When building AI agents, you need them to understand your data—whether it’s PDFs, websites, or internal documents. Most tools for this are closed-source, requiring API keys and external platforms. But what if you could do it all in Python with an open-source library? In this week’s video, I show you how to build a fully open-source document extraction pipeline using Docling. You’ll learn how to: - Extract, parse, and chunk documents for AI processing. - Store and retrieve data efficiently with vector databases. - Build a working chat application that can answer questions based on your documents. Watch the video here.

https://claude.ai/ has out a new model and new feature, where you can upload documents, code, pdfs etc and it will use these as a reference when giving its answers. I have to learn MSIX packaging and planned to purchase a sub, load in all the MSIX documentation and then get help as i bundle up MS Code as a project, but has anyone had any experience in this? Dont want to waste money!

Has anyone had any experience with this AI? Private, Permissionless AI (venice.ai) This is their mission statement: Our mission is to empower users to freely express themselves and explore their creativity without limitations or censorship. We believe in the importance of unrestricted free speech and providing a platform that allows users to push boundaries and challenge themselves without fear of judgment or suppression. We differentiate ourselves from other AI platforms by prioritizing privacy and data security. All user prompt data and response data is stored privately in the user's browser and never stored on our servers, ensuring that users have complete control over their interactions with our AI models. This allows for a more seamless and secure experience, without the risk of data being exploited or misused. Additionally, our commitment to providing a censored-free environment and our focus on user privacy and data security has led to a strong community of individuals who value these principles. This community-driven approach fosters a unique and supportive environment that encourages users to explore their creativity and push the boundaries of what is possible. Overall, our mission is to provide a platform that prioritizes the user's freedom of expression and creativity while maintaining the highest levels of privacy and data security. We believe that this approach sets us apart from other AI platforms and allows us to provide a truly unique and valuable experience for our users. Im going to do some experimenting with it, i usually ask multiple AIs the same thing and sometimes cross reference each others work, I'll update when I have any thoughts.

Hello all, thats me through the first few classes here and appreciate the great work. I just wondered what other things alongside this you are all working on? Im going for a discrete mathematics course just to get a grasp on some fundamentals, and a programming course which does python concepts and command line, git etc: https://www.boot.dev?bannerlord=grimnature57 - Its free if you dont want the gaming style athestic and tutoring, i found using ai if i run into difficulty works great!

Ilya Sutskever is launching Safe Superintelligence Inc., an AI startup that will prioritize safety over ‘commercial pressures.’ https://www.theverge.com/2024/6/19/24181870/openai-former-chief-scientist-ilya-sutskever-ssi-safe-superintelligence