magicpdf / Magic-DocLinks
conversion doc(pdf/html/doc/docx/ppt/pptx)to markdown
☆48Updated last year
Alternatives and similar repositories for Magic-Doc
Users that are interested in Magic-Doc are comparing it to the libraries listed below
Sorting:
- 360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute☆305Updated last year
- Analysis of Chinese and English layouts 中英文版面分析☆260Updated 6 months ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆125Updated 7 months ago
- 中文原生检索增强生成测评基准☆124Updated last year
- TianGong-AI-Unstructure☆69Updated this week
- Imitate OpenAI with Local Models☆90Updated last year
- ☆106Updated 2 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆140Updated last year
- ☆234Updated last year
- 基于序列表格识别算法推理 库,集成PP-Structure和modelscope等表格识别算法。☆409Updated 5 months ago
- LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA☆517Updated last year
- gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。☆244Updated this week
- A High-efficiency Open-source Toolkit for Table-to-Latex Task☆274Updated 2 months ago
- [ACL2025 demo track] ROGRAG: A Robustly Optimized GraphRAG Framework☆194Updated last month
- code for piccolo embedding model from SenseTime☆145Updated last year
- 文档方向分类☆222Updated last year
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题: 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆63Updated last year
- MPB (Miner-PDF-Benchmark) is an end-to-end PDF document comprehension evaluation suite designed for large-scale model data scenarios.☆23Updated last year
- [NAACL 2024] Visually Guided Generative Text-Layout Pre-training for Document Intelligence☆149Updated last year
- [ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"☆259Updated 9 months ago
- PDF Parsing Tool: GOT's vLLM acceleration implementation, MinerU for layout recognition, and GOT for table formula parsing.☆65Updated last year
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆141Updated last year
- ☆67Updated last year
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆39Updated last year
- ☆175Updated last year
- 研究GOT-OCR-项目落地加速,不限语言☆62Updated last year
- Code implement reposity of Paper HiQA☆104Updated 11 months ago
- 📝 针对文档类图像做内容提取,将文档类图像一比一输出到Word或者Txt中,便于进一步使用或处理。后续计划支持输入PDF/图像,输出对应json格式、Txt格式、Word格式和Markdown格式。☆207Updated last year
- A unified tool to generate fine-tuning datasets for LLMs, including questions, answers, and dialogues. ✨🤖📚💬☆62Updated 10 months ago
- ☆28Updated last year