Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
Repository Index
47,133 repositories indexed
1–24 of 26 · Most stars
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
TranslatedChinese word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, constituency parsing, semantic dependency parsing, semantic role labeling, coreference resolution, style transfer, semantic similarity, new word discovery, keyword and keyphrase extraction, automatic summarization, text classification and clustering, pinyin and Simplified/Traditional Chinese conversion, natural language processing
- nlp
- natural-language-processing
- hanlp
- pos-tagging
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
- text-similarity
- natural-language-processing
- word-embeddings
- python
A simple screen parsing tool towards pure vision based GUI agent
Chronic is a pure Ruby natural language date parser.
Deep neural network to extract intelligent information from invoice documents.
- invoice
- invoice-management
- invoices
- invoice-insight
Direct Sparse Odometry
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
Owl - OCaml Scientific Computing @ https://ocaml.xyz
- matrix
- linear-algebra
- ndarray
- statistical-functions
C++ library for solving large sparse linear systems with algebraic multigrid method
- amg
- c-plus-plus
- sparse-linear-systems
- opencl
Parse human names into title, given, middle, family, suffix, nickname and maiden name. Typed, zero-dependency, CJK-aware.
- python
- text-processing
- text-parser
- python-module
Numerical linear algebra software package
- linear-algebra
- hpc
- gpu-computing
- cuda
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
A curated list of NLP resources for Hungarian
- nlp
- natural-language-processing
- text-mining
- information-retrieval
Sparse matrix formats for linear algebra supporting scientific and machine learning applications
- go
- golang
- matrix
- scientific-computing
MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
A Library to parse natural language in pure Clojure and ClojureScript
- natural-language-processing
- clojure
- clojurescript
- pos-tagger
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
Natural language parser for recurring events
C# math expression library with symbolic computation support
- csharp
- dotnet
- expression-parser
- math
An Earley parser written in Ruby
- ruby
- rubynlp
- natural-language-processing
- nlp
Multilingual library to easily parse date strings to java.util.Date objects.
- clojure
- parsing
- date-time
- date-parser
PostgreSQL migration linter. Blocks unsafe migrations before merge: 112 rules, the real Postgres parser, lock analysis, auto-fix. CLI, GitHub Action, MCP.