PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o
I've developed a Python API service that uses GPT-4o for OCR on PDFs. It features parallel processing and batch handling for improved performance. Not only does it convert PDF to markdown, but it also describes the images within the PDF using captions like `[Image: This picture shows 4 people waving]`. In testing with NASA's Apollo 17 flight documents, it successfully converted complex, multi-oriented pages into well-structured Markdown. The project is open-source and available on GitHub. Feedback is welcome.
PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o launched on September 22, 2024 with 191 votes, #309 of 5,281 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
PDF to MD by LLMs is a Python API service that converts PDF documents into structured Markdown format using GPT-4o for optical character recognition. It extracts text, tables, and generates descriptive captions for images within PDFs. The tool handles parallel processing and batch operations for improved performance, successfully managing complex, multi-oriented pages. Designed for developers and researchers who need to digitize and restructure PDF content, it is open-source and available on GitHub.
written from the facts on this page · September 2026
From the sources
PDF to markdown using vision LLMs — tables, layouts, and structure preserved - yigitkonur/api-llm-ocr
Does a similar job
all alternatives →
Ocrbase – pdf → .md/.json document OCR and structured extraction APIJan 2026 · github.com · ▲99📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. - majcheradam/ocrbase
LLM-aided OCR – Correcting Tesseract OCR errors with LLMs2024 · github.com · ▲479Almost exactly 1 year ago, I submitted something to HN about using Llama2 (which had just come out) to improve the output of Tesseract OCR by correcting obvious OCR errors [0]. That was exciting at the time because OpenAI's API calls were still quite expensive for GPT4, and the cost of running it on a book-length PDF would just be prohibitive. In contrast, you could run Llama2 locally on a machine with just a CPU, and it would be extremely slow, but "free" if you had a spare machine lying around. Well, it's amazing how things have changed since then. Not only have models gotten a lot better,…
I just open sourced my document/website extractor for Vision-LLMs2024 · github.com · ▲37Hi 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…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
