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

81–90 of 124 posts

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

#81

Post by macklinkachorn »

localfirst wrote: post #76
constantinum wrote: post #59

Earlier quoted context omitted.

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.

then please elaborate on "complexities involved down the funnel" and where I am misunderstanding with examples.

A few that we experience as we’re building Trellis out:

1. Managing end-to-end workflows from integrating with data sources, automatically triggering new runs when there’s new data coming in, and keeping track of different business logic that’s involved (i.e. I want to classify the type of the emails and based on that apply different extraction logic)

2. Most out-of-the-box solutions only get you 95% of the way there. The customers want the ability to pass in their own data to improve performance and specify their unique ontology.

3. Building a good UI and API support for both technical and non-technical users to use the product.

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

#82

Post by atak1 »

aiden3 wrote: post #62

What about a pdf with many separate datapoints on it? For instance, I have 100 pdfs, each with 10-100 individual products listed (in different formats). I want to create a single table with one row per product appearing in any of the PDFs, with various details like price, product description, etc., From what I can tell from the demo, it seems like 1 file = 1 row in Trellis?

Just did an extraction and table mode targets this rly well :)

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

#84

Post by macklinkachorn »

hubraumhugo wrote: post #83

You mention validation and schema guarantees as key features for high accuracy. Are you using an LLM-as-a-judge combined with traditional checks for this?

Yes, we combine LLMs as a judge with traditional checks like reverse search in original data sources, defining your own post-processing logic, and simple classifier for confidence score.

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

#85

Post by efriis »

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…

Would recommend using the updated guide here! That link is from the v0.1 docs. https://python.langchain.com/v0.2/docs/how_to/structured_out...

OOC which openai model were you using? Would recommend trying 4o as well as Anthropic claude 3.5 sonnet if ya haven't played around with those yet

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

#86

Post by rahimnathwani »

efriis wrote: post #85
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…

Would recommend using the updated guide here! That link is from the v0.1 docs. https://python.langchain.com/v0.2/docs/how_to/structured_out... OOC which openai model were you using? Would recommend trying 4o as well as Anthropic claude 3.5 sonnet if ya haven't played around with those yet

Thanks.

I was using gpt-3.5-turbo-0125. It was before the recent pricing change.

But I have a bunch of updates to make to the json schema, so will re-run everything with gpt-4o-mini.

Sonnet seems a lot more expensive, but I'll 'upgrade' if the schema changes don't get sufficiently good results.

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

#87

Post by efriis »

rahimnathwani wrote: post #86
efriis wrote: post #85

Earlier quoted context omitted.

Would recommend using the updated guide here! That link is from the v0.1 docs. https://python.langchain.com/v0.2/docs/how_to/structured_out... OOC which openai model were you using? Would recommend trying 4o as well as Anthropic claude 3.5 sonnet if ya haven't played around with those yet

Thanks. I was using gpt-3.5-turbo-0125. It was before the recent pricing change. But I have a bunch of updates to make to the json schema, so will re-run everything with gpt-4o-mini. Sonnet seems a lot more expensive, but I'll 'upgrade' if the schema changes don't get sufficiently good results.

Nice. Could also give haiku a try!

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

#88

Post by lmeyerov »

wjnc wrote: post #68
lmeyerov wrote: post #44

Earlier quoted context omitted.

Yep, and nowadays, banks are already deploying this stuff internally via their own IT teams. They have 1-2 decades of having built up ETL/orchestration talent + infra, and have been growing deals with openai/azure/google/aws/databricks for the LLM bits. Internally, big banks are rolling out hundreds of LLM apps each, and generally have freezes on new external AI vendors due to 'AI compliance risk'. NLP commoditized s…

Am I in another world? (See my response above.) Most of the ‘hundreds of LLM apps’ I see are, well, not very fancy and struggling to keep up on accuracy in comparison to the meatspace solutions they promised to massively outperform. I agree with your assessment that the IT risk barrier is very high in big corp so that entry might be hard for Trellis. Plus a continuous push afterwards to go back to traditional cloud o…

I totally agree, and it's useful to play out the shrinking quality gap over time:

- Today: Financial companies are willing to pay cloud providers for DB, LLM, & AI services, and want to paper over the rest with internal teams + OSS, and maybe some already-trusted contractors for stopgaps. Institutional immune system largely rejects innovators not in the above categories.

- Next 6-18mo: Projects continue, and they hit today's typical quality issues. It's easiest to continue to solve these with the current team, maybe pull on a consultant or neighboring team due to good-money-after-bad, and likely, the cloud/AI provider solves more and more for them (GPT5, ..., new Google Vertex APIs, ..)

- Next year or year after: Either the above solved it, or they make a new decision around contractors + new software vendors. But how much is still needed here?

It's a scary question for non-vertical startups to still make sense with the assumption that horizontal data incumbents and core AI infra providers don't continue to eat into the territory here. Data extraction, vector indexing, RAG as a service, data quality, talk to your data, etc. Throw in the pressure of VC funding and even more fun. I think there's opportunity here, but when I think about who is positioned wrt distribution & engineering resources to get at that... I do not envy founders without those advantages.

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

#89

Post by jackienotchan »

constantinum wrote: post #52

Congrats on the launch! For anyone curious who wants to dig deep and solve document processing workflows via open-source, do try Unstract https://github.com/Zipstack/unstract

This was the top comment for quite a while but suddenly dropped to the bottom. Was it automatically downranked for mentioning an OS alternative?

How many upvotes does your comment have?

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

#90

Post by miguelspizza »

We built something tangentially related at SoundTrace.

Basically when we onboard a new client they dump all their audiograms on us as PDFs.

The data needs extraction needs to be perfect because the tables values are used to detect hearing loss over time.

We settled on a pipeline that looks roughly like

PDF -> gpto pre filter phase -> OCR to extract text tables and forms -> things branch out here

We do a direct parse of forms and text through an LLM

Extract audiogram graphs and send them to a foundation convnet

Attempt to parse tables programmatically

-> an audiogram might have 3 separate places where the values are so we pass the results of all three of these routes through Claude sonnet and if they match they get auto approved. If they don’t, they get flagged for manual review.

All in all it’s been a journey but the accuracy is near 100 percent. These tools are incredible

Post reply on HN