13 comments

  • simonw 8 hours ago

    I implemented a similar pattern in my LLM tool and Python library back in February: https://simonwillison.net/2025/Feb/28/llm-schemas/

    My version works with Pydantic models or JSON schema in Python code, or with JSON schema or a weird DSL I invented on the command-line:

      curl https://news.ycombinator.com/ | \
        llm --schema-multi 'headline,url,votes int' \
        -m gpt-4.1 --system 'all links'
    
    Result: https://gist.github.com/simonw/f8143836cae0f058f059e1b8fc2d9...
  • wodenokoto 16 hours ago

    It’s not extracting data _from_ the model it is using the model to extract structured data from the input.

  • ttul 8 hours ago

    The use case that immediately comes to mind is analysis of legal documents. Lawyers spend a lot of time going through piles of contracts during due diligence for any kind of investment or acquisition transaction, painstakingly identifying concepts that need to be addressed in various ways. LLMs are decent at doing this kind of work, but error-prone (as are humans, by the way). Having a way to visualize the results could be helpful in speeding up the review process of the LLM’s work.

  • andrewrn 8 hours ago

    You could use this to generate character graphs from big novels. Make an app that allows you to input a page number so the model only extracts characters you've encountered thus far.

  • Noumenon72 9 hours ago

    In the example, if `extraction_class` can be any string, how does it know that "relationship" implies it should have attributes "character_1" and "character_2" when your example data didn't?

  • constantinum a day ago

    There is also Unstract(open-source) that helps process structured data extraction. Key differences:

    1. Unstract has a Pre-processing layer(OCR). Which converts documents into LLM readable formats.(helps improve accuracy, and control costs)

    2. Unstract also connects to your existing data sources, making it an out-of-the-box ETL tool.

    https://github.com/Zipstack/unstract

    • ttul 8 hours ago

      I’d throw a vote in the column for Unstract. Making the code AGPL is a first class move for a company that is trying to make money from the hosted version of the same software.

    • fudged71 19 hours ago

      Any idea how it compares with docetl?

    • oriettaxx 21 hours ago

      impressive, really

  • ramkumarkb 9 hours ago

    Does this work with other open-source LLMs like Qwen3 or other OpenAI compatible LLM Apis?

  • hm-nah 20 hours ago

    Oly Chit! This is a BIG deal! Sub-page citations…in-context RAG…built-in HTML UI…this is like the holy grail of deterministic text extraction. I’m trying this ASAP Rocky.

  • brokensegue 7 hours ago

    wiring this to wikidata would be great