This is an automated email from the ASF dual-hosted git repository.
morningman pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris-website.git
The following commit(s) were added to refs/heads/master by this push:
new d578a89d653 0525-blog-update-detail (#3766)
d578a89d653 is described below
commit d578a89d6533b687c8e8689578ddc131f74ce6d3
Author: Qin Chen <[email protected]>
AuthorDate: Mon May 25 23:56:01 2026 +0800
0525-blog-update-detail (#3766)
---
blog/apache-doris-4-1-iceberg-v3.md | 16 +++++++++
blog/apache-doris-4-1-spill-to-disk.md | 14 ++++++++
blog/autonomous-driving-multimodal-search.md | 2 --
blog/chunking-embedding-cookbook.md | 16 +++++++++
...lickhouse-elasticsearch-to-apache-doris-kwai.md | 2 --
blog/from-data-silos-to-context-silos.md | 16 +++++++++
blog/netease-games-unified-doris-lakehouse.md | 16 +++++++++
blog/olake-iceberg-and-doris.md | 2 --
blog/puppygraph-apache-doris.md | 2 --
src/components/recent-blogs/recent-blogs.data.ts | 20 ++++++------
src/constant/newsletter.data.ts | 36 ++++++++++-----------
.../images/blogs/20260515_chunking_horizontal.png | Bin 0 -> 55630 bytes
.../images/blogs/202605_Iceberg_v3_horizontal.jpg | Bin 0 -> 181417 bytes
.../blogs/202605_context_silo_horizontal.png | Bin 0 -> 929315 bytes
.../blogs/202605_netease_games_horizontal.jpg | Bin 0 -> 242471 bytes
.../blogs/202605_spill_to_disk_horizontal.png | Bin 0 -> 917589 bytes
16 files changed, 106 insertions(+), 36 deletions(-)
diff --git a/blog/apache-doris-4-1-iceberg-v3.md
b/blog/apache-doris-4-1-iceberg-v3.md
new file mode 100644
index 00000000000..a959ee98a55
--- /dev/null
+++ b/blog/apache-doris-4-1-iceberg-v3.md
@@ -0,0 +1,16 @@
+---
+ 'title': 'Apache Doris 4.1 on Iceberg V3: Running the Full Lakehouse
Lifecycle from One SQL Engine'
+ 'summary': 'Apache Doris 4.1 introduces comprehensive Iceberg V3 support,
enabling reads, writes (UPDATE, DELETE, MERGE INTO), DDL operations, table
maintenance, and diagnostics entirely through SQL without switching to other
tools.'
+ 'description': 'Apache Doris 4.1 introduces comprehensive Iceberg V3
support, enabling reads, writes (UPDATE, DELETE, MERGE INTO), DDL operations,
table maintenance, and diagnostics entirely through SQL without switching to
other tools.'
+ 'picked': "true"
+ 'order': "3"
+ 'date': '2026-5-22'
+ 'author': 'velodb.io · Rayner Chen'
+ 'externalLink':
'https://www.velodb.io/blog/apache-doris-4-1-on-iceberg-v3-full-lakehouse-lifecycle'
+ 'tags': ['Tech Sharing']
+ "image": '/images/blogs/202605_Iceberg_v3_horizontal.jpg'
+---
+import { BlogLink } from '../src/components/blogs/components/blog-link';
+import { SeeMore } from '../src/components/blogs/components/see-more';
+
+> <BlogLink rel="noopener noreferrer" target='_blank'
href='https://www.velodb.io/blog/apache-doris-4-1-on-iceberg-v3-full-lakehouse-lifecycle'>Apache
Doris 4.1 introduces comprehensive Iceberg V3 support, enabling reads, writes
(UPDATE, DELETE, MERGE INTO), DDL operations, table maintenance, and
diagnostics entirely through SQL without switching to other tools. <SeeMore
/></BlogLink>
diff --git a/blog/apache-doris-4-1-spill-to-disk.md
b/blog/apache-doris-4-1-spill-to-disk.md
new file mode 100644
index 00000000000..71f71fe836d
--- /dev/null
+++ b/blog/apache-doris-4-1-spill-to-disk.md
@@ -0,0 +1,14 @@
+---
+ 'title': 'Apache Doris 4.1 Spill to Disk: Running Memory-Intensive Queries
Without OOM'
+ 'summary': 'Apache Doris 4.1 introduces mature spill-to-disk capabilities,
enabling Hash Join, Aggregation, and Sort operators to write intermediate state
to disk when memory pressure rises so that memory-intensive analytical queries
complete without OOM errors.'
