UiForm – Never write a parser again, make any file LLM-ready
Hey HN! UiForm is a document processing SDK that (1) makes any file LLM-ready, eliminating the need to write custom parsers for each format, and (2) improves structured data extraction through built-in Chain-of-Thought prompting (repo: https://github.com/UiForm/uiform, site: uiform.com). We’ve been analyzing shipping documents with LLMs for over a year with Cube. While building, we faced two major challenges in document analysis: First, each client had different document formats (PDFs, Excel sheets, emails) requiring custom parsers. Second, getting consistent, structured…
What it does
In the maker’s words, at launch
Hey HN! UiForm is a document processing SDK that (1) makes any file LLM-ready, eliminating the need to write custom parsers for each format, and (2) improves structured data extraction through built-in Chain-of-Thought prompting (repo: https://github.com/UiForm/uiform, site: uiform.com). We’ve been analyzing shipping documents with LLMs for over a year with Cube. While building, we faced two major challenges in document analysis: First, each client had different document formats (PDFs, Excel sheets, emails) requiring custom parsers. Second, getting consistent, structured outputs from LLMs was a constant struggle - small prompt changes would lead to unpredictable results. After months of building parsers and refining prompts, we realized everyone working with LLMs faces these same challenges, so we built UiForm as an open solution that handles both the document processing and prompt engineering pieces in one cohesive system. Today: 1. We’re launching uiform (free for all!), an API that pre-processes any file (e.g. excel, email, …) for use with LLMs. We built it to be compatible with Pydantic, JSON schemas, and most LLM providers. 2. We're open sourcing a prompt engineering framework that combines JSON schema validation with Chain-of-Thought reasoning to ensure reliable structured outputs Prompt engineering is managed directly within the JSON schema using three additional directives: - X-SystemPrompt - X-FieldPrompt enhances the standard field description to decorrelate prompt engineering and schema specification - X-ReasoningPrompt creates an auxiliary reasoning field that gives the LLM more time to think, to perform better when dealing with complex data. Since o1, everybody's been talking about CoT and inference time compute. We found that using reasoning fields with structured generation improves performance on document analysis tasks. We’d love to see document analysis be more community driven, with people sharing their JSON-schemas for different use-cases, which is why we open-sourced our prompt-engineering utility :) Looking forward to hearing your thoughts, we’ll be in the comments or on discord (https://discord.com/invite/vc5tWRPqag). Thanks!
Does the same job
all alternatives →- EUExtend UI – open-source UI kit for modern document appsJun 2026 · extend.ai · ▲252
We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable. 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…
- ANA new benchmark for testing LLMs for deterministic outputsApr 2026 · interfaze.ai · ▲60
When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries. The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not. Structured output today is a big part of using LLMs, especially when building deterministic workflows. Current structured output benchmarks (e.g., JSONSchemaBench) only validate…
- RLRobust LLM extractor for websites in TypeScriptMar 2026 · github.com · ▲72
We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, January 2025
the whole month →- IM
Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https://github.com/Hello9999901/laptop
Dev tools · 2025 · byran.ee
- TITetris in a PDF▲1,289
I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I/O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing/hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…
Life & fun · 2025 · th0mas.nl
Create lifelike, personalized AI avatars from text prompts
AI · 2025 · jogg.ai
