#go #database #document #ferretdb #golang #mongo #mongo_db #mongodb #mongodb_database #postgres #postgresql

https://github.com/FerretDB/FerretDB

#python #document_ai #document_image_analysis #document_layout_analysis #document_parser #document_understanding #layoutlm #nlp #ocr #publaynet #pubtabnet #pytorch #table_detection #table_recognition #tensorflow

https://github.com/deepdoctection/deepdoctection

#cplusplus #artificial_intelligence #computer_vision #document #document_analysis #document_intelligence #document_recognition #document_understanding #documentai #end_to_end_ocr #multimodal #multimodal_deep_learning #ocr #scene_text_detection #scene_text_detection_recognition #scene_text_recognition #text_detection #text_recognition #vision_language #vision_language_model #vision_language_transformer

https://github.com/AlibabaResearch/AdvancedLiterateMachinery

#python #beit #beit_3 #bitnet #deepnet #document_ai #foundation_models #kosmos #kosmos_1 #layoutlm #layoutxlm #llm #minilm #mllm #multimodal #nlp #pre_trained_model #textdiffuser #trocr #unilm #xlm_e

Microsoft is developing advanced AI models through large-scale self-supervised pre-training across various tasks, languages, and modalities. These models, such as Foundation Transformers (Magneto) and Kosmos-2.5, are designed to be highly generalizable and capable of handling multiple tasks like language understanding, vision, speech, and multimodal interactions. The benefit to users includes state-of-the-art performance in document AI, speech recognition, machine translation, and more, making these models highly versatile and efficient for a wide range of applications. Additionally, tools like TorchScale and Aggressive Decoding enhance stability, efficiency, and speed in model training and deployment.

https://github.com/microsoft/unilm

#python #agent #agents #ai_search #chatbot #chatgpt #data_pipelines #deep_learning #document_parser #document_understanding #genai #graph #graphrag #llm #nlp #pdf_to_text #preprocessing #rag #retrieval_augmented_generation #table_structure_recognition #text2sql

RAGFlow is an open-source tool that helps businesses answer questions accurately using large language models and deep document understanding. It extracts information from various complex data formats, such as Word documents, Excel files, and web pages, and provides grounded citations to support its answers. You can try a demo online or set it up on your own server using Docker. The setup is relatively straightforward, requiring a few steps like cloning the repository, building the Docker image, and configuring the system settings. RAGFlow offers key features like template-based chunking, reduced hallucinations, and compatibility with multiple data sources, making it a powerful tool for truthful question-answering capabilities. This benefits users by providing reliable and explainable answers, streamlining their workflow, and supporting integration with their business systems.

https://github.com/infiniflow/ragflow

#python #ai4science #document_analysis #extract_data #layout_analysis #ocr #parser #pdf #pdf_converter #pdf_extractor_llm #pdf_extractor_pretrain #pdf_extractor_rag #pdf_parser #python

MinerU is a tool that converts PDFs into machine-readable formats like markdown or JSON. Here are the key benefits and features MinerU removes headers, footers, and other unnecessary elements to ensure the text is semantically coherent and in human-readable order, even for complex layouts.
- **Structure Preservation** It extracts images, image descriptions, tables, and table titles.
- **Formula Conversion** Recognizes tables and converts them to LaTeX or HTML format.
- **OCR Support** Supports multiple output formats and various visualization results.
- **GPU and CPU Compatibility**: Works on both CPU and GPU environments, compatible with Windows, Linux, and Mac.

You can try MinerU through an online demo, a quick CPU demo, or by using a GPU for faster processing. For detailed usage, refer to the command line options, API integration, and deployment guides provided.

https://github.com/opendatalab/MinerU

#ruby #daisyui #document_signing #documents #e_signature #github_catalyst #hotwired_turbo #legaltech #open_source #pdf #pdf_sign #pdf_signature #ruby_on_rails #self_hosted #tailwindcss #vuejs #webpack

