Turn any PDF, image, DOCX, or PPTX into clean... Markdown! 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: (don’t forget to star it ⭐) I recently used Datalab to build an agent that scans an identity document, extracts the required fields, and fills a tax form automatically. The article covers the full workflow, including document parsing, structured extraction, field mapping, and form completion. Read it below.show more

Introducing our /parse endpoint 🔥 Convert any document into... clean data for AI agents via API. - Turn PDF, DOCX, and XLSX files into Markdown or JSON - Preserves reading order and tables - Zero Data Retention support All powered by our 5x faster Rust-based parser.show more

Building RAG is easy. Parsing real, unstructured data is... the hard part. Most tools fail when documents get complicated. RAGFlow by InfiniFlow makes the entire process visual and flawless 🔥 It is an (open-source!) engine built specifically to find the exact needle in a data haystack, even across literally unlimited tokens. The platform comes packed with: → "Quality in, quality out" parsing for highly complex formats → Multiple recall paired with fused re-ranking → A built-in Python and JavaScript code executor for agents → An orchestrable ingestion pipeline Here's why it stands out: 1️⃣ Structural Understanding Instead of just scraping text, it handles tables across pages, scanned copies, slides, and Excel sheets natively using deep document understanding. 2️⃣ Grounded Citations Every answer is verifiable. The UI highlights the exact chunks used, allowing you to trace any response directly back to the source material. 3️⃣ Enterprise Synchronization Keep your context constantly updated with native data sync from Google Drive, Notion, Discord, and Confluence. Stop letting bad document parsing ruin your RAG systems. Best part? It's 100% Free and open-source. Link to the repo in 🧵↓show more

Introducing olmOCR, our open-source tool to extract clean plain... text from PDFs! Built for scale, olmOCR handles many document types with high throughput. Run it on your own GPU for free—at over 3000 token/s, equivalent to $190 per million pages, or 1/32 the cost of GPT-4o!show more

Built a tax document classifier with Jev. We ingest... thousands of tax documents using an LLM pipeline I built last tax season. I read multiple articles as late as April this year claiming AI fails at tax document classification. Wasn't the case back then, and it's proved wrong again now. Jev classifies 100% of our tax document corpus at $0.001 per page. 34x cheaper and 6x faster than the LLM setup. Open sourcing it:show more

Use Qwen Code to parse the PDF document into... markdown content, and then translate it. Follow us for more AI tips and updates!show more

Announcing jina-ocr-v1, our new visual document parser with 3.4B... total parameters and 570M active parameters, with speculative decoding built in. Throw PDFs, scans, tables, charts, or invoices at it and get clean markdown back. Available on 🤗 & Jina Reader `x-respond-with` todayshow more

DOM3 is made from HTML, CSS and Javascript, closer... to a document than a canvas. It's a strange contemporary material that shapes much of our digital lives. The rhythm of endless creation and deletion in DOM3 is a self-driving version of what happens when you browse the web. "The Document Object Model (DOM) connects web pages to scripts or programming languages by representing the structure of a document—such as the HTML representing a web page—in memory." A html element, and a rectangle on a canvas, are not the same thing. It's a different material. Even if it all ends up controlling the same pixels, the process is different. The html element kind of actually exists, in this abstract context of a document object model. And in memory, in the moment. If it was possible to measure its weight, it would be heavier than a pixel on a canvas.show more

Introducing Extend UI — open-source components for document agents... - 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more - fully customizable - MIT licensed when we started, we tried every file viewer and document component library we could find unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for Extend it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community it's useful for building agents, user-facing document flows, or internal tools we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day) it also works with design system agents like Magic Patterns for faster exploration and prototyping available today on the shadcn component registry! some examples in 🧵show more

We're launching 5x faster document parsing in the Firecrawl... MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!show more

Turn complex docs into clean, LLM-ready data! Every AI... company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!show more

Parsing PDFs at scale with LLMs is cost prohibitive.... Newer models (e.g. gemini 3) are good at reading pdfs, but you burn unnecessary vision tokens even when the page is text heavy. We’ve built in a “cost-optimizer” within LlamaParse that will dynamically route pages to fast/cheap parsing depending on its complexity. Complex pages (e.g. those with tables/charts/diagrams) will still get routed to our VLM-enabled modes. This will let you save anywhere from 50-90% of parsing costs, at much higher accuracy compared to the comparable mode of feeding screenshots into VLMs. Check it out!show more

If you’re building one of these, we should talk:... - AI search that answers from live web pages - RAG pipelines that go stale between crawls - Agents that need to see a page the way a person in that country sees it Teneo’s Live Web Data API loaded 97.7% of 150,000 test pages, including online shops and job boards. Free 7-day pilot. DMs open.show more

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR... is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!show more

Stop manually making flowcharts. Try this GitHub skill with... Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.show more

Introducing Pages on Superset is now Paradev mobile Your... agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.show more

I tested Nutrient on a CMS-1500 health claim, which... is exactly the kind of document that can trip up extraction systems. The red grid alone can get mangled by scanners, and the form is packed with dense fields where one wrong value can matter. What stood out to me was the grounding. Hover over any extracted field and Nutrient shows the exact place on the original claim where that value came from. So instead of asking “did the AI probably get this right?”, you can check the evidence yourself. For healthcare documents, that feels like a much better standard: not just extraction, but extraction you can actually verify.show more

Ask Claude to document and describe the main flows... in your app and output in a single page html + json data file. Incredibly useful for humans and the JSON file is very useful for explaining the flow to the LLM when working on new features/bugfixes.show more

today we're open-sourcing Krea Realtime. this 14B autoregressive model... is 10x larger than any open-source equivalent, and it can generate long-form videos at 11 fps on a single B200. weights and technical report below 👇show more

I am speechless --> get it. Now I can... use Cartesia's Managed Agents to turn any simple prompt into a working voice agent in minutes! You choose the instructions, pick an LLM and a voice, and connect the tools your agent needs. Cartesia takes care of the voice infrastructure behind the scenes and they're so good at it! You can build agents that answer questions, search knowledge bases, book appointments, and interact with people over the phone. A few things that stand out: • Supports 44+ languages • Handles interruptions naturally • Connects with your own tools and knowledge bases • Works through a browser or phone call The exciting part is not just making an AI talk. It is giving it a useful job and letting it get things done through a conversation. I am curious to see what developers build with this. What would your first voice agent do? Cartesia #VoiceAI #AIAgents #techshow more