, services, and deployment options --- + {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The ArangoDB Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -34,7 +33,7 @@ ArangoDB's unique capabilities and flexible integration of knowledge graphs and LLMs provide a powerful and efficient solution for anyone seeking to extract valuable insights from diverse datasets. -The GraphRAG component of the GenAI Suite brings all the capabilities +The GraphRAG component of AI Services brings all the capabilities together with an easy-to-use interface, so you can make the knowledge accessible to your organization. @@ -76,7 +75,7 @@ information in a structured graph format, allowing efficient querying and retrie 3. Store the generated Knowledge Graph in the database for retrieval and reasoning. For detailed information about the service, see the -[Importer](../services/importer.md) service documentation. +[Importer](../reference/importer.md) service documentation. ### Extract information from the Knowledge Graph @@ -87,7 +86,7 @@ You can extract information from Knowledge Graphs using two distinct methods: - Local retrieval For detailed information about the service, see the -[Retriever](../services/retriever.md) service documentation. +[Retriever](../reference/retriever.md) service documentation. #### Global retrieval @@ -134,7 +133,7 @@ collection, and then it expands that subgraph over related entities, relations If you're working in an air-gapped environment or need to keep your data private, you can use the private LLM mode with -[Triton Inference Server](../services/triton-inference-server.md). +[Triton Inference Server](../reference/triton-inference-server.md). This option allows you to run the service completely within your own infrastructure. The Triton Inference Server is a crucial component when diff --git a/site/content/gen-ai/graphrag/tutorial-notebook.md b/site/content/ai-services/graphrag/tutorial-notebook.md similarity index 98% rename from site/content/gen-ai/graphrag/tutorial-notebook.md rename to site/content/ai-services/graphrag/tutorial-notebook.md index 1bbcfebf8d..ffadbad182 100644 --- a/site/content/gen-ai/graphrag/tutorial-notebook.md +++ b/site/content/ai-services/graphrag/tutorial-notebook.md @@ -3,10 +3,10 @@ title: GraphRAG Notebook Tutorial menuTitle: Notebook Tutorial description: >- Building a GraphRAG pipeline using ArangoDB's integrated notebook servers -weight: 10 +weight: 25 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -199,9 +199,9 @@ pprint(importerResponse) Once the importer service has processed the document, you can visualize and interact with the generated Knowledge Graph using the [Graph Visualizer](../../data-platform/graph-visualizer.md) -directly from the ArangoDB Platform web interface. +directly from the Arango Data Platform web interface. -1. In the ArangoDB Platform web interface, select the database you have previously used. +1. In the Arango Data Platform web interface, select the database you have previously used. 2. Click **Graphs** in the main navigation. 3. Select the graph named **Knowledge Graph** from the list. 4. The viewport of the Graph Visualizer opens for exploring the graph. diff --git a/site/content/ai-services/graphrag/use-cases.md b/site/content/ai-services/graphrag/use-cases.md new file mode 100644 index 0000000000..9b08fe169d --- /dev/null +++ b/site/content/ai-services/graphrag/use-cases.md @@ -0,0 +1,87 @@ +--- +title: GraphRAG Use Cases +menuTitle: Use Cases +weight: 10 +description: >- + Real-world enterprise use cases for ArangoDB's GraphRAG solution and + comparison with traditional RAG approaches, including business benefits + and practical applications +--- + +## GraphRAG Enterprise Use Cases + +Whether you are evaluating GraphRAG for your organization or looking to understand +its business applications, these real-world scenarios demonstrate how GraphRAG can transform the way you extract insights from your data. + +### Enterprise knowledge management + +**Scenario**: A consulting firm has accumulated thousands of PDF reports, research papers, +and client documents over years. Team members struggle to find relevant information +quickly and often miss connections between different projects. + +**GraphRAG solution**: The pipeline processes all documents, creating a knowledge graph +that understands how concepts relate across different projects and time periods. Team +members can now ask questions like "What approaches have we used for supply chain +optimization across different industries?" and get comprehensive answers that reference +multiple documents and projects. + +**Business value**: +- Reduces research time by 70% +- Improves proposal quality by leveraging past insights +- Enables knowledge sharing across teams + +### Research and development + +**Scenario**: A pharmaceutical company's R&D team needs to analyze research papers, +clinical trial data, and regulatory documents to identify potential drug interactions +and development pathways. + +**GraphRAG solution**: The system processes all research documents, clinical data, and +regulatory information, creating connections between different studies and findings. +Researchers can query complex relationships like "What are the common side effects +mentioned across all Phase II trials for similar compounds?" + +**Business value**: +- Accelerates research insights +- Reduces risk of missing critical connections +- Improves decision-making speed + +### Legal document analysis + +**Scenario**: A law firm needs to analyze case law, legal precedents, and client +documents to build comprehensive legal strategies. + +**GraphRAG solution**: The pipeline processes legal documents, creating a knowledge +graph that understands legal precedents, case relationships, and argument patterns. +Lawyers can ask complex questions like "How have similar contract disputes been +resolved in different jurisdictions?" + +**Business value**: +- Improves case preparation quality +- Reduces research time +- Enables more comprehensive legal strategies + +## GraphRAG versus Traditional RAG (VectorRAG) + +Traditional RAG systems find text chunks that are semantically similar to your query. +However, they don't understand the inherent relationships between these chunks. + +For example, when asked, "What is the fix for Issue A?", a VectorRAG system might +retrieve two separate, unstructured chunks: one describing "Issue A" and another +mentioning a "Fix 1" for a related system. Because the connection isn't explicit, +the LLM cannot confidently link them and will often default to a safe, unhelpful answer: + +**VectorRAG Response**: _"The context does not provide a specific fix for Issue A."_ + +GraphRAG overcomes this limitation by retrieving a subgraph of interconnected data. +Instead of just text, it provides the LLM with a clear map of how information is related. + +For the same question, GraphRAG fetches structured triplets (node-relationship-node), +such as `(Issue A) -> [HAS_FIX] -> (Fix 1)`. This context is unambiguous, it explicitly +states the relationship between the problem and the solution, allowing the LLM to +provide a direct and correct answer: + +**GraphRAG Response**: _"The fix for Issue A is Fix 1."