Skip to content

Commit 7d5c428

Browse files
nerpaulaSimran-B
nerpaula
and
Simran-B
authored
Data Platform & AI Suite | October release notes (#824)
* add release notes * Review --------- Co-authored-by: Simran Spiller <simran@arangodb.com>
1 parent 8fded54 commit 7d5c428

File tree

2 files changed

+148
-22
lines changed

2 files changed

+148
-22
lines changed

‎site/content/ai-suite/release-notes.md‎

Lines changed: 69 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,69 @@
1+
---
2+
title: What's new in the AI Suite
3+
menuTitle: Release notes
4+
weight: 100
5+
description: >-
6+
Features and improvements in the AI Suite of the Arango Data Platform
7+
---
8+
{{< tip >}}
9+
The AI Suite is available as a pre-release. To get exclusive early access,
10+
[get in touch](https://arango.ai/contact-us/) with the Arango team.
11+
{{< /tip >}}
12+
13+
## October 2024 (pre-release)
14+
15+
This release introduces new features and enhancements to the AI Suite components.
16+
See also the [Arango Data Platform Release Notes](../data-platform/release-notes.md).
17+
18+
### GraphRAG enhancements
19+
20+
- **Instant and Deep Search**: New [Retriever](reference/retriever.md#search-methods) search methods
21+
optimized for different use cases. Instant Search provides fast responses with
22+
streaming support. Deep Search offers detailed, accurate responses for complex queries
23+
requiring high accuracy. Both methods are accessible via the API or the
24+
[GraphRAG web interface](graphrag/web-interface.md#chat-with-your-knowledge-graph).
25+
26+
- **Update Knowledge Graphs**: [Add additional data sources](graphrag/web-interface.md#update-the-knowledge-graph)
27+
to existing Knowledge Graphs through the web interface. Upload new files to
28+
automatically update the Knowledge Graph and underlying collections with new data.
29+
30+
- **Unified LLM provider configuration**: Simplified deployment configuration using
31+
OpenAI-compatible APIs. Mix and match providers for chat and embeddings (e.g.,
32+
use OpenRouter for chat and OpenAI for embeddings). Support for OpenAI, OpenRouter,
33+
Gemini, Anthropic, and any self-hosted LLM with OpenAI-compatible endpoints.
34+
35+
### AQLizer
36+
37+
The [Natural Language to AQL Translation Service](reference/natural-language-to-aql.md)
38+
enables you to query your ArangoDB database using natural language or get
39+
LLM-powered answers to general questions.
40+
41+
You can generate AQL queries from natural language directly in the Query Editor using the
42+
[AQLizer](aqlizer.md) mode. More advanced features are available via the API.
43+
44+
## July 2024 (pre-release)
45+
46+
This release marks the initial internal launch of the AI Suite with the following
47+
components. For Data Platform features in this release, see
48+
[Arango Data Platform Release Notes](../data-platform/release-notes.md).
49+
50+
- **[GraphRAG](graphrag/_index.md)**: Transform unstructured documents into
51+
intelligent knowledge graphs and natural language querying through Importer
52+
and Retriever services.
53+
54+
- **[GraphML](graphml/_index.md)**: Apply machine learning to graphs with node
55+
classification and embedding generation, built on GraphSAGE framework.
56+
57+
- **[Graph Analytics](graph-analytics.md)**: Run algorithms like PageRank,
58+
Connected Components, and more.
59+
60+
- **[Jupyter Notebooks](notebook-servers.md)**: Launch integrated Jupyter
61+
notebook servers with pre-installed ArangoDB drivers and data science libraries
62+
for interactive experimentation.
63+
64+
- **[MLflow Integration](reference/mlflow.md)**: Use MLflow as a model registry
65+
for private LLMs and machine learning experiment tracking.
66+
67+
- **[Triton Inference Server](reference/triton-inference-server.md)**: Host
68+
private Large Language Models using NVIDIA Triton Inference Server for secure,
69+
on-premises AI capabilities.

‎site/content/data-platform/release-notes.md‎

Lines changed: 79 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -6,34 +6,91 @@ description: >-
66
Features and improvements in the Arango Data Platform
77
---
88
{{< tip >}}
9-
The Arango Data Platform & AI Suite are available as a pre-release. To get
10-
exclusive early access, [get in touch](https://arango.ai/contact-us/) with
11-
the Arango team.
9+
The Arango Data Platform is available as a pre-release. To get exclusive early access,
10+
[get in touch](https://arango.ai/contact-us/) with the Arango team.
1211
{{< /tip >}}
1312

14-
## Arango Data Platform
13+
## October 2024 (pre-release)
1514

16-
<small>Introduced in: v3.12.5</small>
15+
<small>ArangoDB Enterprise Edition: v3.12.6</small>
1716

