Dependable AI in Airborne Systems ✈️
Integrating AI into safety-critical embedded systems in aeronautics presents unique challenges. This talk will address the complexities of ensuring reliability, predictability, and compliance with stringent safety standards.
poolside Offsite in Peniche 🥽
Still buzzing from an incredible exchange with the leadership team poolside where we explored a (not-so-distant) future where humans and AI agents work side by side.
AI x Innovation @ AIHub 🧠
Today, the AI x Innovation team went on a ‘school trip’ to the AIHub by Unicorn Factory Lisboa to talk with startups working on the bleeding edge of AI.
AI Red Teaming @ Critical Software 🟥
In collaboration with the AIHub by Unicorn Factory Lisboa, we’re organizing a semi-private red teaming exercise focused on AI that will take place in our Lisbon office. This will be a unique event that brings together enterprises and some of the most promising startups in the field to test the limits of AI systems in a controlled, ethical, and collaborative environment.
📨 Feel free to DM me if you’d like to know more.
Critical Software @ Liga dos Inovadores 💡
The podcast Liga dos Inovadores just launched a new episode featuring yours truly, where I talk about our work at Critical Software and the challenges of using AI in Defense (OVERSEE) and Space (Karvel).
🎧 Listen to the episode now: Barcos a andar a par, a mudar a rota ou a afastarem-se rapidamente da costa: como um “mapa dos mares” deteta atividades ilícitas
Safety-Critical AI is now Awesome 🚀
Awesome Safety-Critical AI contains a curated list of references on the role of AI in safety-critical systems i.e. systems whose failure can result in loss of life, significant property damage or harm to the environment.
AI in critical systems is not about polishing demos or chasing benchmarks. It’s about anticipating chaos - and designing for it.
This isn’t just another (awesome) list. It’s a call to action!
🌟 Let me know what you think and don’t forget to star it!
Command AI Assistant (Bedrock Edition) ⛰️👨💻
A Zsh plugin powered by Amazon Bedrock that analyzes command execution and provides instant feedback when commands fail or produce unexpected results.
🙌 This project was adapted from Sean Smith’s Command AI Assistant powered by Ollama.
👨💻 All code and documentation is available at github.com/JGalego/command-ai-bedrock.
LLM Goblet 🍷 > LLM proxy application powered by AWS Chalice and LiteLLM
LLM proxy application powered by AWS Chalice and LiteLLM.
👨💻 All code and documentation is available at github.com/JGalego/LLM-Goblet.
cl-bedrock 👽⛰️ > Amazon Bedrock meets Lisp
A simple Common Lisp library for Amazon Bedrock, a fully managed service that makes it easy to use foundation models from third-party providers and Amazon.
👨💻 All code and documentation is available at github.com/JGalego/cl-bedrock.
Serverless LLM Proxy ✨ /֎-Compatible/
OpenAI-compatible proxy on AWS Lambda powered by LiteLLM and Amazon API Gateway powered by LiteLLM.
👨💻 All code and documentation is available at github.com/JGalego/Serverless-LLM-Proxy.
VektorDB 🏹 > Minimal Vector Database for Teaching
A minimal vector database for educational purposes.
👨💻 All code and documentation is available at github.com/JGalego/VektorDB.
Hacking GraphRAG with Amazon Bedrock 🌄
Learn how to run GraphRAG pipelines backed by Amazon Bedrock using LiteLLM proxy.
📝 Read the full article on AWS Community.
Make Programs, not Prompts: DSPy Pipelines with Llama 3 on Amazon SageMaker JumpStart
Learn how to create ML pipelines with DSPy powered by Meta’s Llama 3 70B Instruct model running on Amazon SageMaker.
📝 Read the full article on AWS Community.
Leaving no language behind with Amazon SageMaker Serverless Inference 🌍💬
Host a high-quality translation model at scale using Amazon SageMaker Serverless Inference.
📝 Read the full article on AWS Community.
Build Document Processing Pipelines with Project Lakechain
Learn how to create cloud-native, AI-powered document processing pipelines on AWS with Project Lakechain.
📝 Read the full article on AWS Community.
Your idea is my command: multi-agent collaboration for software development 💡🚀
Create your own virtual software company with Amazon Bedrock ⛰️ and ChatDev 👨🏼💻 and use it to build custom applications through LLM-powered multi-agent interactions.
📝 Read the full article on AWS Community.
Running LangChain.js Applications on AWS Lambda
Learn how to run LangChain.js apps powered by Amazon Bedrock on AWS Lambda using function URLs and response streaming.
📝 Read the full article on AWS Community.