+ 'description': 'Apache Doris 4.1 introduces mature spill-to-disk
capabilities, enabling Hash Join, Aggregation, and Sort operators to write
intermediate state to disk when memory pressure rises so that memory-intensive
analytical queries complete without OOM errors.'
+ 'date': '2026-5-8'
+ 'author': 'velodb.io · Matt Yi'
+ 'externalLink':
'https://www.velodb.io/blog/apache-doris-4-1-spill-to-disk-running-memory-intensive-queries-without-oom'
+ 'tags': ['Tech Sharing']
+ "image": '/images/blogs/202605_spill_to_disk_horizontal.png'
+---
+import { BlogLink } from '../src/components/blogs/components/blog-link';
+import { SeeMore } from '../src/components/blogs/components/see-more';
+
+> <BlogLink rel="noopener noreferrer" target='_blank'
href='https://www.velodb.io/blog/apache-doris-4-1-spill-to-disk-running-memory-intensive-queries-without-oom'>Apache
Doris 4.1 introduces mature spill-to-disk capabilities, enabling Hash Join,
Aggregation, and Sort operators to write intermediate state to disk when memory
pressure rises so that memory-intensive analytical queries complete without OOM
errors. <SeeMore /></BlogLink>
diff --git a/blog/autonomous-driving-multimodal-search.md
b/blog/autonomous-driving-multimodal-search.md
index 9b4c08db96b..3859ce457e5 100644
--- a/blog/autonomous-driving-multimodal-search.md
+++ b/blog/autonomous-driving-multimodal-search.md
@@ -2,8 +2,6 @@
'title': 'How an Autonomous Driving Company Unified Multimodal Search on a
Single Analytics Engine'
'summary': 'An autonomous driving company consolidated fragmented data
platforms by adopting Apache Doris as a unified analytics engine, enabling
seamless search across text, vectors, labels, and metadata while reducing query
times from minutes to seconds.'
'description': 'An autonomous driving company consolidated fragmented data
platforms by adopting Apache Doris as a unified analytics engine, enabling
seamless search across text, vectors, labels, and metadata while reducing query
times from minutes to seconds.'
- 'picked': "true"
- 'order': "1"
'date': '2026-4-18'
'author': 'velodb.io · Wesley Zhu'
'externalLink':
'https://www.velodb.io/blog/autonomous-driving-company-unified-multimodal-search-on-apache-doris'
diff --git a/blog/chunking-embedding-cookbook.md
b/blog/chunking-embedding-cookbook.md
new file mode 100644
index 00000000000..6ace9ecf949
--- /dev/null
+++ b/blog/chunking-embedding-cookbook.md
@@ -0,0 +1,16 @@
+---
+ 'title': 'The Chunking and Embedding Cookbook for Production Context
Engineering'
+ 'summary': 'This guide covers three critical decisions for production RAG
systems: chunk shaping, embedding selection, and ANN index scaling, bridging
the gap between demo retrieval and real-scale deployments.'
+ 'description': 'This guide covers three critical decisions for production
RAG systems: chunk shaping, embedding selection, and ANN index scaling,
bridging the gap between demo retrieval and real-scale deployments.'