_ + +The key difference is that VectorRAG gives the LLM a pile of ingredients, while GraphRAG +provides the actual recipe. \ No newline at end of file diff --git a/site/content/gen-ai/graphrag/web-interface.md b/site/content/ai-services/graphrag/web-interface.md similarity index 88% rename from site/content/gen-ai/graphrag/web-interface.md rename to site/content/ai-services/graphrag/web-interface.md index 47e76c67b4..f9297b6d23 100644 --- a/site/content/gen-ai/graphrag/web-interface.md +++ b/site/content/ai-services/graphrag/web-interface.md @@ -1,13 +1,13 @@ --- -title: How to use GraphRAG in the ArangoDB Platform web interface +title: How to use GraphRAG in the Arango Data Platform web interface menuTitle: Web Interface -weight: 5 +weight: 20 description: >- Learn how to create, configure, and run a full GraphRAG workflow in four steps using the Platform web interface --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -23,10 +23,10 @@ The entire process is organized into sequential steps within a **Project**: ## Create a GraphRAG project -To create a new GraphRAG project using the ArangoDB Platform web interface, follow these steps: +To create a new GraphRAG project using the Arango Data Platform web interface, follow these steps: 1. From the left-hand sidebar, select the database where you want to create the project. -2. In the left-hand sidebar, click **GenAI Suite** to open the GraphRAG project management +2. In the left-hand sidebar, click **AI Services** to open the GraphRAG project management interface, then click **Run GraphRAG**. 3. In the **GraphRAG projects** view, click **Add new project**. 4. The **Create GraphRAG project** modal opens. Enter a **Name** and optionally @@ -75,7 +75,7 @@ while OpenAI is used for the embedding model. 3. Click the **Start importer service** button. {{< info >}} -Note that you must first register your model in MLflow. The [Triton LLM Host](../services/triton-inference-server.md) +Note that you must first register your model in MLflow. The [Triton LLM Host](../reference/triton-inference-server.md) service automatically downloads and loads models from the MLflow registry. {{< /info >}} @@ -84,7 +84,7 @@ service automatically downloads and loads models from the MLflow registry. {{< /tabs >}} -See also the [GraphRAG Importer](../services/importer.md) service documentation. +See also the [GraphRAG Importer](../reference/importer.md) service documentation. ## Upload your file @@ -145,7 +145,7 @@ while OpenAI is used for the embedding model. 3. Click the **Start retriever service** button. {{< info >}} -Note that you must first register your model in MLflow. The [Triton LLM Host](../services/triton-inference-server.md) +Note that you must first register your model in MLflow. The [Triton LLM Host](../reference/triton-inference-server.md) service automatically downloads and loads models from the MLflow registry. {{< /info >}} @@ -154,14 +154,14 @@ service automatically downloads and loads models from the MLflow registry. {{< /tabs >}} -See also the [GraphRAG Retriever](../services/retriever.md) documentation. +See also the [GraphRAG Retriever](../reference/retriever.md) documentation. ## Chat with your Knowledge Graph The Retriever service provides two search methods: -- [Local search](../services/retriever.md#local-search): Local queries let you +- [Local search](../reference/retriever.md#local-search): Local queries let you explore specific nodes and their direct connections. -- [Global search](../services/retriever.md#global-search): Global queries uncover +- [Global search](../reference/retriever.md#global-search): Global queries uncover broader patters and relationships across the entire Knowledge Graph. ![Chat with your Knowledge Graph](../../images/graphrag-ui-chat.png) diff --git a/site/content/gen-ai/notebook-servers.md b/site/content/ai-services/notebook-servers.md similarity index 83% rename from site/content/gen-ai/notebook-servers.md rename to site/content/ai-services/notebook-servers.md index 27a7896fba..fc3c9a0c28 100644 --- a/site/content/gen-ai/notebook-servers.md +++ b/site/content/ai-services/notebook-servers.md @@ -3,23 +3,23 @@ title: Notebook Servers menuTitle: Notebook Servers weight: 20 description: >- - Colocated Jupyter Notebooks within the ArangoDB Platform + Colocated Jupyter Notebooks within the Arango Data Platform aliases: - arangograph-notebooks --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} ArangoDB Notebooks provide a Python-based, Jupyter-compatible interface for building -and experimenting with graph-powered data, GenAI, and graph machine learning +and experimenting with graph-powered data, AI, and graph machine learning workflows directly connected to ArangoDB databases. The notebook servers are -embedded in the ArangoDB Platform ecosystem and offer a +embedded in the Arango Data Platform ecosystem and offer a pre-configured environment where everything, including all the necessary services and configurations, comes preloaded. You don't need to set up or configure the -infrastructure, and can immediately start using the GraphML and GenAI +infrastructure, and can immediately start using the GraphML and AI functionalities. The notebooks are primarily focused on the following solutions: @@ -32,14 +32,14 @@ The notebooks are primarily focused on the following solutions: NetworkX, and other data science tools. The ArangoDB Notebooks include the following: -- Automatically connect to ArangoDB databases and GenAI platform services +- Automatically connect to ArangoDB databases and AI platform services - [Magic commands](../amp/notebooks.md#arangograph-magic-commands) that simplify database interactions - Example notebooks for learning ## Quickstart -1. In the ArangoDB Platform web interface, expand **GenAI Tools** in the +1. In the Arango Data Platform web interface, expand **AI Tools** in the main navigation and click **Notebook servers**. 2. The page displays an overview of the notebook services. Click **New notebook server** to create a new one. diff --git a/site/content/ai-services/reference/_index.md b/site/content/ai-services/reference/_index.md new file mode 100644 index 0000000000..e23683c4ba --- /dev/null +++ b/site/content/ai-services/reference/_index.md @@ -0,0 +1,6 @@ +--- +title: Reference +menuTitle: Reference +description: '' +--- + diff --git a/site/content/gen-ai/services/gen-ai.md b/site/content/ai-services/reference/gen-ai.md similarity index 85% rename from site/content/gen-ai/services/gen-ai.md rename to site/content/ai-services/reference/gen-ai.md index e6bd266480..f0b1ee9bc8 100644 --- a/site/content/gen-ai/services/gen-ai.md +++ b/site/content/ai-services/reference/gen-ai.md @@ -1,20 +1,20 @@ --- -title: GenAI Orchestration Service -menuTitle: GenAI +title: AI Orchestration Service +menuTitle: AI Orchestrator description: >- - The GenAI orchestrator service installs, manages, and runs AI-based services + The AI orchestrator service installs, manages, and runs AI-based services for GraphRAG in your Kubernetes cluster weight: 5 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} ## Overview -The basic operations that the GenAI orchestration service carries out are the following: +The basic operations that the AI orchestration service carries out are the following: - Install a service - Uninstall a service - Get the status of a service @@ -23,7 +23,7 @@ The basic operations that the GenAI orchestration service carries out are the fo Each unique service has its own API endpoint for the deployment. **Endpoint LLM Host:** -`https://:8529/gen-ai/v1/llmhost` +`https://:8529/ai/v1/llmhost` While