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.

🚀 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... show more

Heptabase

18,358 subscribers

36,363 views • 9 months ago •via X (Twitter)

Science & Technology Education Arts

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This AI extracts text, tables, and charts from PDFs with perfect structure and turns them into clean Markdown or JSON. link in comment

This AI extracts text, tables, and charts from PDFs with perfect structure and turns them into clean Markdown or JSON. link in comment

Farhan

23,398 views • 8 months ago

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.

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.

Pietro Schirano

48,786 views • 10 months ago

We’ve launched Web Tab in Heptabase! You can now search Google, YouTube, or open any website directly inside Heptabase — take notes side by side, see AI-suggested related cards, or even chat with the page you’re browsing.

We’ve launched Web Tab in Heptabase! You can now search Google, YouTube, or open any website directly inside Heptabase — take notes side by side, see AI-suggested related cards, or even chat with the page you’re browsing.

Heptabase

15,743 views • 7 months ago

If you open our in-app browsing tool using the split panel, you can now drag text from a web page onto the whiteboard to create new text elements.

If you open our in-app browsing tool using the split panel, you can now drag text from a web page onto the whiteboard to create new text elements.

Heptabase

13,346 views • 2 years ago

ChatGPT for PDFs 🤯 Now convert any PDF into a intelligent chatbot using the AI tool Ask Your PDF. Say goodbye to tedious page scrolling and endless searches - simply ask questions and receive precise answers in a flash!

ChatGPT for PDFs 🤯 Now convert any PDF into a intelligent chatbot using the AI tool Ask Your PDF. Say goodbye to tedious page scrolling and endless searches - simply ask questions and receive precise answers in a flash!

Shubham Saboo

455,578 views • 3 years 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 👇

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

149,264 views • 11 months ago

In the latest version, we've launched the Chat feature! You can now: 1. Chat with AI from OpenAI, Gemini, and Anthropic using your notes as context. 2. Chat with collaborators and track mentions in your Inbox. 3. Drag messages onto whiteboards for deeper exploration.

In the latest version, we've launched the Chat feature! You can now: 1. Chat with AI from OpenAI, Gemini, and Anthropic using your notes as context. 2. Chat with collaborators and track mentions in your Inbox. 3. Drag messages onto whiteboards for deeper exploration.

Heptabase

14,870 views • 1 year ago

💡Ask anything and get answers that think deeper. With AI Answers in #XiaomiHyperOS3, you can search across text, images, or voice — and get precise, AI-powered responses in seconds.

💡Ask anything and get answers that think deeper. With AI Answers in #XiaomiHyperOS3, you can search across text, images, or voice — and get precise, AI-powered responses in seconds.

Xiaomi HyperOS

10,573 views • 7 months ago

In the latest version, you can invite anyone to collaborate on your whiteboard for FREE. Stay tuned—we'll soon have many more updates about conducting collaborative research in Heptabase with both people and AI!

In the latest version, you can invite anyone to collaborate on your whiteboard for FREE. Stay tuned—we'll soon have many more updates about conducting collaborative research in Heptabase with both people and AI!

Heptabase

13,533 views • 1 year ago

We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: Come check out LiteParse:

We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: Come check out LiteParse:

Jerry Liu

318,292 views • 7 days ago

In the latest version, you can add whiteboards as contexts to AI chat! In AI's response, we’ve introduced reference links to the cards and blocks that the response is grounded on, so you’re able to locate the source content.

In the latest version, you can add whiteboards as contexts to AI chat! In AI's response, we’ve introduced reference links to the cards and blocks that the response is grounded on, so you’re able to locate the source content.

