Eric Hartford

Seeking to start orchestrating Ray jobs with Apache Airflow? This integration tutorial demonstrates using the Ray provider package to orchestrate a simple Ray job with Airflow in an existing Ray cluster. If you're looking for more complex implementation examples of the Ray provider package, Astronomer Docs is the place to find additional Ray on Anyscale reference architectures. https://bit.ly/4dtCxzV

21

You can now use Amazon Bedrock knowledge bases to create conversations and query your data in Redshift, SageMaker Lakehouse, and S3 using natural language. Congrats to the team! Try it out at: https://lnkd.in/gkvJ_mC3 #ArtificialIntelligence #DataEngineering #DataScience #MachineLearning #AmazonBedrock #TechInnovation

42

> "Note that different people tend to be drawn to different ends of these trade-offs. For example, TPMs typically are drawn to the “control” side and prototyping engineers are typically drawn to the “autonomy” end. This means that people will have their ego attached to one end of the trade-off, making the debate — especially if it frames the question as a binary and not a trade-off — somewhat emotionally charged." Leading a team can be especially tricky when team members hold strong, opposing viewpoints. The key, at least in my opinion, lies in prioritising a collaborative approach that emphasizes small, iterative steps, regular evaluation, and a shared goal of creating value for users/customers, not winning internal debates.

4

I did a quick test of the new function calling in #ollama using llama3.1 8B model. The good news is that the API works! The bad news is that llama3.1 does a poor job at formatting function args according to my tool spec. A comparison w/ gpt-35-turbo: https://lnkd.in/g_R3ExQn Anyone had success with local SLMs and function calling?

17

Anyone trusting an off-the-shelf LLM to diagnose disease is asking for trouble. I *do* think that it would be possible to create an application that employs more targeted use of AI to help with the diagnosis process. In general I find that I get much better results from asking an AI to help me follow a process and think through a problem than I do if I just ask it for answers. It’s possible to do that in something like ChatGPT, but that requires a lot of prompting knowledge. Using an application that can combine and coordinate a set of prompts and work through a directed process enables people without the prompting experience to get the benefits from an AI that they wouldn’t otherwise.

2

1 Comment

We’ve recently introduced the Anyscale Unified Log Viewer, which simplifies and streamlines the debugging and optimization of distributed Ray applications! Key features include: • Structured logging with actor, instance, and request attributes for effective searching across the cluster • UI and log persistence • Comprehensive search and filtering capabilities • Scalable to 100s of GB of logs and thousands of nodes Check out the video: https://lnkd.in/gwr5hsTf  🛠️ To get started, log in to Anyscale, run your Ray application, and navigate to the new log viewing section in your dashboard. Start debugging and optimizing with ease! 🌟 Read more in our announcement: https://lnkd.in/gpbEvr2h

32

🛠️ RAG On-Prem. Built on Kubernetes, fine-tuned open source models, and battle-tested on 2B+ tokens. 🧿 GroundX has made waves with clients like Air France and Dartmouth, and so far, we’ve processed over 2 billion tokens of data! And now, with Enterprise Grade RAG On Prem— it's designed from the ground up for secure, closed environments. Our API's offer the same high-performance RAG (Retrieval-Augmented Generation) capabilities but fully deployable behind your firewall. We built this for organizations where security isn’t optional but essential—think finance, healthcare, and defense. Are you exploring AI solutions for secure environments? Let’s talk about how GroundX On Prem can meet the most demanding requirements. Learn More: https://buff.ly/2DiomCf #EnterpriseAI #RAG #kubernetes #onprem

5

Using generative AI, NVIDIA operations built an AI Planner agent, developed on NVIDIA Inference Microservices (NIM). The agent leverages LLM, NeMo Retriever and CuOpt NIM to reduce re-planning time from hours to just seconds. https://nvda.ws/4bIfS2T

2

neptune.ai's integration with PyTorch Lightning makes it super easy to track and compare your experiments on Lightning AI. Try out the integration with zero setup: https://lnkd.in/gdf6wwuv

40

"A new abstraction for developers." Temporal Technologies offers an open-source platform for durable execution, simplifying the development of reliable, fault-tolerant applications by abstracting the complexities of scalable distributed systems. Learn more: https://temporal.io #OpenSource #DurableExecution #SoTSpotlights

14

Your code is important, today AI can generate many generic components of code yet each application will have certain intrinsic elements that needs to be protected. How to secure your code when there are multiple parties involved? Introducing Castler Code, a product we recently developed that solves this problem by building code Escrows. Whether you are a big tech company outsourcing development or a freelance developer with multiple clients, you get to define the terms and conditions that work for you, keep your code in an Escrow, make sure it's running without actually sharing the code, define security layers and release it only when the terms are met. Like, follow our new page for more! Website: https://code.castler.com/

38

My refactorings went so smooth with TDD that I decided to try to change my naive binary encoder that produced lists of bytes into producing efficient bytestrings. I feared I was falling prey to premature optimization. But it took me a few minutes and now my tests execute literally ten times faster (my whole test suite went from a sluggish 8s to a blazing 800ms). Definitely worth it. It's incredible how easy some things become when you have a robust test suite (meaning that it checks behavior and lets you swap the implementation).

9

1 Comment

I started writing regularly about AI. If you're an innovators or product developer eager to apply the latest in AI, whether you're in a startup or a big company, consider checking https://lnkd.in/gGdW8PYe I won't teach you ML, but I share real-world insights from launching - and sometimes failing at - numerous ML features on a large scale.

54

2 Comments

when using structured outputs with llms, mirascope makes it easy to retry on validation error and insert the error into the subsequent call this feature ensures end users maintain full control over the retry logic while keeping it simple ti implement docs: https://lnkd.in/gUFY2x-P

4

Learn why the NVIDIA Jetson AGX Orin is the leading platform for running transformer models like GPT-J, vision transformers, and stable diffusion at the edge.

1

Clarifying how data privacy is important in the context for RAG application and the control Elastic is giving you down to the lowest data level: in Jeff Vestal's new blog post https://lnkd.in/gSAZwWJY

76

🚀 Elevate Your AI Projects with Redis Solution! 🚀 Unlock the power of application architecture and TypeScript with Redis Solution. Dive into the complete AI model life-cycle: 1️⃣ **Data Preparation**: Data cleaning, feature engineering, transformations, and splitting. 2️⃣ **Model Building**: Build models using the appropriate frameworks. 3️⃣ **Model Training & Tuning**: Optimize hyperparameters and calibrate your models. 4️⃣ **Model Deployment**: Deploy models in a production environment. 5️⃣ **Model Management**: Detect and address problems with model performance. Visit us at [Redissolution.com](http://Redissolution.com) for expert solutions and insights. 📧 Have questions? Contact us at [email protected]. We're here to assist you! #RedisSolution #ApplicationArchitecture #TypeScript #DataPreparation #ModelBuilding #AI #MachineLearning #ModelDeployment #ModelManagement #RedisSaysYes #DmForAnyQuery