marker

给 AI 喂电子 PDF，可以先用 Marker 转成 Markdown，保留表格和标题。 没显卡也能跑：fast 模式关闭 OCR 后只用 CPU。但扫描页和公式会跳过，别拿它处理扫描合同。配图为官方纯 CPU 测试。 datalab-to/marker t.co

ler PDF é difícil, precisa de umas soluções mirabolantes, estou testando esse cara aqui datalab-to/marker

Copiar una tabla de un PDF y que se desordene todo… Marker convierte documentos a Markdown o JSON y contempla tablas y ecuaciones. Interesante para llevar esa información a otros sistemas. datalab-to/marker

PDF tables and equations breaking when you copy them? 📑 Marker converts documents into Markdown, JSON or HTML and extracts images. Useful for building searchable notes. 🧰 datalab-to/marker #PDF #浇朋友 #蓝朋友 #互关 #fo

PDF 里的表格和公式，一复制就乱？📑 Marker 可以把 PDF 等文档转成 Markdown、JSON 或 HTML，并提取图片。整理资料更省心。🧰 datalab-to/marker #PDF #浇朋友 #蓝朋友 #互关 #fo

Marker GitHub Overview: How Structured Document Parsing Preserves Layout for RAG marker by datalab-to: datalab-to/marker Marker is a document conversion pipeline for turning PDFs, EPUBs, DOCX, and XLSX files into structured Markdown or JSON. This overview explains why flat OCR can damage multi-column reading order, tables, equations, and semantic boundaries used by RAG and vector-database workflows. Marker maps document elements and preserves structure, reconstructs tables, renders mathematics as LaTeX, and removes recurring headers and footers. The architecture discussion follows the version 2.0 rewrite: lightweight CPU workers handle ordinary extraction and layout detection, while targeted difficult regions can use a shared GPU-backed Surya inference server or hybrid LLM routing. The final section covers memory, temporary storage, Linux/WSL2/macOS support, Python 3.10+, and the Python 3.14/Pillow compatibility warning described in the source. TimeStamps: 0:00 Why flat OCR loses document structure 0:32 Marker’s layout-aware conversion pipeline 1:31 Version 2.0 decouples CPU workers and GPU inference 3:52 CPU extraction with pdftext and rf-detr 5:23 Fallback routing for difficult regions 6:05 Hybrid mode and contextual corrections 6:43 Memory and temporary storage constraints 7:38 Supported platforms and Python compatibility 8:14 Python 3.14 and the Pillow conflict 8:25 Repository reference and final architecture takeaway 🧩 Layout-aware parsing for RAG document ingestion 📄 Markdown and JSON outputs with tables and LaTeX ⚙️ CPU extraction with targeted GPU/VLM routing 🖥️ Memory, storage, platform, and Python compatibility Marker is most relevant when flat text extraction is not enough to preserve a document’s meaning. Its decoupled design keeps ordinary parsing lightweight while reserving heavier visual-language processing for difficult regions. The practical tradeoffs are the required memory and temporary storage, supported runtime choices, and the Pillow compatibility boundary for Python 3.14. #Marker #DocumentParsing #RAG [de-DE] YNAS ynp_e005c45888a01b25 Cinematic Privater automatisierter Staging-Upload. Paketidentität: ynp_e005c45888a01b25; Ausgabe: cinematic. [es-US] YNAS ynp_e005c45888a01b25 cinematográfico Carga de entorno de prueba de automatización privada. Identidad del paquete: ynp_e005c45888a01b25; salida: cinematográfica. [fr-FR] YNAS ynp_e005c45888a01b25 cinématique Téléchargement de l'environnement de test d'automatisation privé. Identifiant du package : ynp_e005c45888a01b25 ; sortie : cinématique. [hi] YNAS ynp_e005c45888a01b25 सिनेमैटिक निजी स्वचालन स्टेजिंग अपलोड। पैकेज पहचान: ynp_e005c45888a01b25; आउटपुट: सिनेमाई। [id] YNAS ynp_e005c45888a01b25 sinematik Unggahan staging otomatisasi pribadi. Identitas paket: ynp_e005c45888a01b25; output: sinematik. [it] YNAS ynp_e005c45888a01b25 cinematic Caricamento di automazione privata. Identità del pacchetto: ynp_e005c45888a01b25; output: cinematografico. [pt-BR] YNAS ynp_e005c45888a01b25 cinematográfico Upload de teste de automação privada. Identificação do pacote: ynp_e005c45888a01b25; saída: cinemática.

Convert Complex PDFs to Clean Markdown in Seconds with Marker! 💻⚡ (Open Source) Today we brought another repo called Marker — the open-source high-speed PDF to Markdown converter! 💻⚡ Stop letting messy PDF extractions ruin your RAG context windows with broken tables, garbled columns, and unreadable equations. In our GitHub Repo Series on AI Skill Vault, we explore how Marker uses deep layout parsing to convert complex documents, scientific papers, and multi-column PDFs into clean, structured Markdown in seconds. ⭐ GitHub Repository: VikParuchuri/marker 💻 Language: Python / PyTorch 🛠️ Key Features: High-speed PDF-to-Markdown conversion, layout-aware multi-column parsing, automated table extraction, LaTeX math formatting, and GPU-accelerated processing. 📌 TIMESTAMPS: 0:00 - Today we brought another repo called Marker 0:10 - How It Helps: Converting complex PDFs & scientific tables into clean Markdown 0:20 - Code Demo: `pip install marker-pdf`, running `marker_single` CLI & inspecting Markdown outputs 0:30 - Subscribe to AI Skill Vault Want more practical AI repos, agents and automation? Subscribe to AI Skill Vault. #github #developer #ai #python #marker #pdfparsing #markdown #rag #opensource #coding #aiskillvault

How does this differ from open source cli tools such as Marker (datalab-to/marker)? Also, it seems disingenuous to have “locally” in the title when your default is cloud inference providers and I don't see you naming a recommended LLM that could be hosted locally and is proven to work well for this task. You list “Your files” under “Stays on your machine” and then require an API key for a cloud provider.

