DOC·01★ 23k
DeepSeek-OCR
A vision model that reads documents and compresses pages into very few tokens, making long PDFs cheap to feed a model.
For anyone dealing with OCR — optical context compression.
← all categoriesDOC · category
Documents & OCR
Reading messy PDFs, scans and images into clean, structured text.
5 tools in this category
DOC·02★ 62k
Docling
Converts PDFs, Word, and slides into one clean, structured format for AI — preserving headings, reading order, and tables that most extractors mangle.
I use this — can recommend.
DOC·03★ 9.0k
Dolphin
Parses document images — tables, columns, figures — into clean structured layout for downstream use.
DOC·04★ 37k
LangExtract
Uses an LLM to pull structured fields out of messy text, keeping each value linked back to where it came from.
DOC·05★ 19k
Unlimited-OCR
Baidu's OCR model built for one-shot long-horizon parsing — it reads an entire long, multi-page document in a single pass into clean structured text, pushing the DeepSeek-OCR idea a step further for real-world PDFs.