Heptabase

14,742 views • 11 months ago

Experience the All-New SciSpace Copilot – Smarter, Faster, Better! 🚀 The latest Copilot upgrade lets you engage with research papers, extracting context-rich, accurate insights instantly. Analyze figures, decode tables, and unlock historical documents with unmatched precision. 🔍 Key Upgrades: ✅ Full-context, AI-powered answers from any research paper ✅ Advanced analysis of figures, tables, and charts ✅ Access to scanned, image-based, and archival papers ✅ Seamless processing of 1000+ pages large, multi-page PDFs Try it out today:

Experience the All-New SciSpace Copilot – Smarter, Faster, Better! 🚀 The latest Copilot upgrade lets you engage with research papers, extracting context-rich, accurate insights instantly. Analyze figures, decode tables, and unlock historical documents with unmatched precision. 🔍 Key Upgrades: ✅ Full-context, AI-powered answers from any research paper ✅ Advanced analysis of figures, tables, and charts ✅ Access to scanned, image-based, and archival papers ✅ Seamless processing of 1000+ pages large, multi-page PDFs Try it out today:

SciSpace

300,390 views • 11 months ago

New Video - Building an AI Agent with your own personality with ai16zdao Eliza • Zero to live in 10 minutes (live coding from scratch) • Export your personality from @x, PDFs, videos, markdown, or images • Automatically posts and replies to posts

New Video - Building an AI Agent with your own personality with ai16zdao Eliza • Zero to live in 10 minutes (live coding from scratch) • Export your personality from @x, PDFs, videos, markdown, or images • Automatically posts and replies to posts

nader dabit

203,148 views • 1 year ago

Our document parsing is really good You can see for yourself with our new feature💫: convert complex PDFs with tables, charts, multi-column layouts to clean markdown/JSON representations through our new clickable templates! 1. We convert complex tables with gaps into clean markdown structures 2. We parse chart + line graphs into interpretable 2d tables Check out LlamaCloud: Come talk to us:

Our document parsing is really good You can see for yourself with our new feature💫: convert complex PDFs with tables, charts, multi-column layouts to clean markdown/JSON representations through our new clickable templates! 1. We convert complex tables with gaps into clean markdown structures 2. We parse chart + line graphs into interpretable 2d tables Check out LlamaCloud: Come talk to us:

Jerry Liu

18,020 views • 4 months ago

NEW: Universal PDF support!⚡️📄 OpenRouter now supports PDF processing for every LLM, including PDFs with images. Multi-model demo & details below:

NEW: Universal PDF support!⚡️📄 OpenRouter now supports PDF processing for every LLM, including PDFs with images. Multi-model demo & details below:

OpenRouter

98,647 views • 1 year ago

Update: The new features rollout this week A Google spokesperson responded to the TechCrunch article: “We’re continuing to display blue links on the search results page in addition to AI responses. If someone chooses to ask a follow-up from an AI Overview, or selects the AI Mode button in the Search box, then that takes them to AI Mode. It doesn’t happen automatically – people have to choose to navigate to AI Mode" (via philip lewis)

Update: The new features rollout this week A Google spokesperson responded to the TechCrunch article: “We’re continuing to display blue links on the search results page in addition to AI responses. If someone chooses to ask a follow-up from an AI Overview, or selects the AI Mode button in the Search box, then that takes them to AI Mode. It doesn’t happen automatically – people have to choose to navigate to AI Mode" (via philip lewis)

Culture Crave 🍿

159,193 views • 1 month ago

ChatDOC turns text & tables in even SCANNED FILEs into actionable data, and makes every word searchable. Don't just read your files - chat with them! #ChatDOC #DataExtraction #aitools #GPT #Claude2

ChatDOC turns text & tables in even SCANNED FILEs into actionable data, and makes every word searchable. Don't just read your files - chat with them! #ChatDOC #DataExtraction #aitools #GPT #Claude2

ChatDOC

26,272 views • 2 years ago

We have just released the first version of our web clipper! It allows you to save and tag web content in Heptabase, and further break it down into atomic knowledge cards.

We have just released the first version of our web clipper! It allows you to save and tag web content in Heptabase, and further break it down into atomic knowledge cards.

Heptabase

27,422 views • 2 years ago

I'm really in love with latex. It can generate excellent figures, tables and equations. I enjoy watching AI use latex as a tool and then turn the final html into well-formatted PDF papers.

I'm really in love with latex. It can generate excellent figures, tables and equations. I enjoy watching AI use latex as a tool and then turn the final html into well-formatted PDF papers.

Crystal

50,733 views • 4 months ago