Loading video...

Video Failed to Load

Go Home

I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR. It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown. All you need is a Mistral AI API.

skirano's profile picture

Pietro Schirano

101,646 subscribers

48,786 views • 1 year ago •via X (Twitter)

Science & TechnologyEducationArts
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.
0:22

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.

Akshay 🚀

478,020 views • 1 year ago

Unsiloed AI (Unsiloed AI (YC F25)) builds APIs to parse multimodal unstructured data like PDFs, PPTs, and images and convert it into LLM-ready formats like markdown and JSON. Congrats on the launch, @__Aman_Mishra & Adnan!
0:42

Unsiloed AI (Unsiloed AI (YC F25)) builds APIs to parse multimodal unstructured data like PDFs, PPTs, and images and convert it into LLM-ready formats like markdown and JSON. Congrats on the launch, @__Aman_Mishra & Adnan!

Y Combinator

36,120 views • 11 months ago

🚀 New in Heptabase: PDF Parser - Extract text, tables, equations & images (even from scanned PDFs) → save as clean Markdown - Ask AI with precise context (page ranges & paragraphs) → responses include link refs back to the source - MAX mode ensures AI reads every word → perfect for translation, summarization & fact-checking
1:19

🚀 New in Heptabase: PDF Parser - Extract text, tables, equations & images (even from scanned PDFs) → save as clean Markdown - Ask AI with precise context (page ranges & paragraphs) → responses include link refs back to the source - MAX mode ensures AI reads every word → perfect for translation, summarization & fact-checking

Heptabase

36,690 views • 1 year ago

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.
0:33

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Akshay 🚀

252,443 views • 1 year ago

Meet ninjatools.ai: The ultimate all - in - one AI app. NinjaTools is an ultimate all- in - one AI app. Chat with all the latest models, create images, music videos, mindMaps, and analyze PDFs – all in one place. Launch Coin on Believe $Tools + Ninjatools Believe in us on Believe
2:36

Meet ninjatools.ai: The ultimate all - in - one AI app. NinjaTools is an ultimate all- in - one AI app. Chat with all the latest models, create images, music videos, mindMaps, and analyze PDFs – all in one place. Launch Coin on Believe $Tools + Ninjatools Believe in us on Believe

Abdulla

135,931 views • 1 year ago

I love the Big Arch Burger 🍔 I also love Big Harnesses™ and Big Complex PDFs™ with hundreds of pages of tables, images and forms.
0:29

I love the Big Arch Burger 🍔 I also love Big Harnesses™ and Big Complex PDFs™ with hundreds of pages of tables, images and forms.

Jerry Liu

14,041 views • 7 months ago

Claude Cowork is great at reading markdown files, and not great at reading PDFs 📑 I made a simple command that lets you batch parse PDFs -> markdown in an output folder, so you can just point Cowork to it. It lets the agent understand massive amounts of docs much more quickly and accurately (much lower hallucination errors over complex visuals, tables, etc.) In this example, after I parsed 100+ Supreme Court filings into markdown, cowork is able to return the answer in seconds. My wrapper is a simple extension of our very own semtools. Very DIY, will clean this up:
0:36

Claude Cowork is great at reading markdown files, and not great at reading PDFs 📑 I made a simple command that lets you batch parse PDFs -> markdown in an output folder, so you can just point Cowork to it. It lets the agent understand massive amounts of docs much more quickly and accurately (much lower hallucination errors over complex visuals, tables, etc.) In this example, after I parsed 100+ Supreme Court filings into markdown, cowork is able to return the answer in seconds. My wrapper is a simple extension of our very own semtools. Very DIY, will clean this up:

Jerry Liu

65,994 views • 8 months ago

we all know LLMs love markdown i have built a tool that lets you convert any web page to markdown npm i web-to-markdown i ran some benchmarks and the results are shocking at how many tokens you can save🤯
1:18

we all know LLMs love markdown i have built a tool that lets you convert any web page to markdown npm i web-to-markdown i ran some benchmarks and the results are shocking at how many tokens you can save🤯

Nidhi Singh

30,790 views • 7 months ago

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor
1:05

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor

Chris Ashby

11,258 views • 3 months ago

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.
1:05

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.

Shubham Saboo

24,930 views • 7 months ago

WTF Dude... this is like PDF parsing on steroids, NGL. 🤯 OpenDataLoader PDF is a free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎
0:32

WTF Dude... this is like PDF parsing on steroids, NGL. 🤯 OpenDataLoader PDF is a free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎

Ram Maheshwari

28,680 views • 1 month ago

Images 2.0 + Grok Imagine for landing pages is an insane workflow. I start with a DESIGN.md, select the landing page options and specify the app theme. After generating the page, I recreate all the detected images with Images 2.0. Then I turn them to videos. All in one tool.
0:59

Images 2.0 + Grok Imagine for landing pages is an insane workflow. I start with a DESIGN.md, select the landing page options and specify the app theme. After generating the page, I recreate all the detected images with Images 2.0. Then I turn them to videos. All in one tool.

Meng To

15,295 views • 4 months ago

Holy Sh*t... this is like PDF parsing on steroids, NGL. 🤯 A free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎
0:32

Holy Sh*t... this is like PDF parsing on steroids, NGL. 🤯 A free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎

Ram Maheshwari

17,417 views • 13 days ago

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇
0:44

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇

Rohan Paul

149,464 views • 1 year ago

Mistral OCR 3 now returns confidence scores, at page level or word level. Know exactly how sure the model is about what it extracted. Available now via API and to test in Mistral Studio.
0:27

Mistral OCR 3 now returns confidence scores, at page level or word level. Know exactly how sure the model is about what it extracted. Available now via API and to test in Mistral Studio.

Mistral for Developers

30,200 views • 6 months ago

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀
0:30

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

alphaXiv

289,146 views • 11 months ago

PSA 📣: MLX can now pull Mistral/ Llama/ TinyLlama safetensors directly from the Hub! 🔥 pip install -U mlx is all you need! All mistral/ llama fine-tunes supported too! 20,000+ checkpoints overall! P.S. We also provide a script to convert and quantise checkpoints and directly ship them to the Hub! 😍
0:50

PSA 📣: MLX can now pull Mistral/ Llama/ TinyLlama safetensors directly from the Hub! 🔥 pip install -U mlx is all you need! All mistral/ llama fine-tunes supported too! 20,000+ checkpoints overall! P.S. We also provide a script to convert and quantise checkpoints and directly ship them to the Hub! 😍

Vaibhav (VB) Srivastav

60,608 views • 2 years ago

Today we’re releasing GeoSpy CardID 2.0. An AI model purpose-built to identify vehicles from images on social media and security footage. CardID 2.0 can identify thousands of vehicle makes and models and estimate the approximate year from both interior and exterior images.
0:40

Today we’re releasing GeoSpy CardID 2.0. An AI model purpose-built to identify vehicles from images on social media and security footage. CardID 2.0 can identify thousands of vehicle makes and models and estimate the approximate year from both interior and exterior images.

Daniel Heinen

118,721 views • 9 months ago