services have their own unique endpoint, they share the same creation request body and the same response body structure. The `env` field is used @@ -86,7 +86,7 @@ corresponding service documentation. ## Obtaining a Bearer Token -Before you can authenticate with the GenAI service, you need to obtain a +Before you can authenticate with the AI service, you need to obtain a Bearer token. You can generate this token using the ArangoDB authentication API: ```bash @@ -106,7 +106,7 @@ The example below shows how to install, monitor, and uninstall the Importer serv ### Step 1: Installing the service ```bash -curl -X POST https://:8529/gen-ai/v1/graphragimporter \ +curl -X POST https://:8529/ai/v1/graphragimporter \ -H "Authorization: Bearer " \ -H "Content-Type: application/json" \ -d '{ @@ -136,7 +136,7 @@ curl -X POST https://:8529/gen-ai/v1/graphragimporter \ ### Step 2: Checking the service status ```bash -curl -X GET https://:8529/gen-ai/v1/service/arangodb-graphrag-importer-of1ml \ +curl -X GET https://:8529/ai/v1/service/arangodb-graphrag-importer-of1ml \ -H "Authorization: Bearer " ``` @@ -155,7 +155,7 @@ curl -X GET https://:8529/gen-ai/v1/service/arangodb-graphrag- ### Step 3: Uninstalling the service ```bash -curl -X DELETE https://:8529/gen-ai/v1/service/arangodb-graphrag-importer-of1ml \ +curl -X DELETE https://:8529/ai/v1/service/arangodb-graphrag-importer-of1ml \ -H "Authorization: Bearer " ``` @@ -188,17 +188,17 @@ Replace the following values with your actual configuration: ## Service configuration -The GenAI orchestrator service is **started by default**. +The AI orchestrator service is **started by default**. It will be available at the following URL: -`https://:8529/gen-ai/v1/service` +`https://:8529/ai/v1/service` ## Health check To test whether the service is running, you can use the following snippet: ```bash -curl -X GET https://:8529/gen-ai/v1/health +curl -X GET https://:8529/ai/v1/health ``` Expected output on success: `{"status":"OK"}` diff --git a/site/content/gen-ai/services/importer.md b/site/content/ai-services/reference/importer.md similarity index 96% rename from site/content/gen-ai/services/importer.md rename to site/content/ai-services/reference/importer.md index 955f1a68d2..9c118e6d7e 100644 --- a/site/content/gen-ai/services/importer.md +++ b/site/content/ai-services/reference/importer.md @@ -7,7 +7,7 @@ description: >- weight: 10 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -36,7 +36,7 @@ To create a new GraphRAG project, use the `CreateProject` method by sending a provide a `project_description`. ```curl -curl -X POST "https://:8529/gen-ai/v1/project" \ +curl -X POST "https://:8529/ai/v1/project" \ -H "Content-Type: application/json" \ -d '{ "project_name": "docs", @@ -57,7 +57,7 @@ Additional project metadata is accessible via the following endpoint, replacing `` with the actual name of your project: ``` -GET /gen-ai/v1/project_by_name/ +GET /ai/v1/project_by_name/ ``` The endpoint provides comprehensive metadata about your project's components, @@ -94,8 +94,8 @@ The Importer service can be configured to use either: - OpenAI (for public LLM deployments) - OpenRouter (for public LLM deployments) -To start the service, use the GenAI service endpoint `/v1/graphragimporter`. -Please refer to the documentation of [GenAI service](gen-ai.md) for more +To start the service, use the AI service endpoint `/v1/graphragimporter`. +Please refer to the documentation of [AI service](gen-ai.md) for more information on how to use it. ### Using Triton Inference Server (Private LLM) @@ -209,7 +209,7 @@ to send an input file to the Importer service: ``` Replace the following placeholders: - - ``: Your ArangoDB Platform URL. + - ``: Your Arango Data Platform URL. - ``: The URL postfix configured in your deployment. @@ -224,7 +224,7 @@ to send an input file to the Importer service: You can verify the state of the import process via the following endpoint: ``` -GET /gen-ai/v1/project_by_name/ +GET /ai/v1/project_by_name/ ``` For example, the `status` object found within `importerServices` may contain the following diff --git a/site/content/gen-ai/services/mlflow.md b/site/content/ai-services/reference/mlflow.md similarity index 97% rename from site/content/gen-ai/services/mlflow.md rename to site/content/ai-services/reference/mlflow.md index 84d43a6e70..39146ba48b 100644 --- a/site/content/gen-ai/services/mlflow.md +++ b/site/content/ai-services/reference/mlflow.md @@ -3,11 +3,11 @@ title: ArangoDB MLflow Service menuTitle: MLflow description: >- The ArangoDB MLflow Service integrates the MLflow platform for managing the - full machine learning lifecycle into the ArangoDB Platform + full machine learning lifecycle into the Arango Data Platform weight: 25 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} diff --git a/site/content/gen-ai/services/natural-language-to-aql.md b/site/content/ai-services/reference/natural-language-to-aql.md similarity index 97% rename from site/content/gen-ai/services/natural-language-to-aql.md rename to site/content/ai-services/reference/natural-language-to-aql.md index 6d2610dfe0..e73234d162 100644 --- a/site/content/gen-ai/services/natural-language-to-aql.md +++ b/site/content/ai-services/reference/natural-language-to-aql.md @@ -55,11 +55,11 @@ TRITON_TIMEOUT= # Optional ### Starting the Service -To start the service, use GenAI service endpoint `CreateGraphRag`. Please refer to the documentation of GenAI service for more information on how to use it. +To start the service, use AI service endpoint `CreateGraphRag`. Please refer to the documentation of AI service for more information on how to use it. ### Required Parameters -These parameters must be provided in the install request sent to GenAI service. +These parameters must be provided in the install request sent to AI service. - `username`: Database username for authentication - `db_name`: Name of the ArangoDB database diff --git a/site/content/gen-ai/services/retriever.md b/site/content/ai-services/reference/retriever.md similarity index 96% rename from site/content/gen-ai/services/retriever.md rename to site/content/ai-services/reference/retriever.md index 9c1f03c0cd..5aba44eacc 100644 --- a/site/content/gen-ai/services/retriever.md +++ b/site/content/ai-services/reference/retriever.md @@ -7,7 +7,7 @@ description: >- weight: 15 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -84,8 +84,8 @@ entities, or relationships. The Retriever service can be configured to use either the Triton Inference Server (for private LLM deployments) or OpenAI/OpenRouter (for public LLM deployments). -To start the service, use the GenAI service endpoint `/v1/graphragretriever`. -Please refer to the documentation of [GenAI service](gen-ai.md) for more +To start the service, use the AI service endpoint `/v1/graphragretriever`. +Please refer to the documentation of [AI service](gen-ai.md) for more information on how to use it. ### Using Triton Inference Server (Private LLM) @@ -236,7 +236,7 @@ GET /v1/health You can verify the state of the retriever process via the following endpoint: ``` -GET /gen-ai/v1/project_by_name/ +GET /ai/v1/project_by_name/ ``` For example, the `status` object found within `retrieverServices` may contain the following diff --git a/site/content/gen-ai/services/triton-inference-server.md b/site/content/ai-services/reference/triton-inference-server.md similarity index 92% rename from