+ 'picked': "true"
+ 'order': "4"
+ 'date': '2026-5-15'
+ 'author': 'velodb.io · Tom Zhang'
+ 'externalLink':
'https://www.velodb.io/blog/the-chunking-and-embedding-cookbook-for-production-context-engineering'
+ 'tags': ['Tech Sharing']
+ "image": '/images/blogs/20260515_chunking_horizontal.png'
+---
+import { BlogLink } from '../src/components/blogs/components/blog-link';
+import { SeeMore } from '../src/components/blogs/components/see-more';
+
+> <BlogLink rel="noopener noreferrer" target='_blank'
href='https://www.velodb.io/blog/the-chunking-and-embedding-cookbook-for-production-context-engineering'>This
guide covers three critical decisions for production RAG systems: chunk
shaping, embedding selection, and ANN index scaling, bridging the gap between
demo retrieval and real-scale deployments. <SeeMore /></BlogLink>
diff --git a/blog/from-clickhouse-elasticsearch-to-apache-doris-kwai.md
b/blog/from-clickhouse-elasticsearch-to-apache-doris-kwai.md
index 62396f892b5..0f542bcd450 100644
--- a/blog/from-clickhouse-elasticsearch-to-apache-doris-kwai.md
+++ b/blog/from-clickhouse-elasticsearch-to-apache-doris-kwai.md
@@ -2,8 +2,6 @@
'title': 'From ClickHouse + Elasticsearch to Apache Doris: How Kwai
Unified Trillion-Scale Ad Analytics'
'summary': 'Kwai, a short-video platform with over 400 million daily
active users, migrated its advertising analytics from ClickHouse and
Elasticsearch to Apache Doris, achieving up to 90% latency reduction and 3x
write throughput.'
'description': 'Kwai, a short-video platform with over 400 million daily
active users, migrated its advertising analytics from ClickHouse and
Elasticsearch to Apache Doris, achieving up to 90% latency reduction and 3x
write throughput.'
- 'picked': "true"
- 'order': "4"
'date': '2026-3-20'
'author': 'velodb.io · Simin Zhou'
'externalLink':
'https://www.velodb.io/blog/from-clickhouse-elasticsearch-to-apache-doris-how-kwai-unified-trillion-scale-ad-analytics'
diff --git a/blog/from-data-silos-to-context-silos.md
b/blog/from-data-silos-to-context-silos.md
new file mode 100644
index 00000000000..086d93d0f50
--- /dev/null
+++ b/blog/from-data-silos-to-context-silos.md
@@ -0,0 +1,16 @@
+---
+ 'title': 'From Data Silos to Context Silos: What Database History Teaches
Us About the AI Infrastructure Problem'
+ 'summary': 'The database industry is repeating a historical cycle where
specialized systems create fragmentation that demands convergence. As AI agents
become primary data consumers, organizations face a new challenge: context
silos, where information exists but cannot be retrieved fast enough for
autonomous systems to act effectively.'
+ 'description': 'The database industry is repeating a historical cycle
where specialized systems create fragmentation that demands convergence. As AI
agents become primary data consumers, organizations face a new challenge:
context silos, where information exists but cannot be retrieved fast enough for
autonomous systems to act effectively.'
+ 'picked': "true"
+ 'order': "2"
+ 'date': '2026-5-9'
+ 'author': 'velodb.io · Kevin Shen'
+ 'externalLink':
'https://www.velodb.io/blog/from-data-silos-to-context-silos'
+ 'tags': ['Tech Sharing']
+ "image": '/images/blogs/202605_context_silo_horizontal.png'
+---
+import { BlogLink } from '../src/components/blogs/components/blog-link';
+import { SeeMore } from '../src/components/blogs/components/see-more';
+
+> <BlogLink rel="noopener noreferrer" target='_blank'
href='https://www.velodb.io/blog/from-data-silos-to-context-silos'>The database
industry is repeating a historical cycle where specialized systems create
fragmentation that demands convergence. As AI agents become primary data
consumers, organizations face a new challenge: context silos, where information
exists but cannot be retrieved fast enough for autonomous systems to act
effectively. <SeeMore /></BlogLink>
diff --git a/blog/netease-games-unified-doris-lakehouse.md
b/blog/netease-games-unified-doris-lakehouse.md
new file mode 100644
index 00000000000..513a42d4b1c
--- /dev/null
+++ b/blog/netease-games-unified-doris-lakehouse.md
@@ -0,0 +1,16 @@
+---
+ 'title': 'NetEase Games: From Elasticsearch, HBase, and ClickHouse to a
Unified Apache Doris Lakehouse'
+ 'summary': 'NetEase Games consolidated six specialized data systems into
Apache Doris across two phases, first unifying real-time analytics, then adding
batch processing capabilities to create a lakehouse architecture serving 15
million daily queries.'
