HN user

bobvanluijt

301 karma

Working on an open-source vector database called Weaviate

Posts77
Comments70
View on HN
arxiv.org 4mo ago

A Visual Document Benchmark for Scientific Retrieval and Question Answering

bobvanluijt
2pts0
twitter.com 6mo ago

Removing branches from the hot path: A 60% speed-up for Product Quantization

bobvanluijt
1pts0
www.youtube.com 7mo ago

Kamer 306: Pioneers of Dutch Electronic Music (1956–1960) [video]

bobvanluijt
2pts1
weaviate.io 10mo ago

Hybrid Search vs. Agentic Search Benchmarks

bobvanluijt
1pts1
weaviate.io 10mo ago

Compress Vectors by 4x by using 8-bit Rotational Quantization

bobvanluijt
3pts0
github.com 11mo ago

Elysia – open-source agentic AI platform

bobvanluijt
4pts1
mythgen.ai 1y ago

MythGen – Lovable for world-building (Unity and Unreal)

bobvanluijt
1pts1
weaviate.io 1y ago

Exploring RAG and GraphRAG: Understanding when and how to use both

bobvanluijt
2pts0
github.com 1y ago

Is it possible to vibe-code a production-grade database?

bobvanluijt
3pts1
weaviate.io 1y ago

Weaviate Transformation Agent

bobvanluijt
1pts0
builders.mozilla.org 1y ago

Hyperspace Bypass

bobvanluijt
1pts1
weaviate.io 1y ago

Improved filtered vector search with ACORN

bobvanluijt
2pts0
twitter.com 1y ago

Overview of RAG Architectures

bobvanluijt
2pts0
weaviate.io 1y ago

Detailed Explanation of Vector Search

bobvanluijt
2pts0
www.youtube.com 1y ago

Weaviate Database Talk (CMU Intro to Database Systems)

bobvanluijt
2pts0
weaviate.io 1y ago

What Is Agentic RAG?

bobvanluijt
2pts0
txt.vanluijt.nl 1y ago

In My Humble Opinion – things I've learned building a tech startup

bobvanluijt
2pts1
arxiv.org 1y ago

StructuredRAG: JSON Response Formatting with Large Language Models

bobvanluijt
38pts4
www.cradle.bio 1y ago

Affordable High-Throughput Protein Purification

bobvanluijt
1pts0
weaviate.io 1y ago

Weaviate releases hot, warm, and cold storage tiers

bobvanluijt
3pts1
weaviate.io 2y ago

Evaluation Metrics for Search and Recommendation Systems

bobvanluijt
3pts0
research.contrary.com 2y ago

Building an AI-Native Company

bobvanluijt
2pts0
www.economist.com 2y ago

Why is so much of the internet's infrastructure run by volunteers?

bobvanluijt
4pts1
www.supervised.news 2y ago

Let's check back in on the vector databases

bobvanluijt
2pts0
twitter.com 2y ago

How to Be More Impressive

bobvanluijt
1pts0
twitter.com 2y ago

Gemini 1.5 Pro Demo

bobvanluijt
2pts1
github.com 2y ago

Show HN: Running Weaviate on Snowpark Container Services

bobvanluijt
4pts0
papers.ssrn.com 2y ago

HBS Strategy: The Value of Open Source Software

bobvanluijt
3pts2
www.youtube.com 2y ago

Can Apple Win Back Music?

bobvanluijt
3pts0
weaviate.io 2y ago

Weaviate 1.23 Released

bobvanluijt
1pts0

"Kamer 306 is a 2006 documentary about the birth of electronic music inside the Philips Natuurkundig Laboratorium (NatLab) in Eindhoven. Set in the legendary Room 306 of the lab’s Acoustics Department, the film traces how Philips technicians, engineers, and composers opened up a completely new sonic world in the late 1950s."

Besides pure vector search there is hybrid (BM25 + vector) but now there is also agentic search (where the agent can set additional filters, do multiple roundtrips, etc on top of hybrid vector search.

It depends on additional filters and whether you want to use vector search only. The upside of using Faiss would be storing the ID as file metadata and embedding it in the Faiss index. However, if you need any other filters or data, you would need to store it somewhere else.

How nice to see Stockhausen on the front page. It’s definitely an acquired taste, but if you take the time to dive in, you will appreciate it

We could make programs _so much_ better than they currently are, it’s not even funny.

IMHO, that's what the author is arguing. Now that we have the tech to do it, this is how companies will win new users. Making the technology "better" means subjective design decisions that can be defined as tasteful when done well.

I've been working on Weaviate for 5 years, and today, I'm in the fortunate position to be able to help other founders, too.

In the process, I've noticed that many founders ask me the same questions so I've decided to answer them in an IMHO section on my website.

I would love to get some feedback and/or opinions if this is helpful to other founders, builders, etc.

The author gives the example of the Köln Concert; we can buy scores to play the piece, but the score doesn't contain enough information to _really_ replicate the performance. That's what I meant by the missing context.

Interesting that Nelson Goodmanis is mentioned. IMO music notation has the same, albeit lesser observable, problem as language and that's context. Regardless if it’s the Köln concert or a modular synth. If we try to capture all context for -let's say- the first second of a musical piece, it’s almost impossible to do.

“We estimate the supply-side value of widely-used OSS is $4.15 billion, but that the demand-side value is much larger at $8.8 trillion. We find that firms would need to spend 3.5 times more on software than they currently do if OSS did not exist.”

Modules are optional, so if you want to create an end-to-end RAG pipeline, you can do this from the database directly. It's basically less abstraction based on how the user wants to feed data into the prompt of the model.