ReceiptGuard: A privacy-first, locally running invoice and receipt data extractor designed specifically for freelancers and solo-preneurs. This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built ReceiptGuard: A privacy-first, locally running invoice and receipt data extractor designed specifically for freelancers and solo-preneurs. Freelancers hate manually typing out data from receipts for taxes, but cloud-based AI OCR tools require uploading sensitive financial documents, creating a privacy risk and often costing a recurring monthly subscription. ReceiptGuard solves this by running entirely on the user's laptop. It extracts structured JSON (Date, Vendor, Amount, Tax, Category) from PDFs and images, allowing users to export directly to CSV. Because it runs locally with zero per-use API fees, it can be sold as a highly affordable, one-time-purchase desktop app ($39 lifetime) rather than a subscription, making it a viable side hustle that users actually want to pay for. Demo (Note: In your actual DEV post, you can replace this note with a short Loom video or GIF of the app in action. Below is the system architecture.) graph TD A[User Uploads Receipt PDF/Image] --> B[Local OCR: Tesseract / Marker] B --> C{Extracted Raw Text} C --> D[Ollama Local Inference Server] D -->|Llama-3-8B-Instruct| E[LangChain Prompt Template] E --> F[Structured JSON Output via Pydantic] F --> G[Gradio Local Web UI] G --> H[Export to CSV/Excel] style D fill:#f9f,stroke:#333,stroke-width:2px style E fill:#bbf,stroke:#333,stroke-width:2px style A fill:#dfd,stroke:#333,stroke-width:2px Code The entire project is open-source. You can explore the codebase, run it locally, or fork it for your own use: 🔗 hardikxk/receiptguard-ai How I Built It ReceiptGuard is built entirely on open-source AI and local-first principles: 1. Local Inference Engine: Ollama serves as the local inference backend, running the Llama-3-8B-Instruct open-weight model. This provides robust reasoning and formatting capabilities without needing an internet connection. 2. Orchestration Framework: LangChain is used to chain the OCR output into a structured prompt, enforcing strict JSON schema output using Pydantic to ensure reliable data parsing. 3. Document Parsing: Marker (an open-source PDF/OCR toolkit) handles the initial extraction of text from messy receipt images and PDFs before passing it to the LLM. 4. User Interface: A simple, clean local web interface built with Gradio, making it accessible to non-technical users without requiring them to touch the command line. Why Does Open Innovation Matter? For this specific side hustle, open-source AI isn't just a nice-to-have; it is the core value proposition: - Uncompromising Privacy: Closed APIs require uploading sensitive client financial data to third-party servers. With open-weight models running locally, I can guarantee users that their data never leaves their machine. This is a massive selling point for freelancers with strict NDA or data-handling requirements. - Viable Side Hustle Economics: Closed API costs (e.g., $0.10–$0.50 per document) destroy the margins of a one-time-purchase desktop app. Local inference has a marginal cost of $0, making a $39 lifetime license genuinely profitable and sustainable. - Zero Vendor Lock-in: If a new, more hardware-efficient model drops (like Phi-3 or a new Mistral variant), I can swap the model backend in a single line of code. I am not at the mercy of a provider's pricing changes, deprecations, or rate limits. My Agent Session I used an open-source agent harness to iterate on the prompt engineering and ensure consistent JSON output across messy, real-world receipt formats. (You can view the saved DevRelay agent session showing the prompt iteration and testing process here: DevRelay Session Link) My First User I shared an early build with Sarah, a freelance graphic designer who manages 10+ clients and constantly complains about tax season. She was immediately skeptical of cloud-based receipt scanners because her contracts require her to keep financial data confidential. When I showed her ReceiptGuard running entirely offline via Ollama, her reaction was: "Wait, it actually doesn't upload anything to the cloud?" She processed a month's worth of messy coffee shop and software subscription receipts in under 2 minutes. When I asked if she would pay for this, she said: "I currently pay $15/month for a cloud tool I hate. I would gladly pay $40 once for this if it stays offline and keeps my client data safe." Her immediate feature request: A direct export to a QuickBooks-compatible CSV format (which I am actively adding to the v1.1 roadmap!). Prize Categories - Open Source AI - Local First / Privacy - Developer Productivity --- Thanks for participating!

Turn any PDF, image, doc or PPT into clean Markdown (100% open-source with 40k stars) Production workloads contain millions of pages, mixed formats, inconsistent layouts, low-quality scans, and documents written in dozens of languages. Datalab Marker v2 (open-source with 40k stars) handles that workload at scale through one open-source document parsing pipeline. It recovers: - Reading order - Complex equations - Images and captions - Tables and nested tables - Text from scanned pages - Headings and page structure It can return Markdown, JSON, or HTML for RAG pipelines, search indexes, data extraction systems, document agents, and archive migrations. Marker v2 runs at up to 23.7 pages per second on a single B200 GPU and supports more than 90 languages. GitHub repo: datalab-to/marker (don’t forget to star it ⭐) 👉 Over to you: How are you running document parsing pipelines at scale today? ____ Share this with your network if you found this insightful ♻️ Find me → Avi Chawla. Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.