Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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!

Ai2

87,100 subscribers

282,403 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

PatronusAI

14,879 views • 1 year ago

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.

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.

Avi Chawla

13,147 views • 20 days ago

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!

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!

Jerry Liu

55,931 views • 8 months ago

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Paul Couvert

504,333 views • 1 year ago

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

yazin

293,633 views • 7 months ago

Free and open-source desktop app for downloading videos or extract audio from hundreds of sites, including YouTube and TikTok, with playlists, history, and built-in compression

Free and open-source desktop app for downloading videos or extract audio from hundreds of sites, including YouTube and TikTok, with playlists, history, and built-in compression

AlternativeTo

62,079 views • 8 months ago

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Alvaro Cintas

15,934 views • 1 month ago

Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.

Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.

Owen Colegrove

44,502 views • 2 years ago

Introducing step . parts, an open source directory of 12,000+ STEP parts for your next CAD project Many CAD tools like Autodesk have huge closed libraries of standard mechanical and electrical parts The goal is to build an equivalent catalog for the open source CAD community

Introducing step . parts, an open source directory of 12,000+ STEP parts for your next CAD project Many CAD tools like Autodesk have huge closed libraries of standard mechanical and electrical parts The goal is to build an equivalent catalog for the open source CAD community

Jake Fitzgerald

96,986 views • 5 months ago

NanoBanana 2 just made your static ad agency obsolete. And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.

Peter Quadrel

293,766 views • 7 months ago

This free tool lets Claude scrape Google Maps for you, on autopilot. It's called Google Maps Scraper Kit. Give Claude a city and a business type, and it drives a local scraper to hand back a clean list of businesses, names, phones, emails, websites, ratings, and reviews. → One-command setup, runs entirely on your laptop → Claude Code skill triggers on plain language → Optional social media lookup at no extra cost → Built-in rate-limit safeguards and proxy support for larger jobs 100% Free. Open source.

This free tool lets Claude scrape Google Maps for you, on autopilot. It's called Google Maps Scraper Kit. Give Claude a city and a business type, and it drives a local scraper to hand back a clean list of businesses, names, phones, emails, websites, ratings, and reviews. → One-command setup, runs entirely on your laptop → Claude Code skill triggers on plain language → Optional social media lookup at no extra cost → Built-in rate-limit safeguards and proxy support for larger jobs 100% Free. Open source.

Simplifying AI

229,502 views • 3 months ago

We are launching Open Dots, run the same capabilities in 1/10th of the cost OpenAI shipped Dot yesterday for Pro users. Ours is open source, runs on your Mac and cheaper Here's how it works: - each dot has its own browser that stays logged in securely - it can use and setup triggers on your Gmail, Calendar and 1,500 other apps - you can call it and give it things to do while you talk - dots can coordinate and schedule reminders built with Composio OpenRouter free and open source:

We are launching Open Dots, run the same capabilities in 1/10th of the cost OpenAI shipped Dot yesterday for Pro users. Ours is open source, runs on your Mac and cheaper Here's how it works: - each dot has its own browser that stays logged in securely - it can use and setup triggers on your Gmail, Calendar and 1,500 other apps - you can call it and give it things to do while you talk - dots can coordinate and schedule reminders built with Composio OpenRouter free and open source:

Karan Vaidya

239,350 views • 28 days ago

You can now input PDF files directly to the Responses and Chat Completions APIs! Then let o1, gpt-4o, or gpt-4o-mini generate text with that context.

You can now input PDF files directly to the Responses and Chat Completions APIs! Then let o1, gpt-4o, or gpt-4o-mini generate text with that context.

OpenAI Developers

160,032 views • 1 year ago

$For TreeHacks, we built Braille Bot. It transforms any document—text, images, or websites—into printed braille at a fraction of the cost. It can be easily installed on an existing 3D printer for just $15, significantly cheaper than anything currently available.$

For TreeHacks, we built Braille Bot. It transforms any document—text, images, or websites—into printed braille at a fraction of the cost. It can be easily installed on an existing 3D printer for just $15, significantly cheaper than anything currently available.