+ 'description': 'NetEase Games consolidated six specialized data systems
into Apache Doris across two phases, first unifying real-time analytics, then
adding batch processing capabilities to create a lakehouse architecture serving
15 million daily queries.'
+ 'picked': "true"
+ 'order': "1"
+ 'date': '2026-5-22'
+ 'author': 'velodb.io · Biao Hu'
+ 'externalLink':
'https://www.velodb.io/blog/netease-games-from-elasticsearch-and-clickhouse-to-a-unified-apache-doris-lakehouse'
+ 'tags': ['Best Practice']
+ "image": '/images/blogs/202605_netease_games_horizontal.jpg'
+---
+import { BlogLink } from '../src/components/blogs/components/blog-link';
+import { SeeMore } from '../src/components/blogs/components/see-more';
+
+> <BlogLink rel="noopener noreferrer" target='_blank'
href='https://www.velodb.io/blog/netease-games-from-elasticsearch-and-clickhouse-to-a-unified-apache-doris-lakehouse'>NetEase
Games consolidated six specialized data systems into Apache Doris across two
phases, first unifying real-time analytics, then adding batch processing
capabilities to create a lakehouse architecture serving 15 million daily
queries. <SeeMore /></BlogLink>
diff --git a/blog/olake-iceberg-and-doris.md b/blog/olake-iceberg-and-doris.md
index fb09302862e..d8a503e072a 100644
--- a/blog/olake-iceberg-and-doris.md
+++ b/blog/olake-iceberg-and-doris.md
@@ -2,8 +2,6 @@
'title': 'Set Up a Lakehouse with PostgreSQL, Apache Iceberg, and Apache
Doris in 15 Minutes'
'summary': 'A step-by-step guide to building a lakehouse with PostgreSQL,
Apache Iceberg, and Apache Doris in 15 minutes, covering CDC setup, data
ingestion, and analytical queries on a fully open-source stack.'
'description': 'A step-by-step guide to building a lakehouse with
PostgreSQL, Apache Iceberg, and Apache Doris in 15 minutes, covering CDC setup,
data ingestion, and analytical queries on a fully open-source stack.'
- 'picked': "true"
- 'order': "3"
'date': '2026-4-23'
'author': 'velodb.io · Rohan Khameshra'
'externalLink':
'https://www.velodb.io/blog/set-up-a-lakehouse-with-postgresql-apache-iceberg-and-apache-doris'
diff --git a/blog/puppygraph-apache-doris.md b/blog/puppygraph-apache-doris.md
index 8dbe4ba1644..49901221548 100644
--- a/blog/puppygraph-apache-doris.md
+++ b/blog/puppygraph-apache-doris.md
@@ -2,8 +2,6 @@
'title': 'Querying Apache Doris Data as a Graph with PuppyGraph'
'summary': 'PuppyGraph enables graph analytics on Apache Doris data
without requiring separate graph databases or ETL pipelines, supporting
relationship traversal queries through Cypher and Gremlin.'
'description': 'PuppyGraph enables graph analytics on Apache Doris data
without requiring separate graph databases or ETL pipelines, supporting
relationship traversal queries through Cypher and Gremlin.'
