blog
- agentic-ai
- ir
- llm
- math
- nlg-basics
- software
- visualization
•
•
•
•
•
•
-
[Under construction] Evaluating an Agentic AI Application 2/2: Summarizing my Experience Evaluating Conversations at Codify
How can you make sure that your AI agents' output is truthful and faithful to your query and continues to be so throughout the conversation? Here I summarize my experience evaluating conversations from an agentic AI application using DeepEval, Arize Phoenix, and Google Cloud.
-
[Under construction] A Comprehensive Introduction to Information Retrieval
In today's AI-permeated climate, information retrieval is a crucial component of many applications. But which retrieval models perform well? What affects performance? What is the performance-runtime trade-off? What do different types of retrievers struggle with?
-
[Under construction] My Experience with Publishing an R Package on CRAN
How to create an R package? How to publish the R package on The Comprehensive R Archive Network (CRAN)? How to avoid Hadley Wickham as a reviewer? Well, I actually cannot help with the latter, but I can give some insights for the first two questions.
-
Evaluating an Agentic AI Application 1/2: Summarizing my Experience Integrating DeepEval with Arize Phoenix at Codify
How can you make sure that your AI agents' output is truthful and faithful to your query? This is what inspired our journey integrating the evaluation platform DeepEval with the LLM trace platform Arize Phoenix. In this blog post, I will present the challenges I faced in this journey and how I solved them.
-
A Brief Introduction to (some of) the Math Behind the Transformer
The Transformer architecture, introduced in 2017 by Google, is the basis for every state-of-the-art generative AI model today. Understanding (some of) the math behind it is essential for understanding the Transformer itself and today's generative AI models.