Alternatives
Products that do what Smelt – Extract structured data from PDFs and HTML using LLM does
I built a CLI tool in Go that extracts structured data (JSON, CSV, Parquet) from messy PDFs and HTML pages. The core idea: LLMs are great at understanding structure but wasteful for bulk data extraction. So smelt uses a two-pass architecture: 1. A fast Go capture layer parses the document and detects table-like regions 2. Those regions (not the whole document) get sent to Claude for schema inference — column names, types, nesting 3. The Go layer then does deterministic extraction using the inferred schema This means the LLM is never in the hot path of actual data processing. It figures out…
- 1
- 2
Extract web data into structured JSON, no scraper required.
Jun 2026
- 3
- 4
- 5
- 6
- 7
- 8SP
I built Sculptor after repeatedly seeing founders try to hire data scientists for a task that ultimately boiled down to extracting structured data from unstructured text (customer records, social posts, websites, etc) using an LLM API. We ended up reinventing this pattern internally at least three times in the past year, so I published Sculptor as a streamlined, open-source solution: - Simple schema-based extraction, with parallelization and type validation. - Multi-step pipelines with filtering or transforms between steps. - Configure everything in YAML/JSON for easy reuse. It’s MIT…
2025 · github.com
- 9XS
Hi HN. I made a little JS library for streaming structured data from LLMs using leniently-parsed XML as a medium. E.g. await simple('fun pet names', { schema: { name: Array(String) }, model: 'openrouter:mistralai/ministral-3b' }); // => ["Daisy", "Whiskers", "Rocky"] Demos: xmllm.j11y.io When using LLMs, I've ended up gravitating towards boring time-tested XML-esque tag-based delimiters instead of JSON/function-calling for the following reasons: - Diverse presence in training corpuses (consider flavours of content commonly adjacent to these syntaxes vs. JSON) - HTML was…
2024 · github.com
- 10TU
LLM-Powered document extraction & analysis tool
2024 · dataku.ai
- 11AC
Hey HN, I have been working in the last weeks on the task of automatically extracting a table of contents from a raw (audio or video) transcript, aka a 'chaptering' task. That turned out to be more difficult than I inially thought, especially because I needed to keep the timestamp data, and because I had to deal with long transcripts, and LLMs tend to 'forget' part of input data when it is too long. I was also surprised that I could not find any open-source solution for that, in standard libraries like Langchain or LLamaIndex, despite the wide range of possible use cases (text summarization,…
2024 · huggingface.co
- 12AO
Hi, We are building an open-source framework for loading and structuring LLM context to create accurate and explainable LLM answers using knowledge graphs and vector stores. We built the tool with four main concepts in mind: 1. Loader -> uses dlt in the backend to load and structure the data 2. Cognify step -> creates a graph with summaries, labels and factoids that are interconnected across the documents and stored as a representation in the vector store 3. Optimizer -> Uses DSPy to optimize LLM queries, and we plan to extend it to most of the knobs we can turn, like chunking etc. 4. Search…
2024 · github.com
- 13TA
Let's try a small experiment with LLMs that have a large context length: feed an entire book into the context window and ask it to generate a list of characters, their relationships, and physical descriptions—data that can later be used for image generation. In this repository, you can find two tools: a script that extracts data from book text using an LLM (Gemini or OpenRouter API) and an HTML/JS (D3) visualization of the character graph. An external text-to-image model can be used to generate character illustrations (a Google Colab example is provided). Explore the visualizations,…
2025 · github.com
- 14EA
A few months ago I was working on a flight search engine that would include pet transport costs (I know a few by hearth but storing them and make the calculations in the UI would be nice) While I was collecting pet pricing from several airlines I strugled to extract data in a common format without hallucinated values. That's when I thought: What if I use multiple LLMs and take the most common response to improve accuracy? This idea became this new project. You provide your documents, an SQLModel schema, an LLM provider, plus what you'd like to extract and Extrai does the rest. Including…
Nov 2025 · github.com
- 15SH
This library aims to be something like pandas.read_html or table_extract Rust crate, but more idiomatic for Go. htmltable enables structured data extraction from HTML tables and URLs and requires almost no external dependencies. Tested with Go 1.18.x and 1.19.x. Complex tables with row and col spans are natively supported as well.
2022 · github.com
- 16LA
We build LlamaExtract, a tool that allow you to automatically extract a data model from a collection of documents, and then reusing this datamodels (JSON Schema) to extract data from documents. Available as a Python library and as an API. Announcement blog: https://www.llamaindex.ai/blog/introducing-llamaextract-beta...
2024 · github.com
- 17HP
I built this because I was tired of scrolling through hundreds of lines of AWS CLI JSON output just to find instance status. hawk brings pandas-like operations (select, group_by, aggregations) to CLI with unified syntax across JSON/YAML/CSV. Key features: - Instant data structure overview with `| info` - Same query syntax for all formats - Built in Rust for speed and single-binary distribution Would love feedback from the community!
2025 · github.com
- 18SC
I created a tool that consolidates information from the following inputs: GitHub repository URL (e.g., https://github.com/jimmc414/onefilellm) arXiv abstract URL (e.g., https://arxiv.org/abs/2401.14295) Local folder path (e.g., C:\python\PipMyRide) Youtube video URL (e.g., https://www.youtube.com/watch?v=KZ_NlnmPQYk) Webpage URL (e.g., https://llm.datasette.io/en/stable/) It outputs the repo, web documentation, arXiv paper or YT transcript to a text file and the clipboard, displaying a token count. It also…
2024 · github.com
- 19DE
Hey! We’ve built a data extraction tool to flexibly automate data and document processing. You’ve probably seen a few of these, so have we! A few of us have been varyingly stuck trying to automate the extraction of borrower financials for the past 5 years. We think that there are a few missing features of most data extraction tools. * They are usually too complex to quickly get up and running * They are overly constrained in terms of what workflows and documents they support We’ve always felt like speed and flexibility were sticking points, so we went slightly orthogonal to the alternatives.…
2024 · go.sea.dev
- 20BL
Hello everyone! I am Jan, CTO and one of the creators of Pathway, the real-time data processing framework. I’m excited to share Pathway’s ready-to-use AI Pipelines, configurable with just YAML! These frameworks offer out-of-the-box solutions for AI search, RAG, and more—optimized for real-time indexing and in-memory processing. What makes it simple? YAML templates! The pipeline templates are fully customizable using YAMLs to fit your needs, from changing the data sources to the choice of the LLM model, all without touching Pathway’s Python code. Thanks to the Pathway data processing engine,…
2024 · pathway.com
- 21SJ
2016 · siphonjs.com
- 22OA
Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Mar 2026 · openui.com
- 23DE
Hi HN! I built Docuglean, an open-source SDK for intelligent document processing that works with OpenAI, Mistral, Google Gemini, and Hugging Face models. The idea came from repeatedly writing boilerplate code to extract structured data from invoices, receipts, and other documents. Instead of wrestling with different API formats, I wanted a unified interface that: - Extracts structured data using Zod/Pydantic schemas - Classifies and splits multi-section documents (e.g., medical records) - Processes documents in batches with automatic error handling - Works locally without APIs (for…
Nov 2025 · github.com
- 24PT
Hey all, I built a quick PoC that scrapes a webpage, sends the content to Gemini Flash, and outputs a clean, structured JSON — ready for RAG workflows. In my case, I’ll use this structured data to enhance models by integrating external knowledge sources during the generation process. Curious if you think this has potential or if there are any use cases I might have missed. Happy to share more details if there's interest!
2025 · structured.pages.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →