velviagris / PaddleOCRFastAPILinks
A simple way to deploy PaddleOCR based on FastAPI. (PaddleOCR 的 FastAPI 快速部署方案)
☆159Updated 2 months ago
Alternatives and similar repositories for PaddleOCRFastAPI
Users that are interested in PaddleOCRFastAPI are comparing it to the libraries listed below
Sorting:
- Based on RapidOCR, extract the PDF content☆184Updated 7 months ago
- 开源的中英文离线 OCR,使用 PaddleOCR 实现,提供了简单的 Web 页面及接口☆131Updated 3 years ago
- Using GPT to parse PDF☆102Updated last year
- MinerU API server☆84Updated last year
- BrainX 是一个智能系统,分析各种媒体格式,整合到知识库,并生成定制内容,包括机器人、洞察和媒体。它旨在为用户提供个性化和自动化的解决方案。☆74Updated 5 months ago
- 视频理解:千问视频多模态模型 & Dify☆66Updated last year
- 图片搜索引擎,很简单。三步构建属于你自己的图片搜索引擎,掌握向量数据库和以图搜图、文本搜索图片。☆148Updated 2 years ago
- dify外接fastgpt知识库的工具☆77Updated 9 months ago
- Convert files into markdown to help RAG or LLM understand, based on markitdown and MinerU, which could provide high quality pdf parser.☆131Updated 9 months ago
- Python3 package for Chinese/English OCR,use paddleocr-v5 onnx model(~20MB), with ultra-fast inference speed. 基于ppocr-v5-onnx模型推理,中英文OCR开源…☆119Updated 5 months ago
- AI Q&A Search Engine ➡️ 基于LangChain和SearXNG打造的开源AI搜索引擎☆213Updated 7 months ago
- 基于SenseVoice的funasr版本进行的api发布,可以无缝对接oneapi☆89Updated last year
- 无缝集成处理和调度 Dify & Dify on WeChat,Web 可视化多用户管理/一键启动 ChatBot,简化了令人惊叹且响应迅速的 ChatBot 应用程序的创建。☆71Updated last year
- Python 接入文多多AiPPT,通过主题/文件/网址等方式生成PPT,支持原生图表、动画、3D特效等复杂PPT的解析和渲染,支持用户自定义模板,支持智能添加动画。AI generates PowerPoint Presentation, Supports parsing…☆29Updated last year
- Image Search by Image, Image Search Engine Based on Graph Vector And Vector Database(以图搜图,基于图向量和向量数据库的图片搜索引擎)☆17Updated 7 months ago
- an open high-performance Optical Character Recognition (OCR) toolkit☆305Updated 5 months ago
- 如需体验TextIn文档解析,请访问 https://cc.co/16YSIy☆181Updated 6 months ago
- 😆 Generate PPT by LLM follow your template. 📢 Not only use llm to generate ppt, but also according to your favorite ppt template. Just…☆96Updated last year
- bisheng-unstructured library☆57Updated 7 months ago
- Analysis of Chinese and English layouts 中英文版面分析☆259Updated 4 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
- 混合票据识别,增值税专用发票, 增值税普通发票, 增值税电子专用发票, 增值税电子普通发票, 增值税普通发票(卷式), 非税财政电子票据, 过路费发票, 火车票, 飞机票, 客运票, 出租车票, 定额, 通 用机打发票☆148Updated 3 years ago
- lang2openai☆74Updated last year
- 基于 Serverless 架构部署通用文字识别 PaddleOCR☆125Updated 3 months ago
- A book room based Agent | 智能书库☆55Updated 8 months ago
- WebUI for using SmolDocling-256M-preview☆13Updated 9 months ago
- dify-connector is a tool to publish Dify apps to various IM platforms. | dify-connector 是一个将 Dify 发布到各种 IM 平台的工具。☆101Updated last year
- GOT-OCR的GUI版本,提供OCR、导出PDF、批处理等功能,但不提供训练功能☆179Updated last month
- ragflow中的ocr部分,非官方项目☆52Updated last year
- Dive into LLM Agents☆18Updated last year