Just PyMuPdf! So figures are dropped, a good direction for improvement would be to keep images, but then we'd need to switch to a VLM instead of LLM.
LLMS
-
Gemini 2.5 Pro Achieves State-of-the-Art Video Understanding
By
–
Gemini 2.5 Pro (05-06) is SOTA at most video understanding tasks (by a large margin) . Lots of work by the Gemini multimodal team to make this happen, excited to see developers push this capability in new ways. More details below!
-
Subscribe to AI Engineering Weekly Tutorials on ML and LLMs
By
–
If you're interested in ML, LLMs, and AI Agents and want to receive tutorials every week, subscribe to AI Engineering (for free): http://
aiengineering.beehiiv.com Github Repo to Docling: -
Transform Documents into LLM Ready Data with Python
By
–
Transform any document into LLM ready data in just a few lines of python code! Supports PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc, Markdown and more. Compatible with macOS, Linux and Windows environments. Both x86_64 and arm64 architectures. 100% Open Source
-
Using o3 Prompting for Automated Curriculum Design
By
–
Steal my o3 prompt to create a comprehensive 30-day course to learn and master any topic ——————————————-
ULTIMATE 30-DAY MASTERY ROADMAP ——————————————- ULTIMATE LEARNING ROADMAP ARCHITECT: 30-DAY MASTERY SYSTEM
You are a -
Open source NotebookLM alternative uses Llama 3.3-70B for podcasts
By
–
I've made an open and free version of Google's NotebookLM, and it shows how high the open source tech task has risen! The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks @AIatMeta
's Llama 3.3-70B, with writing the podcast -
MCP Protocol for Automated Backend Service Generation
By
–
who's building a protocol like mcp but for generating backend services its so easy to use an mcp like supabase to setup your project, tables, etc. its still up to the llm to setup the code for your application to work i want the latter to feel like the former, and only a
-
AI costs become outdated quickly as token prices drop
By
–
i kinda think anything around 'how much will it cost' is too out of date as soon as you say it. ie everything is getting cheaper in tokens/context
-
Vatican invests to overcome LLM data wall challenge
By
–
and of course since 2023 we've been dealing with a problem called the data wall, where a large portion of all text data known to humanity has already been indexed, cleaned, and trained into today's large language models. that's why the vatican is planning to invest in new data
-
AI Agent System Prompt Generator Tool
By
–
I should literally charge $99 for this…but today, it’s free. If you build AI agents, this System Prompt Generator will blow your mind. → Create expert-level system prompts
→ Save hours of prompt engineering
→ Works with ChatGPT, Claude, Gemini, DeepSeek RT + comment