Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

news.ycombinator.com

Post reply on HN
Print view View original

51–60 of 124 posts

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#51

Post by meiraleal »

darkhorse13 wrote: post #17

Congrats on the launch. Serious question though, does YC only fund AI companies these days?

The problem for me is that all of them look more of the same. I have a feeling of dejavu every time I see a Show HN of an AI generator, AI nocode, AI supabase, AI PDF scanner, AI monitoring startup.

I'm developing an "AI wrapper" myself and I know how difficult it is to create a reliable system using LLM integration and I guess these many similar projects are competing on being the one to create something that won't risk ruining their customers reputation. But I see no differentiation, no eye-catching tech, algorithm, invention.

YC and HN used to be the bastion of innovation in tech.

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#54

Post by purplepatrick »

Two quick questions: any plans on being hipaa compliant? Probably one of the biggest use cases for this is in health insurance, etc.

How do your capabilities compare to Google Document AI or Watson SDU? Also what about standalone competitors such as Indico Data or DocuPanda?

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#55

Post by meiraleal »

breadwinner wrote: post #31
destraynor wrote: post #22

Congrats on the launch, and thanks for using Intercom (co-founder here)

Is that the chat thing that pops up in the bottom right corner? It is the most annoying thing in the world. Because it pops up uninvited, and obscures the page content I am trying to read. So annoying.

I hate it so much when it rings out of nowhere and I don't even know which tab it is.

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#56

Post by macklinkachorn »

rahimnathwani wrote: post #50

I've had do some of this recently, as a one-off, to extract the same fields from thousands of scanned documents. I used OpenAI's function calling (via Langchain's https://python.langchain.com/v0.1/docs/modules/model_io/chat... API). Some of the challenges I had: 1. poor recall for some fields, even with a wide variety of input document formats 2. needing to experiment with the json schema (particularly field descript…

We face similar challenges you listed and handle all of the above. 1. Out of the box OCR doesn't perform as well for complex documents (with tables, images, etc.). We use vision model to help process that documents. 2. Recall (for longer documents) and accuracy are also a major problem. We built in validation systems and references to help users validate the results. 3. Maintain this systems in production, integrate with the data sources and refresh when new data comes in are quite annoying. We manage that for the end users. 4. For non-technical users, we allow them to iterate through different business logic and have a one unify place to manage data workflows.

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#57

Post by constantinum »

chrisweekly wrote: post #38

disclaimer: I'm a barely-informed layperson, not any kind of AI expert non-snarky genuine question: is "generate structured data from unstructured data using AI" intended to be a moat or differentiator? catalyst for my question: I just read about this capability becoming available from other AI vendors, e.g. https://openai.com/index/introducing-structured-outputs-in-t...

That is only part of the problem; the others include:

1. writing connectors for various sources

2. writing connectors for destination

3. supporting multiple models, embeddings, vector database, text extractors

3. workflow automation engine(cron jobs)

4. performance tuning for speed and costs

5. security and compliance

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#58

Post by macklinkachorn »

skeptrune wrote: post #45

Both fulltext (BM25 or SPLADE) and dense vector search have issues with documents of different lengths. Part of what makes recursive sentence splitting work so well are its length normalization properties. Filters are a really important feature downstream of that which this system can provide. We have also worked with the Enron corpus for demos and fast, reliable ETL for a set of documents that large is more difficul…

Thanks! We also start to see the patterns where search systems are being improved with filters and hierarchy level metadata. Another use case that people use Trellis for is ingesting data into their downstream LLMs applications.

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#59

Post by constantinum »

localfirst wrote: post #33
hamsterbooster wrote: post #23

Earlier quoted context omitted.

In many use cases, like flagging documents for compliance issues or processing customer emails, it's challenging to manage this at the vendor level because end customers want the ability to apply business logic and run different analyses. For data ingestion and mapping, I agree that in an ideal world, we would all have first-party API integrations. However, many industries still rely on PDFs and CSV files to transfer…

perhaps im misunderstanding the product offering here, isn't this just throwing PDFs (which also has unparsable content like formulas, symbols and large tables even with OCR) on an LLM with structured outputs and running SQL queries? isn't it obvious that this would be a problem that will eventually be solved by the LLM providers themselves including the ability to flag and apply business logic on top of the structur…

This misunderstanding is valid. Another example is why subscription/recurring billing software exists when payment gateways can solve this problem themselves. The elephant in the room is the complexities involved down the funnel that need very specific focus/solutions.

Re: Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

#60

Post by macklinkachorn »

constantinum wrote: post #57
chrisweekly wrote: post #38

disclaimer: I'm a barely-informed layperson, not any kind of AI expert non-snarky genuine question: is "generate structured data from unstructured data using AI" intended to be a moat or differentiator? catalyst for my question: I just read about this capability becoming available from other AI vendors, e.g. https://openai.com/index/introducing-structured-outputs-in-t...

That is only part of the problem; the others include: 1. writing connectors for various sources 2. writing connectors for destination 3. supporting multiple models, embeddings, vector database, text extractors 3. workflow automation engine(cron jobs) 4. performance tuning for speed and costs 5. security and compliance

Totally! The structured extraction from AI is only a small part in the product. Beyond the list above we also built 1. Custom validation that allows end users to validate outputs with their own logic 2. Manage different workflows (monitoring, scaling) and keep track of business logic in processing different data sources.
Post reply on HN