- 'picked': "true"
- 'order': "2"
'date': '2026-4-9'
'author': 'velodb.io · Rayner Chen'
'externalLink':
'https://www.velodb.io/blog/querying-apache-doris-data-as-a-graph-with-puppygraph'
diff --git a/src/components/recent-blogs/recent-blogs.data.ts
b/src/components/recent-blogs/recent-blogs.data.ts
index 4fc1bb57f85..64d04ce779d 100644
--- a/src/components/recent-blogs/recent-blogs.data.ts
+++ b/src/components/recent-blogs/recent-blogs.data.ts
@@ -1,19 +1,19 @@
export const RECENT_BLOGS_POSTS = [
{
- label: 'How an Autonomous Driving Company Unified Multimodal Search on
a Single Analytics Engine',
- link:
'https://www.velodb.io/blog/autonomous-driving-company-unified-multimodal-search-on-apache-doris',
+ label: 'NetEase Games: From Elasticsearch, HBase, and ClickHouse to a
Unified Apache Doris Lakehouse',
+ link:
'https://www.velodb.io/blog/netease-games-from-elasticsearch-and-clickhouse-to-a-unified-apache-doris-lakehouse',
},
{
- label: 'Querying Apache Doris Data as a Graph with PuppyGraph',
- link:
'https://www.velodb.io/blog/querying-apache-doris-data-as-a-graph-with-puppygraph',
+ label: 'From Data Silos to Context Silos: What Database History
Teaches Us About the AI Infrastructure Problem',
+ link: 'https://www.velodb.io/blog/from-data-silos-to-context-silos',
},
{
- label: 'Set Up a Lakehouse with PostgreSQL, Apache Iceberg, and Apache
Doris in 15 Minutes',
- link:
'https://www.velodb.io/blog/set-up-a-lakehouse-with-postgresql-apache-iceberg-and-apache-doris',
+ label: 'Apache Doris 4.1 on Iceberg V3: Running the Full Lakehouse
Lifecycle from One SQL Engine',
+ link:
'https://www.velodb.io/blog/apache-doris-4-1-on-iceberg-v3-full-lakehouse-lifecycle',
},
{
- label: 'From ClickHouse + Elasticsearch to Apache Doris: How Kwai
Unified Trillion-Scale Ad Analytics',
- link:
'https://www.velodb.io/blog/from-clickhouse-elasticsearch-to-apache-doris-how-kwai-unified-trillion-scale-ad-analytics',
+ label: 'The Chunking and Embedding Cookbook for Production Context
Engineering',
+ link:
'https://www.velodb.io/blog/the-chunking-and-embedding-cookbook-for-production-context-engineering',
},
-
-];
\ No newline at end of file
+
+];
diff --git a/src/constant/newsletter.data.ts b/src/constant/newsletter.data.ts
index 1d4e1d2cb79..5a32bd9018e 100644
--- a/src/constant/newsletter.data.ts
+++ b/src/constant/newsletter.data.ts
@@ -1,30 +1,30 @@
export const NEWSLETTER_DATA = [
{
tags: ['Best Practice'],
- title: "How an Autonomous Driving Company Unified Multimodal Search on
a Single Analytics Engine",
- content: `An autonomous driving company consolidated fragmented data
platforms by adopting Apache Doris as a unified analytics engine, enabling
seamless search across text, vectors, labels, and metadata while reducing query
times from minutes to seconds.`,
- to:
'https://www.velodb.io/blog/autonomous-driving-company-unified-multimodal-search-on-apache-doris',
- image: 'blogs/202604_Multimodal_search_horizontal.png',
+ title: "NetEase Games: From Elasticsearch, HBase, and ClickHouse to a
Unified Apache Doris Lakehouse",
+ content: `NetEase Games consolidated six specialized data systems into
Apache Doris across two phases, first unifying real-time analytics, then adding
batch processing capabilities to create a lakehouse architecture serving 15
million daily queries.`,
+ to:
'https://www.velodb.io/blog/netease-games-from-elasticsearch-and-clickhouse-to-a-unified-apache-doris-lakehouse',
+ image: 'blogs/202605_netease_games_horizontal.jpg',
},
{
tags: ['Tech Sharing'],
- title: "Querying Apache Doris Data as a Graph with PuppyGraph",
- content: `PuppyGraph enables graph analytics on Apache Doris data
without requiring separate graph databases or ETL pipelines, supporting
relationship traversal queries through Cypher and Gremlin.`,
- to:
'https://www.velodb.io/blog/querying-apache-doris-data-as-a-graph-with-puppygraph',
- image: 'blogs/202604_Puppygraph_horizontal.png',
