RAG Pipeline Evaluation, Integrating Data Science and MLOps, Boosting Gen AI with Data Engineering, and the Free ODSC East Open Pass

ODSC - Open Data Science
ODSCJournal
Published in
Sent as a

Newsletter

5 min readApr 11, 2024

A Practical Guide to RAG Pipeline Evaluation (Part 1: Retrieval)

Retrieval is a critical and complex subsystem of the RAG pipelines. After all, the LLM output is only as good as the information you provide it, unless your app relies solely on the training data of the LLM.

Podcast: Open Table Formats Reshaping the Data Industry — A Deep Dive with Ryan Blue

Check out this podcast with Ryan Blue of Apache Iceberg to learn more about data engineering, open table formats, and data warehouses.

A Tale of Two Cultures: Integrating Data Science and MLOps to Build Successful ML Products

To leverage the full potential of ML, we need to solve the challenge of integrating the opposing cultures of data science and MLOps into a cohesive team.

Unlocking the Power of Gen AI with Data Engineering

Data engineering stands at the nexus of this symbiotic relationship between data and AI, playing a pivotal role in unlocking the full potential of Gen AI applications.

Reliable Data Orchestration for AI Applications

In this blog post, we discuss how Dosu — an exciting new company in the AI space — uses Astronomer to manage its data pipelines, and how Dosu supports the Astronomer team in helping maintain Cosmos, which simplifies how data engineers integrate dbt with Airflow.

Accelerating ML Application Development: Production-Ready Airflow Integrations with Critical AI Tools

Apache Airflow is at the core of many teams’ ML operations, and with new integrations for LLMs, Airflow enables these teams to build production-quality applications with the latest advances in ML and AI.

How to Accelerate AI with Apache Airflow

Apache Airflow is playing a key role in the AI/ML initiatives of modern enterprises. Find out how to start delivering production-ready AI with Airflow in this free ebook by Astronomer.

At the AI Solution Showcase Expo Hall, you’ll have the opportunity to explore cutting-edge AI solutions from industry leaders. From MLOps to machine learning to data analytics, you’ll see firsthand how AI can improve your business outcomes. Register for free here!

Industry, Opinion, Career Advice

How To Unlock Trust and Success Before You Start an AI Project

One way organizations have found success in building trust and achieving higher rates of project success for companies is by starting every AI project with a discovery and design process.

12 Out-of-the-Box AI Solutions to Transform Your Company

Looking to implement AI in your organization? Look no further! These AI solutions will be game-changers for you and in no time at all.

Dagster+ Launch

April 12th, NYC and San Francisco

Join us for the unveiling of Dagster+, the next generation of Dagster Cloud. Find out how to weave data reliability and quality checks into the execution of your data pipelines and more.

Data Science & AI News

ODSC’s AI Weekly Recap: Week of April 5th

This week’s AI Weekly Recap is all about CodeLlama-34 B, the US/UK’s new AI partnership, and Google’s latest AI move. Sign up here to get this as a newsletter every Friday morning.

US & UK Announce New AI Safety/Testing Partnership

Last week, leaders of the G7, the United States, and Britain solidified their commitment to the future of artificial intelligence safety.

Lipscomb University Introduces Master of Science in Applied AI

Lipscomb University has unveiled its latest graduate program offering: Master of Science in Applied Artificial Intelligence.

CodeLlama-34B Released by IBM

IBM watsonx has officially announced the release of CodeLlama-34B in a bid to help developers improve productivity.

White House Pushes Fed Agencies to Hire AI Chiefs

The White House Office of Management and Budget has introduced guidelines mandating agencies to appoint AI Chiefs.

Report: Google May Move AI Features to Paid Plan

According to a new report, Google is looking to overhaul its business model and put some AI features behind a paywall.

ODSC Highlights

Learn 9 Ways to Implement Responsible AI at ODSC East 2024

At ODSC East, we’ll learn about the ways that responsible AI can help minimize harm and maximize the benefits of data science and AI applications.

9 Sessions to Get Started with AI at ODSC East 2024

Here are nine different sessions coming to ODSC East this April 23–25 that will help you get started with a career in AI.

New Podcast Episode: Deep Learning for Financial Trading with Sofien Kaabar

In this episode, Sofien Kaabar will discuss the role of deep learning and machine learning for finance, through the lens of his recent book Deep Learning for Finance. You’ll explore a whole range of topics including machine learning for finance, featuring engineering, time series prediction strategies, challenges such as backtesting, overfitting, and non-stationary data, and much more! Spotify | SoundCloud | Apple

Video of the Week: Continual Learning of Natural Language Processing Tasks

Delve into the advanced machine learning paradigm of continual learning. This approach, akin to human intelligence, enables machines to learn continuously, and retain and apply knowledge to new challenges, revolutionizing traditional, isolated learning methods. Discover how continual learning is set to redefine our understanding and capabilities in language processing, making it a must-watch for anyone interested in AI, deep learning, data science, and technological innovation.

Upcoming Webinars and Meetups:

Enhancing Security Report Generation with RAG and Fine-Tuned Language Models: Integrating Account Telemetry and OCI Cloud Guard

Tue, May 7, 2024 12:00 PM — 1:00 PM EDT

In the rapidly evolving landscape of cyber security, the ability to swiftly generate comprehensive and accurate security reports is paramount. This session showcases an advanced approach that leverages RAG and fine-tuned LLMs, such as Cohere and Llama2, to automate the creation of detailed security reports. By incorporating account telemetry and network traffic logs as RAG, this method enhances the report’s contextuality and relevance, ensuring precise and insightful incident narratives and breach analyses.

--

--

ODSC - Open Data Science
ODSCJournal

Our passion is bringing thousands of the best and brightest data scientists together under one roof for an incredible learning and networking experience.