ZenML Blog

The latest news, opinions and technical guides from ZenML.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
12 mins

The Ultimate Guide to LLM Batch Inference with OpenAI and ZenML

OpenAI's Batch API allows you to submit queries for 50% of what you'd normally pay. Not all their models work with the service, but in many use cases this will save you lots of money on your LLM inference, just so long as you're not building a chatbot!
Read post
5 mins

The struggles of defining a Machine Learning Pipeline

On the difficulties in precisely defining a machine learning pipeline, exploring how code changes, versioning, and naming conventions complicate the concept in MLOps frameworks like ZenML.
Read post
4 mins

Reflections on working with 100s of ML Platform teams

Exploring the evolution of MLOps practices in organizations, from manual processes to automated systems, covering aspects like data science workflows, experiment tracking, code management, and model monitoring.
Read post
1 min

How to use ZenML and DBT together

How to use ZenML and dbt together, all powered by ZenML's built-in success hooks that run whenever your pipeline successfully completes.
Read post
2 mins

Building and Optimizing RAG Pipelines: Data Preprocessing, Embeddings, and Evaluation with ZenML

We dive deep into the world of Retrieval-Augmented Generation (RAG) pipelines and how ZenML can streamline your RAG workflows.
Read post

Newsletter Edition #4 - Learnings from Building with LLMs

Today, we're back to LLM land (Not too far from Lalaland). Not only do we have a new LoRA + Accelerate-powered finetuning pipeline for you, we're also hosting a RAG themed webinar.
Read post
4 mins

Bigger Isn't Always Better: The Case for RAG in the Age of Infinite Context

Context windows in large language models are getting super big, which makes you wonder if Retrieval-Augmented Generation (RAG) systems will still be useful. But even with unlimited context windows, RAG systems are likely here to stay because they're simple, efficient, flexible, and easy to understand.
Read post
Oops, there are no matching results for your search.

Start your new ML Project today with ZenML Pro

Join 1,000s of members already deploying models with ZenML.