Sign up to save your podcasts
Or
Share Why JVector 3 Is The Most Advanced Embedded Vector Search Engine
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Why JVector 3 Is The Most Advanced Embedded Vector Search Engine
An airhacks.fm conversation with Jonathan Ellis (@spyced) about:
discussion of JVector 3 features and improvements,
compression techniques for vector indexes,
binary quantization vs product quantization,
anisotropic product quantization for improved accuracy,
indexing Wikipedia example,
Cassandra integration,
SIMD acceleration with Fused ADC,
optimization with Chronicle Map,
E5 embedding models,
comparison of CPU vs GPU for vector search,
implementation details and low-level optimizations in Java,
use of Java Panama API and foreign function interface,
JVector's performance advantages,
memory footprint reduction,
integration with Cassandra and Astra DB,
challenges of vector search at scale,
trade-offs between RAM usage and CPU performance,
Eventual Consistency in distributed vector search,
comparison of different embedding models and their accuracy,
importance of re-ranking in vector search,
advantages of JVector over other vector search implementations
Jonathan Ellis on twitter: @spyced
View all episodes
By Adam Bien
5
55 ratings
An airhacks.fm conversation with Jonathan Ellis (@spyced) about:
discussion of JVector 3 features and improvements,
compression techniques for vector indexes,
binary quantization vs product quantization,
anisotropic product quantization for improved accuracy,
indexing Wikipedia example,
Cassandra integration,
SIMD acceleration with Fused ADC,
optimization with Chronicle Map,
E5 embedding models,
comparison of CPU vs GPU for vector search,
implementation details and low-level optimizations in Java,
use of Java Panama API and foreign function interface,
JVector's performance advantages,
memory footprint reduction,
integration with Cassandra and Astra DB,
challenges of vector search at scale,
trade-offs between RAM usage and CPU performance,
Eventual Consistency in distributed vector search,
comparison of different embedding models and their accuracy,
importance of re-ranking in vector search,
advantages of JVector over other vector search implementations
Jonathan Ellis on twitter: @spyced
More shows like airhacks.fm podcast with adam bien
View all
Software Engineering Radio - the podcast for professional software developers
270 Listeners
The Changelog: Software Development, Open Source
283 Listeners
Thoughtworks Technology Podcast
42 Listeners
Talk Python To Me
583 Listeners
Software Engineering Daily
626 Listeners
Soft Skills Engineering
282 Listeners
AWS Podcast
203 Listeners
Duke's Corner
8 Listeners
Home Assistant Podcast
69 Listeners
Syntax - Tasty Web Development Treats
986 Listeners
A Bootiful Podcast
29 Listeners
The Stack Overflow Podcast
65 Listeners
The Real Python Podcast
141 Listeners
Latent Space: The AI Engineer Podcast
89 Listeners
The Pragmatic Engineer
61 Listeners