DocQuery, an OSS tool for analyzing documents with LLMs

Hi HN, I built a tool for teaching LLMs how to extract structured data from documents by annotating, not prompt engineering. I’d love your feedback. How it works: - Upload a document (DOCX, PDF, image, etc.) - Select and tag parts of it (supports nesting, arrays, custom tag structures) - Upload another document → click "predict" → see editable annotations - Amend them and save as a new example - Call the API with a third document → get JSON back Use cases: - Identify "important clauses" in contracts - Extract "total value" from invoices - Anything subjective, like "healthy ingredients" on a…

SQL powered operating system instrumentation and analytics.

hi HN! a couple of months ago I had to analyze a few thousand audio recordings to help identify issues with customer support. i was able to get some raw high-level initial results with python scripts invoking LLM APIs, but they were too general and unhelpful. writing basic prompts is easy, but tuning them and making them specific enough to ensure no faint signal is missed is hard. you need to iterate through the data with an initial prompt, segment the data into different buckets, chain another prompt for each bucket etc. Then you need to constantly review the raw data to tweak the prompts…

Hi HackerNews, Lately, I have seen an explosion in posts offering paid APIs/services to get unstructured data into LLMs (i.e. langchain extract, ragflow, unstructured, unstract, just to name a few) and I have been largely disappointed by them, either because they fail to implement multimodal support, fail to give good context for "really tricky" PDFs / Word docs / Powerpoints, or are just plain difficult to use. In light of all these posts I figured I'd share my solution that has been working smoothly for me and my clients. I put it up on GitHub for free so you can check it…

Hi folks. I've been doing some experiments on how LLMs could get more handy in the day to day of working with files (CSV, Parquet, etc). Earlier last year, I built https://datakit.page and evolved it over and over into an all in-browser experience with help of duckdb-wasm. Got loads of feedbacks and I think it turned into a good shape with being an adhoc local data studio, but I kept hearing two main things/issues: Why can't the AI also change cells in the file we give to it? Why can't we modify this grid ourselves? So besides the whole READ and text-to-SQL flows, what seemed…

Document management and insights in the age of AI