18-
The Arango Data Platform is a scalable architecture that offers you all features
19-
of the core ArangoDB database system along with graph-powered machine learning
20-
and AI capabilities as a single solution with a unified interface. Deploy the
21-
Platform on-premise or in the cloud on top of Kubernetes.
17+
This release includes new features and enhancements for the Data Platform web
18+
interface, running with ArangoDB Enterprise Edition v3.12.6. For AI Suite updates
19+
in this release, see [AI Suite Release Notes](../ai-suite/release-notes.md).
2220

23-
To get started, see [Self-host the Arango Data Platform](./get-started.md#self-host-the-arango-data-platform).
21+
### Query Editor
2422

25-
### AI Suite
23+
A new [Query Editor](query-editor.md) has been integrated into the
24+
Arango Data Platform web interface for writing, executing, and managing AQL queries.
2625

27-
The Arango AI Data Platform features dedicated AI and data science services, built upon
28-
the powerful ArangoDB database core.
26+
Key features:
2927

30-
The AI Suite consists of the following components, each featuring an intuitive,
31-
user-friendly interface seamlessly integrated into the Arango Data Platform web interface:
32-
- GraphRAG
33-
- GraphML
34-
- Jupyter Notebooks
35-
- MLflow integration
36-
- Graph Visualizer
28+
- **Tabbed interface**: Work on multiple queries concurrently with side-by-side
29+
query and results views.
30+
- **Query operations**: Run, explain, and profile queries with dedicated buttons
31+
and result history tracking.
32+
- **Saved queries**: Save and share frequently used queries with all users in the
33+
database, persisted across sessions.
34+
- **Query monitoring**: View running queries and slow query logs, with the ability
35+
to kill long-running operations.
36+
- **Flexible viewport**: Drag and drop tabs to reorganize panels horizontally or
37+
vertically.
3738

38-
To learn more, see [AI Suite](../ai-suite/_index.md)
39-
documentation.
39+
### Graph Visualizer enhancements
40+
41+
The [Graph Visualizer](graph-visualizer.md) has been significantly enhanced with
42+
new visual customization capabilities, improved navigation features, and better
43+
performance for exploring large-scale graphs.
44+
45+
Key improvements:
46+
47+
- **Icon assignment**: Assign pictograms to node collections for quick visual
48+
identification of entity types on the canvas.
49+
- **Theme support**: Create and manage multiple themes to highlight different
50+
aspects of graph data, with default themes that automatically color different
51+
collections on the canvas.
52+
- **Shortest path**: Find and visualize the shortest path between two selected
53+
nodes directly on the canvas.
54+
- **Enhanced tooltips**: Hover over nodes and edges to view document IDs and
55+
customizable additional attributes without opening the full properties dialog.
56+
- **Bulk selection**: Select all nodes or edges of a specific type (collection)
57+
from the Legend panel, showing the count of elements per collection.
58+
- **Edge properties view**: View and edit edge properties through a dedicated
59+
properties dialog with Form and JSON editing modes.
60+
- **Attribute-based styling**: Define conditional styling rules based on document
61+
attributes to dynamically color and style nodes and edges (e.g., apply colors
62+
based on genre or other field values).
63+
- **Performance improvements**: Optimized rendering for large graphs with
64+
millions of nodes and edges.
65+
66+
## July 2024 (pre-release)
67+
68+
<small>ArangoDB Enterprise Edition: v3.12.5</small>
69+
70+
This release marks the initial internal launch of the Arango Data Platform, running with
71+
ArangoDB Enterprise Edition v3.12.5. For AI Suite features in this release, see
72+
[AI Suite Release Notes](../ai-suite/release-notes.md).
73+
74+
### Arango Data Platform
75+
76+
The Arango Data Platform is a Kubernetes-native technical infrastructure that
77+
brings together the entire ArangoDB offering into a unified solution.
78+
See [Get Started with the Arango Data Platform](get-started.md).
79+
80+
What's included:
81+
82+
- **ArangoDB Enterprise Edition**: Multi-model database foundation supporting
83+
graphs, documents, key-value, vector search, and full-text search capabilities.
84+
- **Graph Visualizer**: Sophisticated web-based interface for interactive graph
85+
exploration, visual customization, and direct graph editing.
86+
- **Arango Platform Suite**: Enterprise-grade features including high availability
87+
and monitoring, comprehensive APIs and connectors, and centralized orchestration
88+
and resource management.
89+
- **Kubernetes orchestration**: Powered by the official ArangoDB Kubernetes
90+
Operator for automated deployment, scaling, and management.
91+
- **Unified web interface**: Single interface for accessing all Platform services
92+
and components.
93+
94+
The Platform can be extended with the [AI Suite](../ai-suite/_index.md) for
95+
advanced capabilities like GraphRAG, GraphML, Graph Analytics, AQLizer, and more
96+
(requires separate license).

0 commit comments

Comments
 (0)