site/content/gen-ai/services/triton-inference-server.md rename to site/content/ai-services/reference/triton-inference-server.md index e1a7ca4112..43b96d4bc4 100644 --- a/site/content/gen-ai/services/triton-inference-server.md +++ b/site/content/ai-services/reference/triton-inference-server.md @@ -6,7 +6,7 @@ description: >- weight: 30 --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -21,7 +21,7 @@ and seamless Kubernetes integration. ## Workflow The Triton LLM Host enables your GraphRAG pipeline to use privately hosted -LLMs directly from the ArangoDB Platform environment. The process involves the +LLMs directly from the Arango Data Platform environment. The process involves the following steps: 1. Install the Triton LLM Host service. @@ -37,14 +37,14 @@ more about the service and how to interact with it. ## Deployment The Triton LLM Host service is deployed as a **Kubernetes application** using Helm charts in -the ArangoDB Platform ecosystem. It integrates with the: +the Arango Data Platform ecosystem. It integrates with the: - MLFlow model registry for model management. - Storage sidecar for artifact storage. -## Installation via GenAI Service API +## Installation via AI Service API To install the Triton LLM Host service, send an API request to the -**GenAI service** using the following parameters: +**AI service** using the following parameters: ### Required parameters @@ -165,18 +165,18 @@ requests for example. Refer to the specific service with which you are using Triton Inference Server for more details. {{< /info >}} -- **Internal access (within ArangoDB Platform)**: +- **Internal access (within Arango Data Platform)**: `https://{SERVICE_ID}.{KUBERNETES_NAMESPACE}.svc:8000` - `KUBERNETES_NAMESPACE` is available as an environment variable. - - `SERVICE_ID` is returned by the GenAI service API. + - `SERVICE_ID` is returned by the AI service API. **Example**: To check server health: `GET https://{SERVICE_ID}.{KUBERNETES_NAMESPACE}.svc:8000/v2/health/ready` -- **External access (outside ArangoDB Platform)**: +- **External access (outside Arango Data Platform)**: `https://{BASE_URL}:8529/llm/{SERVICE_POSTFIX}/` - - `BASE_URL`: Your ArangoDB Platform base URL. + - `BASE_URL`: Your Arango Data Platform base URL. - `SERVICE_POSTFIX`: Last 5 characters of the service ID. **Example**: diff --git a/site/content/amp/_index.md b/site/content/amp/_index.md index e43ab5ae79..991f8e0dd1 100644 --- a/site/content/amp/_index.md +++ b/site/content/amp/_index.md @@ -1,6 +1,6 @@ --- title: Arango Managed Platform (AMP) -menuTitle: Managed Platform +menuTitle: Arango Managed Platform weight: 4 description: >- The Arango Managed Platform (AMP) provides the entire functionality of @@ -8,6 +8,8 @@ description: >- aliases: - arangograph/changelog --- +{{< cloudbanner>}} + The [Arango Managed Platform (AMP)](https://dashboard.arangodb.cloud/home?utm_source=docs&utm_medium=cluster_pages&utm_campaign=docs_traffic), formerly called Oasis, provides ArangoDB databases as a Service (DBaaS). It enables you to use the entire functionality of an ArangoDB cluster diff --git a/site/content/arangodb/3.12/aql/functions/vector.md b/site/content/arangodb/3.12/aql/functions/vector.md index a20c562137..00b711cfec 100644 --- a/site/content/arangodb/3.12/aql/functions/vector.md +++ b/site/content/arangodb/3.12/aql/functions/vector.md @@ -12,7 +12,7 @@ To use vector search, you need to have vector embeddings stored in documents and the attribute that stores them needs to be indexed by a [vector index](../../index-and-search/indexing/working-with-indexes/vector-indexes.md). -You can calculate vector embeddings using [ArangoDB's GraphML](../../../../gen-ai/graphml/_index.md) +You can calculate vector embeddings using [ArangoDB's GraphML](../../../../ai-services/graphml/_index.md) capabilities (available in ArangoGraph) or using external tools. {{< warning >}} diff --git a/site/content/arangodb/3.12/deploy/_index.md b/site/content/arangodb/3.12/deploy/_index.md index 499c517066..cacd720b1a 100644 --- a/site/content/arangodb/3.12/deploy/_index.md +++ b/site/content/arangodb/3.12/deploy/_index.md @@ -43,14 +43,14 @@ on a single DB-Server node for better performance and with transactional guarantees similar to a single server deployment. OneShard is primarily intended for multi-tenant use cases. -### ArangoDB Platform +### Arango Data Platform -The ArangoDB Platform is the umbrella for deploying and operating the entire +The Arango Data Platform is the umbrella for deploying and operating the entire ArangoDB product offering with a unified interface in a Kubernetes cluster. It is offered for self-hosting on-prem or in the cloud and as a managed service, superseding the Arango Managed Platform (AMP). -See [The ArangoDB Platform](../../../data-platform/about/_index.md) for details. +See [The ArangoDB Platform](../../../data-platform/_index.md) for details. ## How to deploy diff --git a/site/content/arangodb/3.12/features/_index.md b/site/content/arangodb/3.12/features/_index.md index 85b1f4bdde..768a1e24f5 100644 --- a/site/content/arangodb/3.12/features/_index.md +++ b/site/content/arangodb/3.12/features/_index.md @@ -22,8 +22,8 @@ aliases: See the full [Feature list of the ArangoDB database system](list.md). For a scalable architecture based on Kubernetes that supports the full offering -of ArangoDB including graph-powered machine learning and GenAI features, see -the [Feature list of the ArangoDB Platform](../../../data-platform/about/features.md). +of ArangoDB including graph-powered machine learning and AI features, see +the [Feature list of the Arango Data Platform](../../../data-platform/features.md). ## On-premises versus Cloud diff --git a/site/content/arangodb/3.12/index-and-search/indexing/working-with-indexes/vector-indexes.md b/site/content/arangodb/3.12/index-and-search/indexing/working-with-indexes/vector-indexes.md index a3e1fbf1bb..1264199e5e 100644 --- a/site/content/arangodb/3.12/index-and-search/indexing/working-with-indexes/vector-indexes.md +++ b/site/content/arangodb/3.12/index-and-search/indexing/working-with-indexes/vector-indexes.md @@ -33,7 +33,7 @@ startup option needs to be enabled on the deployment you want to restore to. {{< /warning >}} 1. Enable the experimental vector index feature. -2. Calculate vector embeddings using [ArangoDB's GraphML](../../../../../gen-ai/graphml/_index.md) +2. Calculate vector embeddings using [ArangoDB's GraphML](../../../../../ai-services/graphml/_index.md) capabilities (available in ArangoGraph) or using external tools. Store each vector as an attribute in the respective document. 