+ title: "From Data Silos to Context Silos: What Database History
Teaches Us About the AI Infrastructure Problem",
+ content: `The database industry is repeating a historical cycle where
specialized systems create fragmentation that demands convergence. As AI agents
become primary data consumers, organizations face a new challenge: context
silos, where information exists but cannot be retrieved fast enough for
autonomous systems to act effectively.`,
+ to: 'https://www.velodb.io/blog/from-data-silos-to-context-silos',
+ image: 'blogs/202605_context_silo_horizontal.png',
},
{
tags: ['Tech Sharing'],
- title: "Set Up a Lakehouse with PostgreSQL, Apache Iceberg, and Apache
Doris in 15 Minutes",
- content: `A step-by-step guide to building a lakehouse with
PostgreSQL, Apache Iceberg, and Apache Doris in 15 minutes, covering CDC setup,
data ingestion, and analytical queries on a fully open-source stack.`,
- to:
'https://www.velodb.io/blog/set-up-a-lakehouse-with-postgresql-apache-iceberg-and-apache-doris',
- image: 'blogs/202603_Olake_horizontal.png',
+ title: "Apache Doris 4.1 on Iceberg V3: Running the Full Lakehouse
Lifecycle from One SQL Engine",
+ content: `Apache Doris 4.1 introduces comprehensive Iceberg V3
support, enabling reads, writes (UPDATE, DELETE, MERGE INTO), DDL operations,
table maintenance, and diagnostics entirely through SQL without switching to
other tools.`,
+ to:
'https://www.velodb.io/blog/apache-doris-4-1-on-iceberg-v3-full-lakehouse-lifecycle',
+ image: 'blogs/202605_Iceberg_v3_horizontal.jpg',
},
{
- tags: ['Best Practice'],
- title: "From ClickHouse + Elasticsearch to Apache Doris: How Kwai
Unified Trillion-Scale Ad Analytics",
- content: `Kwai, a short-video platform with over 400 million daily
active users, migrated its advertising analytics from ClickHouse and
Elasticsearch to Apache Doris, achieving up to 90% latency reduction and 3x
write throughput.`,
- to:
'https://www.velodb.io/blog/from-clickhouse-elasticsearch-to-apache-doris-how-kwai-unified-trillion-scale-ad-analytics',
- image: 'blogs/202603_Kwai_horizontal.png',
+ tags: ['Tech Sharing'],
+ title: "The Chunking and Embedding Cookbook for Production Context
Engineering",
+ content: `This guide covers three critical decisions for production
RAG systems: chunk shaping, embedding selection, and ANN index scaling,
bridging the gap between demo retrieval and real-scale deployments.`,
+ to:
'https://www.velodb.io/blog/the-chunking-and-embedding-cookbook-for-production-context-engineering',
+ image: 'blogs/20260515_chunking_horizontal.png',
},
-];
\ No newline at end of file
+];
diff --git a/static/images/blogs/20260515_chunking_horizontal.png
b/static/images/blogs/20260515_chunking_horizontal.png
new file mode 100644
index 00000000000..c9345121872
Binary files /dev/null and
b/static/images/blogs/20260515_chunking_horizontal.png differ
diff --git a/static/images/blogs/202605_Iceberg_v3_horizontal.jpg
b/static/images/blogs/202605_Iceberg_v3_horizontal.jpg
new file mode 100644
index 00000000000..8a44dc2cfbc
Binary files /dev/null and
b/static/images/blogs/202605_Iceberg_v3_horizontal.jpg differ
diff --git a/static/images/blogs/202605_context_silo_horizontal.png
b/static/images/blogs/202605_context_silo_horizontal.png
new file mode 100644
index 00000000000..c2fa44c30be
Binary files /dev/null and
b/static/images/blogs/202605_context_silo_horizontal.png differ
diff --git a/static/images/blogs/202605_netease_games_horizontal.jpg
b/static/images/blogs/202605_netease_games_horizontal.jpg
new file mode 100644
index 00000000000..24d03c3ab7f
Binary files /dev/null and
b/static/images/blogs/202605_netease_games_horizontal.jpg differ
diff --git a/static/images/blogs/202605_spill_to_disk_horizontal.png
b/static/images/blogs/202605_spill_to_disk_horizontal.png
new file mode 100644
index 00000000000..e7c66ca48cf
Binary files /dev/null and
b/static/images/blogs/202605_spill_to_disk_horizontal.png differ
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