Scrape All Things: AI-powered scraping with ScrapeGraphAI 🕷️ and Amazon Bedrock ⛰️
Learn how to extract information from documents and websites using natural language prompts.
📝 Read the full article on AWS Community.
Bug hunting with Amazon Bedrock and SWE-Agent 👨💻
Use SWE-Agent with Amazon Bedrock to create your own software engineering agent that can fix real-life bugs and issues in GitHub repositories.
📝 Read the full article on AWS Community.
Fighting Hallucinations with LLM Cascades 🍄
Learn how to implement FrugalGPT-style LLM cascades on top of Amazon Bedrock using LangChain and LangGraph without breaking the bank.
📝 Read the full article on AWS Community.
👨💻 All code and documentation is available at github.com/JGalego/FrugalBedrock.
Running Small Language Models on AWS Lambda 🤏
In this post, I’m going to show you a neat way to deploy small languages models (SLMs) or quantized versions of larger ones on AWS Lambda using function URLs and response streaming.
📝 Read the full article on AWS Community.
👨💻 All code and documentation is available at github.com/JGalego/SLaMbda.
Mapping embeddings: from meaning to vectors and back
My adventures with RAGmap 🗺️🔍 and RAGxplorer 🦙🦺 with a light introduction to embeddings, vector databases, dimensionality reduction techniques and advanced retrieval mechanisms.
📝 Read the full article on AWS Community.
📢 UPDATE: A new interactive and extended version of this article is available here.
#TGIFun🎈 Building GenAI apps with managed AI services
Some random thoughts on managed AI services and their place in the GenAI stack… with examples.
📝 Read the full article on AWS Community.
🧪 The Rise of the LLM OS: From AIOS to MemGPT and beyond
A personal tale of experimentation at the intersection of LLMs and operating systems with some thoughts on how they might work together in a not-so-distant future.
📝 Read the full article on AWS Community.
#TGIFun🎈 YOLambda: Running Serverless YOLOv8/9
In this episode of #TGIFun🎈, I’d like to demonstrate a quick and easy way to deploy YOLOv8/9 👁️ on AWS Lambda using the AWS SAM (Serverless Application Model) CLI.
📝 Read the full article on AWS Community.
👨💻 All code and documentation is available at github.com/JGalego/YOLambda.
Deploy LangChain 🦜🔗 applications on AWS with LangServe 🦜️🏓
Learn how to deploy LangChain applications with LangServe in minutes on Amazon ECS and AWS Fargate using AWS Copilot.
📝 Read the full article on AWS Community.
Bedrock JCVD 🕺🥋 on LangChain templates
The Bedrock JCVD 🕺🥋 template is now officially part of LangChain!
Bringing 🤗 Text Embeddings Inference to Amazon SageMaker
Just opened a PR (huggingface/text-embeddings-inference#103) to add support for SageMaker-compatible images. Similar to huggingface/text-generation-inference#147, only for HF TEI.
Chatting with Support - Cost Optimization with AWS 💰
New video on cost optimization with Jonas Ferreira. The first one of the series in PT-PT for the AWS Iberia YouTube channel.
A Tour of GenAI 🚀 - There and Back Again
My take on the GenAI narrative. No hype, no hubris, no hogwash.
📢 UPDATE: Now available at critical-ai.dev/GenAI!
Time in Machine Learning Engineering ⏳
This article started out as a joke and didn’t wander very far in state space. It is a witty and not-so-rigorous attempt to demonstrate the importance of time in ML projects that will annoy most mathematicians and alienate some physicists. There’s some truth in it… it’s just really hard to find. Enjoy! 😛
📝 Read the full article on Medium
HuggingFace 🤗 on Trainium
A (not so deep) exploration of 🤗 Transformers training on AWS Trainium.
📢 UPDATE: 🤗 on Trainium is now part of the AWS Iberia AI/ML workshops
QHack Recap - PennyLane, Amazon Braket and Beyond 🚀
Now that QHack 2021 is officially over, it’s time for a short recap…
📝 Read the full article on Medium
Defect Detection with Amazon Lookout for Vision 🏭
In this article, we give an introduction to AWS for Industrial focusing on Amazon Lookout for Vision, a service that treats defect detection problems as simple binary (image) classification tasks.
📝 Read the full article on Medium
WBME Workshop - Machine Learning for Medicine and Healthcare 👨⚕️
An overview of ML highlighting some of its applications to the health sector - from the rise of expert systems in the 80s to the diagnosis, prognosis and treatment of SARS‑CoV‑2. In this workshop, we’ll explore how AI is shaping the present and how it may one day decide our future.
📝 Full content available on GitHub
For more information about this event, visit 12th WBME - Workshop on Biomedical Engineering