3. Create a vector index over this attribute. You need to choose which diff --git a/site/content/arangodb/3.13/aql/functions/vector.md b/site/content/arangodb/3.13/aql/functions/vector.md index a20c562137..00b711cfec 100644 --- a/site/content/arangodb/3.13/aql/functions/vector.md +++ b/site/content/arangodb/3.13/aql/functions/vector.md @@ -12,7 +12,7 @@ To use vector search, you need to have vector embeddings stored in documents and the attribute that stores them needs to be indexed by a [vector index](../../index-and-search/indexing/working-with-indexes/vector-indexes.md). -You can calculate vector embeddings using [ArangoDB's GraphML](../../../../gen-ai/graphml/_index.md) +You can calculate vector embeddings using [ArangoDB's GraphML](../../../../ai-services/graphml/_index.md) capabilities (available in ArangoGraph) or using external tools. {{< warning >}} diff --git a/site/content/arangodb/3.13/components/platform.md b/site/content/arangodb/3.13/components/platform.md index 6e9764fd15..0e7bd3aae1 100644 --- a/site/content/arangodb/3.13/components/platform.md +++ b/site/content/arangodb/3.13/components/platform.md @@ -7,7 +7,7 @@ description: >- solution that you can deploy on-prem or use as a managed service --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The ArangoDB Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -29,7 +29,7 @@ of the platform features. - **Graph Analytics**: A suite of graph algorithms including PageRank, community detection, and centrality measures with support for GPU acceleration thanks to Nvidia cuGraph. -- **GenAI Suite**: A set of machine learning services, APIs, and +- **AI Services**: A set of machine learning services, APIs, and user interfaces that are available as a package as well as individual products. - **GraphML**: A turnkey solution for graph machine learning for prediction use cases such as fraud detection, supply chain, healthcare, retail, and @@ -48,7 +48,7 @@ of the platform features. - **GraphRAG Retriever**: Perform semantic similarity searches or aggregate insights from graph communities with global and local queries. - **Public and private LLM support**: Use public LLMs such as OpenAI - or private LLMs with [Triton Inference Server](../../../gen-ai/services/triton-inference-server.md). + or private LLMs with [Triton Inference Server](../../../ai-services/reference/triton-inference-server.md). - **MLflow integration**: Use the popular MLflow as a model registry for private LLMs or to run machine learning experiments as part of the ArangoDB Platform. - **Jupyter notebooks**: Run a Jupyter kernel in the platform for hosting @@ -78,7 +78,7 @@ manage this deployment yourself. - **Early access to the ArangoDB Platform**: [Get in touch](https://arangodb.com/contact/) with the ArangoDB team to get - exclusive early access to the pre-release of the ArangoDB Platform & GenAI Suite. + exclusive early access to the pre-release of the ArangoDB Platform & AI Services. - **Kubernetes**: Orchestrates the selected services that comprise the ArangoDB Platform, running them in containers for safety and scalability. diff --git a/site/content/arangodb/3.13/deploy/_index.md b/site/content/arangodb/3.13/deploy/_index.md index 2d9787b64c..46114f74fc 100644 --- a/site/content/arangodb/3.13/deploy/_index.md +++ b/site/content/arangodb/3.13/deploy/_index.md @@ -43,14 +43,14 @@ on a single DB-Server node for better performance and with transactional guarantees similar to a single server deployment. OneShard is primarily intended for multi-tenant use cases. -### ArangoDB Platform +### Arango Data Platform -The ArangoDB Platform is the umbrella for deploying and operating the entire +The Arango Data Platform is the umbrella for deploying and operating the entire ArangoDB product offering with a unified interface in a Kubernetes cluster. It is offered for self-hosting on-prem or in the cloud and as a managed service, superseding the Arango Managed Platform (AMP). -See [The ArangoDB Platform](../components/platform.md) for details. +See [The Arango Data Platform](../../../data-platform/_index.md) for details. ## How to deploy diff --git a/site/content/arangodb/3.13/features/_index.md b/site/content/arangodb/3.13/features/_index.md index 85b1f4bdde..768a1e24f5 100644 --- a/site/content/arangodb/3.13/features/_index.md +++ b/site/content/arangodb/3.13/features/_index.md @@ -22,8 +22,8 @@ aliases: See the full [Feature list of the ArangoDB database system](list.md). For a scalable architecture based on Kubernetes that supports the full offering -of ArangoDB including graph-powered machine learning and GenAI features, see -the [Feature list of the ArangoDB Platform](../../../data-platform/about/features.md). +of ArangoDB including graph-powered machine learning and AI features, see +the [Feature list of the Arango Data Platform](../../../data-platform/features.md). ## On-premises versus Cloud diff --git a/site/content/arangodb/3.13/index-and-search/indexing/working-with-indexes/vector-indexes.md b/site/content/arangodb/3.13/index-and-search/indexing/working-with-indexes/vector-indexes.md index 3ebbb3f8c9..18832bb59a 100644 --- a/site/content/arangodb/3.13/index-and-search/indexing/working-with-indexes/vector-indexes.md +++ b/site/content/arangodb/3.13/index-and-search/indexing/working-with-indexes/vector-indexes.md @@ -33,7 +33,7 @@ startup option needs to be enabled on the deployment you want to restore to. {{< /warning >}} 1. Enable the experimental vector index feature. -2. Calculate vector embeddings using [ArangoDB's GraphML](../../../../../gen-ai/graphml/_index.md) +2. Calculate vector embeddings using [ArangoDB's GraphML](../../../../../ai-services/graphml/_index.md) capabilities (available in ArangoGraph) or using external tools. Store each vector as an attribute in the respective document. 3. Create a vector index over this attribute. You need to choose which diff --git a/site/content/arangodb/3.13/release-notes/platform.md b/site/content/arangodb/3.13/release-notes/platform.md index 850dc4df8b..1eb76ad190 100644 --- a/site/content/arangodb/3.13/release-notes/platform.md +++ b/site/content/arangodb/3.13/release-notes/platform.md @@ -6,7 +6,7 @@ description: >- Features and improvements in the ArangoDB Platform --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The ArangoDB Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} @@ -17,17 +17,17 @@ the ArangoDB team. The ArangoDB Platform is a scalable architecture that offers you all features of the core ArangoDB database system along with graph-powered machine learning -and GenAI capabilities as a single solution with a unified interface. Deploy the +and AI capabilities as a single solution with a unified interface. Deploy the Platform on-premise or in the cloud on top of Kubernetes. To get started, see [Self-host the ArangoDB Platform](../components/platform.md#self-host-the-arangodb-platform). -### GenAI Suite +### AI Services -The ArangoDB Platform features a dedicated GenAI and data science suite, built upon +The ArangoDB Platform features dedicated AI and data science services, built upon the powerful ArangoDB database core. -The GenAI suite consists of the following components, each featuring an intuitive, +AI Services consists of the following components, each featuring an intuitive, user-friendly interface seamlessly integrated into the ArangoDB Platform web interface: - GraphRAG - GraphML @@ -35,5 +35,5 @@ user-friendly interface seamlessly integrated into the ArangoDB Platform web int - MLflow integration - Graph Visualizer -To learn more, see the [GenAI Suite](../../../gen-ai/_index.md) +To learn more, see [AI Services](../../../ai-services/_index.md) documentation. diff --git a/site/content/data-platform/_index.md b/site/content/data-platform/_index.md index 84f9764a1f..82380cfb08 100644 --- a/site/content/data-platform/_index.md +++ b/site/content/data-platform/_index.md @@ -1,20 +1,51 @@ --- -title: Recommended Resources -menuTitle: Data Platform +title: Arango Data Platform +menuTitle: Arango Data Platform weight: 1 -layout: default +description: >- + The Arango Data Platform brings everything ArangoDB offers together to a single + solution that you can deploy on-prem or use as a managed service --- -{{< cloudbanner >}} + +{{< tip >}} +The Arango Data Platform & AI Services are available as a pre-release. To get +exclusive early access, [get in touch](https://arangodb.com/contact/) with +the ArangoDB team. +{{< /tip >}} + +The Arango Data Platform is a **Kubernetes-native** technical infrastructure that acts as the umbrella +for hosting the entire ArangoDB offering of products. Built from the ground up for +cloud-native orchestration, the platform leverages the power of Kubernetes to make it easy +to deploy, scale, and operate the core ArangoDB database system along with any additional +AI solutions for GraphRAG, graph machine learning, data explorations, and more. You can +run it on-premises or in the cloud yourself on top of Kubernetes to access all +of the platform features with enterprise-grade automation and reliability. {{< cards >}} -{{% card title="What is the ArangoDB Platform?" link="about/" %}} -The ArangoDB Platform is the umbrella for hosting the entire ArangoDB offering -of products, including GraphML and GraphRAG. +{{% card title="Get started with the Arango Data Platform" link="get-started/" %}} +Deploy the core ArangoDB database system with Kubernetes orchestration. +Optionally add AI Services to turn data into an AI-powered knowledge engine. +{{% /card %}} + +{{% card title="Features and Architecture" link="features/" %}} +Explore the Kubernetes-native architecture, unified interface, and enterprise-grade capabilities of the Arango Data Platform. +{{% /card %}} + +{{% card title="ArangoDB Kubernetes Operator" link="../../arangodb/3.12/deploy/kubernetes/" %}} +Learn about the official ArangoDB Kubernetes Operator that powers the Arango Data Platform. {{% /card %}} {{% card title="Graph Visualizer" link="graph-visualizer/" %}} -Explore your graph data with an intuitive web interface. +Explore your graph data with an intuitive web interface and sophisticated querying capabilities. +{{% /card %}} + +{{% card title="AI Services" link="../../ai-services/" %}} +Supercharge your platform with GraphRAG, GraphML, and advanced analytics for AI-powered data insights. +{{% /card %}} + +{{% card title="ArangoDB Core Database" link="../../arangodb/3.12/" %}} +Discover the multi-model database at the heart of the platform supporting graphs, documents, key-value, and vector search. {{% /card %}} {{< /cards >}} diff --git a/site/content/data-platform/about/features.md b/site/content/data-platform/about/features.md deleted file mode 100644 index 65f61afc50..0000000000 --- a/site/content/data-platform/about/features.md +++ /dev/null @@ -1,54 +0,0 @@ ---- -title: Feature list of the ArangoDB Platform -menuTitle: ArangoDB Platform -weight: 10 -description: >- - The ArangoDB Platform is a scalable architecture that gets you all features - of ArangoDB including graph-powered machine learning and GenAI as a single - solution with a unified interface ---- -## Architecture - -- **Core Database**: The ArangoDB database system forms the solid core - of the ArangoDB Platform. - -- **Kubernetes**: An open-source container orchestration system for automating - software deployment, scaling, and management designed by Google. It is the - autopilot for operating ArangoDB clusters and the additional Platform services. - -- **Helm**: A package manager for Kubernetes that enables consistent, repeatable - installations and version control. - -- **Envoy**: A high-performance service proxy that acts as the gateway for the - ArangoDB Platform for centralizing authentication and routing. - -- **Web interface**: The Platform includes a unified, browser-based UI that lets - you access its features in an intuitive way. Optional products like the - GenAI Suite seamlessly integrate into the UI if installed. - -## Features - -- [**ArangoDB Core**](../../arangodb/3.12/_index.md): The ArangoDB database system with support for - graphs, documents, key-value, full-text search, and vector search. - -- [**Graph Visualizer**](../graph-visualizer.md): - A web-based tool for exploring your graph data with an intuitive interface and - sophisticated querying capabilities. - -- [**Graph Analytics**](../../gen-ai/graph-analytics.md): - A service that can efficiently load graph data from the core database system - and run graph algorithms such as PageRank and many more. - -- [**GenAI Suite**](../../gen-ai/_index.md): - ArangoDB's graph-powered machine learning (GraphML) as well as GraphRAG for - automatically building knowledge graphs from text and taking advantage of both - excerpts and higher-level summaries as context for turbocharging GenAI - applications. - -- [**Notebook servers**](../../gen-ai/notebook-servers.md): - Run Jupyter kernels in the Platform for hosting interactive, Python-based - notebooks to experiment and develop applications. - -- [**MLflow integration**](../../gen-ai/services/mlflow.md): - Use the popular MLflow for machine learning practitioners as part of the - ArangoDB Platform. diff --git a/site/content/data-platform/features.md b/site/content/data-platform/features.md new file mode 100644 index 0000000000..1979d9f5bf --- /dev/null +++ b/site/content/data-platform/features.md @@ -0,0 +1,81 @@ +--- +title: Feature list of the Arango Data Platform +menuTitle: Features +weight: 5 +description: >- + The Arango Data Platform is a scalable Kubernetes-native architecture that gets you all features + of ArangoDB as a single solution with a unified interface +--- +## Architecture + +The Arango Data Platform is built on a modern, cloud-native foundation designed for enterprise scalability and reliability. + +{{< tip >}} +**Kubernetes-Native Architecture**: Built as a cloud-native platform that leverages +[Kubernetes](https://kubernetes.io/) for container orchestration, automated deployment, +scaling, and management. Powered by the official +[ArangoDB Kubernetes Operator](https://arangodb.github.io/kube-arangodb/) for +enterprise-grade database management and high availability. +{{< /tip >}} + +- **Core Database**: The ArangoDB database system forms the solid core + of the Arango Data Platform. + +- **Helm**: A package manager for Kubernetes that enables consistent, repeatable + installations and version control. + +- **Envoy**: A high-performance service proxy that acts as the gateway for the + Arango Data Platform for centralizing authentication and routing. + +- **Web interface**: The Platform includes a unified, browser-based UI that lets + you access its features in an intuitive way. Optional products like the + AI Services seamlessly integrate into the UI if installed. + +## Kubernetes Integration + +At its core, the Arango Data Platform is purpose-built for Kubernetes environments, leveraging the +[official ArangoDB Kubernetes Operator](https://arangodb.github.io/kube-arangodb/docs/) +(`kube-arangodb`) to deliver enterprise-grade automation, scalability, and operational excellence. + +## Features + +The Arango Data Platform provides these core capabilities out of the box: + +- [**ArangoDB Core**](../arangodb/3.12/_index.md): The ArangoDB database system with support for + graphs, documents, key-value, full-text search, and vector search. + +- [**Graph Visualizer**](graph-visualizer.md): + A web-based tool for exploring your graph data with an intuitive interface and + sophisticated querying capabilities. + +## Extend the Arango Data Platform with AI capabilities + +Take your Arango Data Platform to the next level with [**AI