Comments URL: https://news.ycombinator.com/item?id=48485160

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48484584

Points: 197

# Comments: 54

Comments URL: https://news.ycombinator.com/item?id=48484282

Points: 27

# Comments: 9

Comments URL: https://news.ycombinator.com/item?id=48483854

Points: 21

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=48483387

Points: 124

# Comments: 79

Comments URL: https://news.ycombinator.com/item?id=48482293

Points: 75

# Comments: 68

Comments URL: https://news.ycombinator.com/item?id=48481857

Points: 194

# Comments: 208

Comments URL: https://news.ycombinator.com/item?id=48480978

Points: 573

# Comments: 140

Comments URL: https://news.ycombinator.com/item?id=48479852

Points: 176

# Comments: 12

Comments URL: https://news.ycombinator.com/item?id=48479705

Points: 190

# Comments: 43

Comments URL: https://news.ycombinator.com/item?id=48479452

Points: 365

# Comments: 255

Comments URL: https://news.ycombinator.com/item?id=48478969

Points: 289

# Comments: 265

Demo video here: https://share.extend.ai/kRmSGKRF

When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/. It was only ever meant to be internal, but enough customers kept asking for it that we decided to open source it.

It's useful for building document processing agents, real-time user facing document intake flows, or all kinds of internal tooling.

We naively thought this would be a solved problem. Turns out, making PDF/XLSX/DOCX viewers that work at scale is not trivial...we use and maintain it for Extend ourselves, so we've fixed a lot of edge cases that came up while running millions of pages / day through our own system. Our hope is that with our resources + community support, it'll keep getting better over time.

Comments URL: https://news.ycombinator.com/item?id=48478469

Points: 170

# Comments: 42

Why graph, vector and FTS? Graph databases provide a natural cognitive model for data, vectors allow for a semantic understanding of the entities and relationships in the graph, and FTS provides more specific filtering. Many AI-driven applications attempt to combine all of these functionalities by stitching together multiple disconnected systems, but even then there’s no native way to perform joins or queries that span all systems. You still need to handle this logic at the application level.

Helix started as a graph DB, but we moved to a hybrid graph/vector approach after attempting to build an AI memory system, which led us down the GraphRAG and HybridRAG rabbit hole, where we would need separate graph and vector databases.

We knew scalability would be a challenge at each stage of our product's development, however our initial focus this past year was to prove out the product through local deployments and was only meant to be run on a single node. Scaling graph DBs remained a difficult and expensive problem we’d have to solve later. Some common ways other graph DBs solve scaling is by duplicating entire datasets across distributed machines (extremely expensive per node), or by sharding the data.

Sharding databases is effective and affordable, however, graph data doesn’t have explicit partitions like relational databases do. For example, sharding a relational DB involves splitting up tables. When it comes to graph DBs, the edges can span across any of the partitions, and hopping across multiple machines when traversing nodes is ineffective and computationally expensive.

Replicating graph DBs for high availability and better throughput drastically increases the operational cost of the db and still has a limit of how big you can vertically scale. The workload that we’re used for requires storing a huge amount of data for agents, where only a subset of that data is ever needed at any one time. So rather than having the whole thing in memory, we can store it all in object-storage and get the bits we need when they’re needed.

Agents benefit from better context, which is achieved from more and better data (more relationships etc). By using S3 as the persistence/data layer there is no limit to how big the graph can be or how many relationships you can have, and we can scale to serve throughput and requests by horizontally spinning up nodes and caching relevant subsets of the graph on each node. This way, you get extremely low latency for “hot” data and a p99 of ~100ms for writes and ~50ms for reads from cold storage (S3). Plus you get the benefit of dirt cheap storage.

Workloads that HelixDB is currently supporting: - Huge amounts of data (TBs) from which the agents need to search and traverse over - Offering affordable graph storage for companies where cost of graph data is a bottleneck - Consolidating multiple databases, enabling AI agents to have autonomy over companies, helping them become more autonomous. - AI memory - Company brains

We’re currently working on our own generalised AI memory layer which will use HelixDB under the hood and be completely open-source. Also, we’re finishing up on pre-filtering for vector search which will allow you to pre-filter based on relationships in the graph, metadata, and sub-graphs. And lastly, GA cloud will be available in the coming weeks.

If you want to run Helix locally (either on-disk or in-memory), you can find more info on our github (https://github.com/HelixDB/helix-db) or via our docs (https://docs.helix-db.com/database/local-development). If you’re interested in getting started with our distributed cloud, please email us founders@helix-db.com.

Many thanks! Comments and feedback welcome!

Comments URL: https://news.ycombinator.com/item?id=48478148

Points: 98

# Comments: 32

Comments URL: https://news.ycombinator.com/item?id=48477851

Points: 155

# Comments: 31

Comments URL: https://news.ycombinator.com/item?id=48477400

Points: 183

# Comments: 95

It's been fifteen years since I wrote The Lean Startup, and in that time I've seen some things. In both big companies and tiny startups, NGOs and governments, in almost every industry you can name.

I've helped a lot of people create a lot of amazing companies, but I've also seen so many ways this can go wrong. There's a darkness in our industry that we often don't talk about.

I kept watching good companies drift away from the missions they were founded on. Not because anyone woke up one day and decided to be evil, but because the structure they were built on slowly pulled them there. I call that pull "financial gravity."

We've all experienced watching a company we love or admire be warped and broken beyond recognition; until it's a husk of its former self, or worse. I wanted to understand why. And I wanted to know what all of us can do to stop that from happening.

My new book _Incorruptible_ is my attempt to explain the invisible forces that shape organizations, and how a handful of companies (like Costco, Patagonia, and Novo Nordisk) have successfully been structured to resist gravity and thrive for decades -- or even centuries.

Along the way, I founded the Long-Term Stock Exchange, co-founded an AI R&D lab called Answer.AI with Jeremy Howard, and helped a number of notable companies with their governance (yes, including Anthropic).

I won't pretend I have this all figured out, but I've probably spent more time than is healthy on the "why do good companies go bad" question. Ask me anything!

Comments URL: https://news.ycombinator.com/item?id=48477135

Points: 564

# Comments: 437

Points: 133

# Comments: 90

Comments URL: https://news.ycombinator.com/item?id=48476466

Points: 416

# Comments: 207

Comments URL: https://news.ycombinator.com/item?id=48475483

Points: 1025

# Comments: 471