Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 13 min 34 sec ago

Show HN: Tile.run – Extract structured data from any document via API

Thu, 11/07/2024 - 4:44am

Hey HN,

Today, we’re launching tile.run, an API that extracts structured data from unstructured documents (PDF, images, text) with support for custom schemas.

The Problem: Extracting data out of unstructured documents is surprisingly hard. We built tile.run while solving this for our product Kili (automation for invoicing/reconciliation). We found that getting to accuracy that is reliable enough for automation is challenging. Dense documents (e.g., lots of tables or line items) are even harder, and these are the most valuable to automate. After talking to other teams and developers, we found many other teams were after similar solutions.

Key Features:

- Multiple formats: PDF, JPEG, PNG, TIFF, plain text

- Custom schema support with nested objects/arrays

- Specialized in dense documents with tables

- Self-serve API - start extracting in minutes

Technical Details:

- REST API with simple JSON responses

- Robust error handling and validation

Coming Soon:

- Improved accuracy

- More file formats

- Self-hosting options

- Zero data retention mode

Links:

- Landing page: https://tile.run

- Documentation: https://tile.run/docs

I appreciate there have been a bunch of launches in this area recently, so wanted to address that head on as well:

- Clearly this problem is very valuable to solve but requires significant effort

- There are many ways to approach the same problem. For example, tile.run targets technical teams whereas other teams are solving this for business teams or specific functions (e.g. ETL).

We're excited to hear your feedback on the product.

Comments URL: https://news.ycombinator.com/item?id=42075186

Points: 3

# Comments: 0

Categories: Hacker News

The Big Array Size Survey for C

Thu, 11/07/2024 - 4:42am
Categories: Hacker News

Hello, HPy

Thu, 11/07/2024 - 4:42am
Categories: Hacker News

Ask HN: Has anyone used Zed AI?

Thu, 11/07/2024 - 4:31am

Has anyone used Zed AI, how does it compare with cursor?

Comments URL: https://news.ycombinator.com/item?id=42075126

Points: 1

# Comments: 0

Categories: Hacker News

FLUX1.1 [Pro] Ultra and Raw Modes

Thu, 11/07/2024 - 4:28am
Categories: Hacker News

Join Us on Our Open-Source Adventure

Thu, 11/07/2024 - 4:27am
Categories: Hacker News

Open source project Django Python

Thu, 11/07/2024 - 4:27am

Article URL: https://github.com/Ivipop/ivipop.com

Comments URL: https://news.ycombinator.com/item?id=42075111

Points: 4

# Comments: 0

Categories: Hacker News

Show HN: Enigma Implemented in x86 Assembly

Thu, 11/07/2024 - 4:25am

In case you didn't know, Enigma was used during WWII to encrypt and decrypt messages by the Germans. I re implemented it in x86 assembly. I am learning assembly and thought this might be a good project! Please take your time to review it (it looks awful to me)

Comments URL: https://news.ycombinator.com/item?id=42075101

Points: 1

# Comments: 0

Categories: Hacker News

Hetzner Server Comparison

Thu, 11/07/2024 - 4:24am
Categories: Hacker News

Kuaishou Video Downloader

Thu, 11/07/2024 - 4:23am

Article URL: https://kuaishouvideodownloader.com/

Comments URL: https://news.ycombinator.com/item?id=42075085

Points: 1

# Comments: 1

Categories: Hacker News

My Modern CSS Reset

Thu, 11/07/2024 - 4:23am
Categories: Hacker News

2NF: The Missing Use Case

Thu, 11/07/2024 - 3:11am
Categories: Hacker News

Pages