Lawton Skaling

58,419 views • 1 year ago

Introducing BlockPicks, a free-to-play, play-to-earn prediction game. The goal is simple, onboard users into web3 on a mass scale with small amounts of $BLOCK each week for their participation. Our original BlockSix game wasn’t built to scale. So, we built a new one from scratch. Here’s what’s new…

Introducing BlockPicks, a free-to-play, play-to-earn prediction game. The goal is simple, onboard users into web3 on a mass scale with small amounts of $BLOCK each week for their participation. Our original BlockSix game wasn’t built to scale. So, we built a new one from scratch. Here’s what’s new…

Blockasset

35,296 views • 2 years ago

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!

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!

Firecrawl

47,432 views • 4 months ago

One more end-of-the-year update for the #holisheet. Next year, we will show more fancy results with this low-cost, high-throughput, label-free, volumetric, open-source, lens-scanning, rotating, HOlographic LIght-SHEET. In collaboration with the PrakashLab. #staycurious

One more end-of-the-year update for the #holisheet. Next year, we will show more fancy results with this low-cost, high-throughput, label-free, volumetric, open-source, lens-scanning, rotating, HOlographic LIght-SHEET. In collaboration with the PrakashLab. #staycurious

Benedict Diederich

24,337 views • 3 years ago

Alright guys, hear me out I was skeptical about Llama 4 coding skills... until I started comparing it to other models, including the earlier version of GPT-4o This thing is free, open source, and honestly pretty close to GPT-4o (pre-update), wild if you think about it

Alright guys, hear me out I was skeptical about Llama 4 coding skills... until I started comparing it to other models, including the earlier version of GPT-4o This thing is free, open source, and honestly pretty close to GPT-4o (pre-update), wild if you think about it

Flavio Adamo

378,298 views • 1 year ago

10 GitHub repos that seem "illegal" but are perfectly legal 1. yt-dlp → Downloads videos from any platform. YouTube Premium charges 16 dollars a month to do less 2. Ollama → Runs AI models on your laptop without paying for APIs. What costs many hundreds a month here comes out to 0 3. Fooocus → Generates images with Midjourney-quality on your GPU. Midjourney charges 30 dollars. This is unlimited and free 4. Whisper → Transcribes audio for free in 99 languages. Otter charges 20 dollars a month to do the same 5. Plausible → The open source alternative to Google Analytics. Companies pay thousands a year. Self-hosted costs 0 6. AppFlowy → The open source Notion. Notion charges 20 dollars per user. Here you get unlimited users on your server 7. Penpot → The open source alternative to Figma. Figma charges 16 dollars per editor. Penpot is self-hosted and free 8. n8n → The open source Zapier. Zapier Pro can cost hundreds a month. n8n runs unlimited automations 9. Cal .com → The open source alternative to Calendly. Calendly Teams charges 16 dollars per user. This is free for personal use 10. Bitwarden → The open source alternative to 1Password. Most charge per user. Bitwarden has a very complete free version All legal. All free. All open source Save them all Share it with that person who keeps paying for tools that have been free all this time and Must follow sanzida for see more Ai content .

10 GitHub repos that seem "illegal" but are perfectly legal 1. yt-dlp → Downloads videos from any platform. YouTube Premium charges 16 dollars a month to do less 2. Ollama → Runs AI models on your laptop without paying for APIs. What costs many hundreds a month here comes out to 0 3. Fooocus → Generates images with Midjourney-quality on your GPU. Midjourney charges 30 dollars. This is unlimited and free 4. Whisper → Transcribes audio for free in 99 languages. Otter charges 20 dollars a month to do the same 5. Plausible → The open source alternative to Google Analytics. Companies pay thousands a year. Self-hosted costs 0 6. AppFlowy → The open source Notion. Notion charges 20 dollars per user. Here you get unlimited users on your server 7. Penpot → The open source alternative to Figma. Figma charges 16 dollars per editor. Penpot is self-hosted and free 8. n8n → The open source Zapier. Zapier Pro can cost hundreds a month. n8n runs unlimited automations 9. Cal .com → The open source alternative to Calendly. Calendly Teams charges 16 dollars per user. This is free for personal use 10. Bitwarden → The open source alternative to 1Password. Most charge per user. Bitwarden has a very complete free version All legal. All free. All open source Save them all Share it with that person who keeps paying for tools that have been free all this time and Must follow sanzida for see more Ai content .

sanzida

23,947 views • 18 days ago