Datumagic

Building a RAG-based AI Recommender (2/2)

An end-to-end code walkthrough.

Aug 29 • 

Shiyan Xu

4

July 2025

Building a RAG-based AI Recommender (1/2)

What is RAG, and how to go from data to AI.

Jul 11 • 

Shiyan Xu

5

3

June 2025

Apache Hudi does XYZ (1/10)

File pruning with multi-modal index

Jun 16 • 

Shiyan Xu

3

April 2024

Apache Hudi: From Zero To One (10/10)

Becoming "One" - the upcoming 1.0 highlights

Apr 13, 2024 • 

Shiyan Xu

9

March 2024

Apache Hudi: From Zero To One (9/10)

Hudi Streamer - a "Swiss Army knife" for ingestion

Mar 1, 2024 • 

Shiyan Xu

3

January 2024

Apache Hudi: From Zero To One (8/10)

Read and process incrementally

Jan 5, 2024 • 

Shiyan Xu

1

December 2023

Apache Hudi: From Zero To One (7/10)

Concurrently run writers and table services

Dec 7, 2023 • 

Shiyan Xu

5

November 2023

Apache Hudi: From Zero To One (6/10)

Demystify clustering and space-filling curves

Nov 13, 2023 • 

Shiyan Xu

5

3

October 2023

Apache Hudi: From Zero To One (5/10)

Introduce table services: compaction, cleaning, and indexing

Oct 19, 2023 • 

Shiyan Xu

4

3

September 2023

Apache Hudi: From Zero To One (4/10)

All about writer indexes

Sep 28, 2023 • 

Shiyan Xu

4

4

Apache Hudi: From Zero To One (3/10)

Understand write flows and operations

Sep 15, 2023 • 

Shiyan Xu

9

Apache Hudi: From Zero To One (2/10)

Dive into read operation flow and query types

Sep 6, 2023 • 

Shiyan Xu

10

4