Services**](../ai-services/_index.md) that offers advanced AI and machine learning capabilities that integrate seamlessly into the platform's unified web interface. + +What you get with AI Services: + +- [GraphRAG](../ai-services/graphrag/): Generate knowledge graphs from documents and enable + conversational querying of your data. +- [GraphML](../ai-services/graphml/): Apply machine learning algorithms that leverage graph + structure for better predictions. +- [Graph Analytics](../ai-services/graph-analytics/): Run advanced algorithms like PageRank + to discover influential nodes and patterns. +- [Jupyter notebooks](../ai-services/notebook-servers.md): Run Jupyter Notebooks to build and + experiment with graph-powered data, AI, and machine learning workflows directly connected + to ArangoDB databases. +- Public and private LLM support: Use public LLMs such as OpenAI + or private LLMs with [Triton Inference Server](../ai-services/reference/triton-inference-server.md). +- [MLflow integration](../ai-services/reference/mlflow.md): Use the popular MLflow as a model registry + for private LLMs or to run machine learning experiments as part of the Arango Data Platform. + +{{< tip >}} +AI Services integrate directly into the existing platform interface, no need for +separate systems to manage or learn. A separate license is required. +{{< /tip >}} + + + + + + + diff --git a/site/content/data-platform/about/_index.md b/site/content/data-platform/get-started.md similarity index 62% rename from site/content/data-platform/about/_index.md rename to site/content/data-platform/get-started.md index a7e7925af8..a47c4aa5ea 100644 --- a/site/content/data-platform/about/_index.md +++ b/site/content/data-platform/get-started.md @@ -1,87 +1,50 @@ --- -title: The ArangoDB Platform -menuTitle: Platform -weight: 5 +title: Get Started with the Arango Data Platform +menuTitle: Get Started +weight: 10 description: >- - The ArangoDB Platform brings everything ArangoDB offers together to a single + The Arango Data Platform brings everything ArangoDB offers together to a single solution that you can deploy on-prem or use as a managed service --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} -The ArangoDB Platform is a technical infrastructure that acts as the umbrella +The Arango Data Platform is a technical infrastructure that acts as the umbrella for hosting the entire ArangoDB offering of products. The Platform makes it easy to deploy and operate the core ArangoDB database system along with any additional ArangoDB products for machine learning, data explorations, and more. You can run it on-premises or in the cloud yourself on top of Kubernetes to access all of the platform features. -## Features of the ArangoDB Platform - -- **Core database system**: The ArangoDB graph database system for storing - interconnected data.{{< comment >}} You can use the free Community Edition or the commercial - Enterprise Edition.{{< /comment >}} -- **Graph Visualizer**: A web-based tool for exploring your graph data with an - intuitive interface and sophisticated querying capabilities. -- **Graph Analytics**: A suite of graph algorithms including PageRank, - community detection, and centrality measures with support for GPU - acceleration thanks to Nvidia cuGraph. -- **GenAI Suite**: A set of machine learning services, APIs, and - user interfaces that are available as a package as well as individual products. - - **GraphML**: A turnkey solution for graph machine learning for prediction - use cases such as fraud detection, supply chain, healthcare, retail, and - cyber security. - - **GraphRAG**: Leverage ArangoDB's graph, document, key-value, - full-text search, and vector search features to streamline knowledge - extraction and retrieval. - {{< comment >}}TODO: Not available in prerelease version - - **Txt2AQL**: Unlock natural language querying with a service that converts - user input into ArangoDB Query Language (AQL), powered by fine-tuned - private or public LLMs. - {{< /comment >}} - - **GraphRAG Importer**: Extract entities and relationships from large - text-based files, converting unstructured data into a knowledge graph - stored in ArangoDB. - - **GraphRAG Retriever**: Perform semantic similarity searches or aggregate - insights from graph communities with global and local queries. - - **Public and private LLM support**: Use public LLMs such as OpenAI - or private LLMs with [Triton Inference Server](../../gen-ai/services/triton-inference-server.md). - - **MLflow integration**: Use the popular MLflow as a model registry for private LLMs - or to run machine learning experiments as part of the ArangoDB Platform. -- **Jupyter notebooks**: Run a Jupyter kernel in the platform for hosting - interactive notebooks for experimentation and development of applications - that use ArangoDB as their backend. -{{< comment >}}TODO: Mostly unrelated to Platform, vector index in core, -- **Vector embeddings**: You can train machine learning models for later use - in vector search in conjunction with the core database system's `vector` - index type. It allows you to find similar items in your dataset. -{{< /comment >}} - -## Get started with the ArangoDB Platform +## Use the Arango Data Platform as a managed service -### Use the ArangoDB Platform as a managed service - -The ArangoDB Platform is not available as a managed service yet, but it will +The Arango Data Platform is not available as a managed service yet, but it will become available for the [Arango Managed Platform (AMP)](../../amp/_index.md) in the future. Until then, you can request early access to the self-hosted -ArangoDB Platform for testing. +Arango Data Platform for testing. -### Self-host the ArangoDB Platform +## Self-host the Arango Data Platform -You can set up and run the ArangoDB Platform on-premises or in the cloud and +You can set up and run the Arango Data Platform on-premises or in the cloud and manage this deployment yourself. -#### Requirements for self-hosting +{{< info >}} +**Kubernetes-Native**: The Arango Data Platform is built specifically for Kubernetes +environments and relies on the official [ArangoDB Kubernetes Operator](https://arangodb.github.io/kube-arangodb/) +to provide automated deployment, scaling, and management capabilities. +{{< /info >}} + +### Requirements for self-hosting -- **Early access to the ArangoDB Platform**: +- **Early access to the Arango Data Platform**: [Get in touch](https://arangodb.com/contact/) with the ArangoDB team to get - exclusive early access to the pre-release of the ArangoDB Platform & GenAI Suite. + exclusive early access to the pre-release of the Arango Data Platform & AI Services. - **Kubernetes**: Orchestrates the selected services that comprise the - ArangoDB Platform, running them in containers for safety and scalability. + Arango Data Platform, running them in containers for safety and scalability. Set up a [Kubernetes](https://kubernetes.io/) cluster if you don't have one available yet. @@ -109,9 +72,9 @@ manage this deployment yourself. respective packages. {{< /comment >}} -#### Setup +### Setup -1. Obtain a zip package of the ArangoDB Platform for the offline installation. +1. Obtain a zip package of the Arango Data Platform for the offline installation. It includes helm charts, manifests, and blobs of the container image layers. You also receive a package configuration file from the ArangoDB team. @@ -142,7 +105,7 @@ manage this