DocuSeal is a free and open-source platform that helps you fill and sign documents online easily. You can create PDF forms with various field types like signatures, dates, and checkboxes, and these forms can be filled and signed on any device. It offers features like automated emails, multiple language support, and integration with cloud storage services. The platform is mobile-optimized and has tools for user management and API integrations. This makes it convenient for businesses to integrate document signing into their apps, reducing costs and ensuring security and compliance. You can try it out with a live demo or deploy it quickly using various hosting options.

https://github.com/docusealco/docuseal

#typescript #appscript #collaboration #data_table #doc #document #excel #grid #live_share #office #powerpoint #ppt #productivity #sdk #sheet #slide #spreadsheet #word #xlsx

Univer is a powerful office suite that supports spreadsheets, documents, and presentations. It is highly extensible, customizable, and performant. Here are the key benefits Univer works on browsers, Node.js, and soon on mobile devices, with the same API.
- **Feature-Rich** You can personalize its appearance with themes and support for multiple languages.
- **High Performance** It is easily embeddable into your applications.
- **Community Support**: Active community and various resources available for help and contributions.

Overall, Univer makes it easy to create, edit, and collaborate on office documents with a wide range of advanced features.

https://github.com/dream-num/univer

#typescript #digital_signature #document_signing #docusign_alternative #e_signature #esign #esignature #next_auth #nextjs #open_source #pades_standard #pdf #pdf_sign #pdf_signature #postgresql #prisma #self_hosted #signing #typescript

Documenso is an open-source alternative to DocuSign, allowing you to sign documents digitally in a secure and transparent way. You can self-host it, which means you have full control over how it works and can review the code. This builds trust because you aren't relying on a third-party provider. Joining the community helps in creating a more open and trustworthy signing tool. You can test it locally, provide feedback, and even contribute to its development. This gives you flexibility and control over your document signing process.

https://github.com/documenso/documenso

#typescript #angular #angular2 #browser #create #docs #document #docx #docx_generator #express #expressjs #generate #javascript #microsoft #nodejs #office #react #typescript #vuejs #word

You can easily create and modify Word documents (.docx files) using JavaScript with libraries like **docx.js**. This library works both in web browsers and on Node.js servers, making it versatile for different projects. It allows you to generate documents from scratch or edit existing ones, which is helpful for automating tasks or creating dynamic documents. This can save time and reduce errors, making it a useful tool for developers who need to work with Word files in their applications.

https://github.com/dolanmiu/docx

#python #agents #document_search #evaluation #guardrails #llms #optimization #prompts #rag #vector_stores

Ragbits is a tool that helps build and deploy GenAI applications quickly. It offers features like swapping between many language models, ensuring safe interactions with these models, and connecting to various data storage systems. Ragbits also includes tools for managing data and testing prompts, making it easier to develop reliable AI applications. This helps users create more accurate and efficient AI systems by integrating the latest data and reducing errors. Overall, Ragbits makes it faster and more efficient to develop and deploy AI applications.

https://github.com/deepsense-ai/ragbits

#typescript #bun #conversion #convert #converter #document_conversion #elysia #file_conversion #file_converter #hacktoberfest #pdf_converter #self_hosted #tailwindcss #typescript

ConvertX is a self-hosted online file converter that supports over a thousand file formats, including images, videos, documents, e-books, and 3D assets. It lets you convert multiple files at once, offers password protection, and supports multiple user accounts for privacy. You can run it easily using Docker, making it simple to set up on your own server. This means your files stay private since conversions happen locally without sending data to external servers. It uses powerful open-source tools like FFmpeg and ImageMagick, giving you a versatile and secure way to handle all your file conversion needs in one place[1][2].

https://github.com/C4illin/ConvertX

#python #document_analysis #layout_analysis #ocr #parser #pdf #pdf_converter #pdf_parser #python #vlm_ocr

Dolphin is a smart AI tool that can analyze and understand complex document images, like pages with text, tables, formulas, and pictures. It works in two steps: first, it figures out the layout and reading order of the page; then, it quickly parses each element using special prompts. This makes it fast and accurate for turning document images into structured data like JSON or Markdown. You can use pre-trained models and easy code to process single pages, PDFs, or specific elements. This helps you save time and effort when extracting information from complicated documents efficiently.

https://github.com/bytedance/Dolphin