Homepage
Open in app
Sign in
Get started
data from the trenches
the nitty gritty of data science by the experts @ dataiku
Machine Learning
Engineering
Product
Dataiku
Follow
Latest
Automating Document Processing With AI
Automating Document Processing With AI
An Overview of Some Modern Approaches
Guillaume Cazottes
Nov 14
Taming LLM Outputs
Taming LLM Outputs
Your Guide to Structured Text Generation
Vivien Tran Thien
Oct 31
A Tour of Popular Open Source Frameworks for LLM-Powered Agents
A Tour of Popular Open Source Frameworks for LLM-Powered Agents
One of the most interesting Generative AI trends is the development of agents powered by large language models (LLMs). The word “agent”…
Loic Vanel Tabueu Tagne
Sep 26
Retrieval Augmented ML: How Can You Best Leverage a Data Lake?
Retrieval Augmented ML: How Can You Best Leverage a Data Lake?
An Open Source Pipeline for Benchmarking the Join Suggestion for ML
Riccardo Cappuzzo
Sep 5
Beyond Text: Taking Advantage of Rich Information Sources With Multimodal RAG
Beyond Text: Taking Advantage of Rich Information Sources With Multimodal RAG
Retrieval augmented generation (RAG) has become a very popular approach for creating question-answering systems based on specific document…
Vivien Tran Thien
Jun 6
From Sketch to Success: Strategies for Building and Evaluating an Advanced RAG System
From Sketch to Success: Strategies for Building and Evaluating an Advanced RAG System
By integrating domain-specific knowledge into a Large Language Model (LLM), Retrieval Augmented Generation (RAG) enables the generation of…
Caroline Boudier
Mar 28
Demystifying Multimodal LLM
Demystifying Multimodal LLM
Unlocking the Power of Fusion in Language and Vision
François Phe
Mar 21
Standing on the shoulders of a giant
Standing on the shoulders of a giant
Leveraging the web to answer open-ended questions
Vivien Tran Thien
Feb 5
Quantum Leap: Beyond the Limits of Machine Learning
Quantum Leap: Beyond the Limits of Machine Learning
Quantum Computers as AI Accelerators
Simona Maggio
Feb 1
Quantization in LLMs: Why Does It Matter?
Quantization in LLMs: Why Does It Matter?
As more open source models are released and begin to rival the quality of proprietary models like ChatGPT, many practitioners want to test…
Aimee Coelho
Jan 11
Parameter Efficient LLM Fine-Tuning
Parameter Efficient LLM Fine-Tuning
In this three-part series, we’ll unpack several technical topics that have made their way into the spotlight as a result of the increased…
Louis Fouquet
Dec 21, 2023
From Chatbots to Agents: Augmenting LLMs With Tools
From Chatbots to Agents: Augmenting LLMs With Tools
Large language models (LLMs) excel at generating coherent and credible continuations of input texts and this ability can be used to…
Timothee Weis
Oct 5, 2023
Tackling Imbalanced Learning With Generative Synthesizers
Tackling Imbalanced Learning With Generative Synthesizers
In the landscape of imbalanced classification, the limitations of traditional oversampling approaches have become increasingly evident. In…
Ines Ibnukhsein
Sep 28, 2023
About data from the trenches
Latest Stories
Archive
About Medium
Terms
Privacy
Teams