deployment yourself. --set crds.enabled=true ``` -4. Install the ArangoDB operator for Kubernetes `kube-arangodb` with helm, +4. Install the [ArangoDB Kubernetes Operator](https://arangodb.github.io/kube-arangodb/) `kube-arangodb` with helm, with options to enable webhooks, certificates, and the gateway feature. ```sh @@ -190,7 +153,7 @@ manage this deployment yourself. # ... ``` -6. Download the ArangoDB Platform CLI tool `arangodb_operator_platform` from +6. Download the Arango Data Platform CLI tool `arangodb_operator_platform` from . It is available for Linux and macOS, for the x86-64 as well as 64-bit ARM architecture (e.g. `arangodb_operator_platform_linux_amd64`). @@ -202,7 +165,7 @@ manage this deployment yourself. The Platform CLI tool simplifies the further setup and later management of the Platform's Kubernetes services. -7. Import the zip package of the ArangoDB Platform into the container registry. +7. Import the zip package of the Arango Data Platform into the container registry. Replace `platform.zip` with the file path of the offline installation package. Replace `gcr.io/my-reg` with the address of your registry. @@ -231,13 +194,13 @@ manage this deployment yourself. ## Interfaces -The ArangoDB Platform uses a gateway to make all its services available via a +The Arango Data Platform uses a gateway to make all its services available via a single port at the external address of the deployment. For a local deployment, the base URL is `https://127.0.0.1:8529`. ### Unified web interface -You can access the ArangoDB Platform web interface with a browser by appending +You can access the Arango Data Platform web interface with a browser by appending `/ui/` to the base URL, e.g. `https://127.0.0.1:8529/ui/`. ### ArangoDB Core diff --git a/site/content/data-platform/graph-visualizer.md b/site/content/data-platform/graph-visualizer.md index e429e687fc..85a08c535a 100644 --- a/site/content/data-platform/graph-visualizer.md +++ b/site/content/data-platform/graph-visualizer.md @@ -6,13 +6,13 @@ description: >- Visually explore and interact with your ArangoDB graphs through an intuitive interface --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} The **Graph Visualizer** is a browser-based tool integrated into the web interface -of the ArangoDB Platform. It lets you explore the connections of your named graphs +of the Arango Data Platform. It lets you explore the connections of your named graphs to visually understand the structure as well as to inspect and edit the attributes of individual nodes and edges. It also offers query capabilities and you can create new nodes (vertices) and edges (relations). @@ -49,7 +49,7 @@ supported by the Graph Visualizer. ### Select and load a graph -1. In the ArangoDB Platform web interface, select the database your named graph +1. In the Arango Data Platform web interface, select the database your named graph is stored in. 2. Click **Graphs** in the main navigation. 3. Select a graph from the list. diff --git a/site/content/data-platform/release-notes.md b/site/content/data-platform/release-notes.md index d5d4db5fa9..6800b2ac31 100644 --- a/site/content/data-platform/release-notes.md +++ b/site/content/data-platform/release-notes.md @@ -1,39 +1,39 @@ --- -title: What's new in the ArangoDB Platform +title: What's new in the Arango Data Platform menuTitle: Release notes weight: 50 description: >- - Features and improvements in the ArangoDB Platform + Features and improvements in the Arango Data Platform --- {{< tip >}} -The ArangoDB Platform & GenAI Suite is available as a pre-release. To get +The Arango Data Platform & AI Services are available as a pre-release. To get exclusive early access, [get in touch](https://arangodb.com/contact/) with the ArangoDB team. {{< /tip >}} -## ArangoDB Platform +## Arango Data Platform Introduced in: v3.12.5 -The ArangoDB Platform is a scalable architecture that offers you all features +The Arango Data Platform is a scalable architecture that offers you all features of the core ArangoDB database system along with graph-powered machine learning -and GenAI capabilities as a single solution with a unified interface. Deploy the +and AI capabilities as a single solution with a unified interface. Deploy the Platform on-premise or in the cloud on top of Kubernetes. -To get started, see [Self-host the ArangoDB Platform](about/_index.md#self-host-the-arangodb-platform). +To get started, see [Self-host the Arango Data Platform](./get-started.md#self-host-the-arango-data-platform). -### GenAI Suite +### AI Services -The ArangoDB Platform features a dedicated GenAI and data science suite, built upon +The Arango Data Platform features dedicated AI and data science services, built upon the powerful ArangoDB database core. -The GenAI suite consists of the following components, each featuring an intuitive, -user-friendly interface seamlessly integrated into the ArangoDB Platform web interface: +AI Services consists of the following components, each featuring an intuitive, +user-friendly interface seamlessly integrated into the Arango Data Platform web interface: - GraphRAG - GraphML - Jupyter Notebooks - MLflow integration - Graph Visualizer -To learn more, see the [GenAI Suite](../gen-ai/_index.md) +To learn more, see [AI Services](../ai-services/_index.md) documentation. diff --git a/site/content/gen-ai/_index.md b/site/content/gen-ai/_index.md deleted file mode 100644 index caa176ae72..0000000000 --- a/site/content/gen-ai/_index.md +++ /dev/null @@ -1,24 +0,0 @@ ---- -title: Recommended Resources -menuTitle: 'GenAI Data Platform' -weight: 2 -layout: default ---- -{{< cloudbanner >}} - -{{< cards >}} - -{{% card title="GraphRAG" link="graphrag/" %}} -Arango's GenAI solution for generating knowledge graphs from documents -and chatting with your data. -{{% /card %}} - -{{% card title="GraphML" link="graphml/" %}} -Discover Arango's graph-powered machine learning features. -{{% /card %}} - -{{% card title="Graph Analytics" link="graph-analytics/" %}} -Run algorithms such as PageRank on your graph data. -{{% /card %}} - -{{< /cards >}} diff --git a/site/content/gen-ai/services/_index.md b/site/content/gen-ai/services/_index.md deleted file mode 100644 index 8df04c2c84..0000000000 --- a/site/content/gen-ai/services/_index.md +++ /dev/null @@ -1,6 +0,0 @@ ---- -title: GenAI services -menuTitle: Services -description: '' ---- - diff --git a/site/themes/arangodb-docs-theme/layouts/shortcodes/tag.html b/site/themes/arangodb-docs-theme/layouts/shortcodes/tag.html index 9244cbf9dc..189c6e9b99 100644 --- a/site/themes/arangodb-docs-theme/layouts/shortcodes/tag.html +++ b/site/themes/arangodb-docs-theme/layouts/shortcodes/tag.html @@ -1,7 +1,7 @@ {{ $tooltips := dict "AMP" "This feature is available in the Arango Managed Platform (AMP)" - "Data Platform" "This feature is available in the Arango Data Platform and GenAI Data Platform" - "GenAI Data Platform" "This feature is available in the Arango GenAI Data Platform but not the Data Platform" + "Data Platform" "This feature is available in the Arango Data Platform and AI Services Data Platform" + "AI Services Data Platform" "This feature is available in the Arango AI Services Data Platform but not the Data Platform" "arangosh" "This feature is available in the ArangoDB Shell" "ArangoDB Enterprise Edition" "This feature is available in the Enterprise Edition but not the Community Edition of ArangoDB" -}}