Apoorva Joshi

Featured in: Favicon

mdpi.com

acs.org

theepochtimes.com Favicon

mongabay.com Favicon

alternet.org Favicon

thenewstack.io Favicon

veterinaria.org Favicon

pubs.acs.org

Articles

Apoorva Joshi on LLM Application Evaluation and Performance Improvements

Feb 3, 2025 | infoq.com | Apoorva Joshi |Srini Penchikala

In this podcast, Apoorva Joshi, Senior AI Developer Advocate at MongoDB, discusses how to evaluate software applications that use the Large Language Models or LLMs and how to improve the performance of LLM based applications.
SUSE Says Rancher Observability Is Better Than Pure Plays

Nov 18, 2024 | lxer.com | Bruce Gain |BC Gain |Apoorva Joshi |Emilio Salvador

SALT LAKE CITY — SUSE now offers what it describes as a comprehensive observability platform, designed to cover all environments — whether on AWS, Azure, Google Cloud, on premises or in other environments — that run on Rancher for Kubernetes. With SUSE Cloud Observability, the company seeks to provide observability functionality comparable to that of industry heavyweights, including Datadog, Grafana and Honeycomb.
Fedora 41 Offers Zippy Performance

Nov 17, 2024 | lxer.com | Jack Wallen |Loraine Lawson |David Eastman |Apoorva Joshi

Not even five years ago, if someone said to me that Fedora was a Linux distribution that anyone could use, I would have smirked and pointed them toward Ubuntu, elementary OS, Zorin OS, or Linux Mint. It has long been known as an early test run for Red Hat to test its next version of Red Hat Enterprise Linux. The distro was chock full of great features but still pretty buggy for everyday use.
Optimizing for Relevance Using MongoDB Atlas and LlamaIndex

Oct 2, 2024 | mongodb.social | Apoorva Joshi

In the past year or so, there has been an uptick in natural language experiences in user-facing applications, ranging from RAG (Retrieval Augmented Generation (RAG) chatbots and agents to natural language search. With natural language becoming the new query language, keyword-based full-text search might not always retrieve the best results due to the length, paraphrasing, ambiguity, and vagueness of natural language queries.
How to Evaluate Your LLM Application

Jun 24, 2024 | mongodb.social | Apoorva Joshi

If you have ever deployed machine learning models in production, you know that evaluation is an important part of the process. Evaluation is how you pick the right model for your use case, ensure that your model’s performance translates from prototype to production, and catch performance regressions. While evaluating Generative AI applications (also referred to as LLM applications) might look a little different, the same tenets for why we should evaluate these models apply.
How to Choose the Right Chunking Strategy for Your RAG Application

Jun 4, 2024 | mongodb.com | Apoorva Joshi

In Part 1 of this series on Retrieval Augmented Generation (RAG), we looked into choosing the right embedding model for your RAG application. While the choice of embedding model is an important consideration to ensure good quality retrieval for RAG, there is one key decision to be made before the embedding stage that can have a significant downstream impact — choosing the right chunking strategy for your data.
AI on offense: Can ChatGPT be used for cyberattacks?

May 24, 2023 | elastic.co | Apoorva Joshi

Generating a phishing email is not the same thing as sending a phishing lure. While these models can assist in carrying out sophisticated cyberattacks by providing inputs to those human capabilities, they cannot execute these attacks independently. At least not yet. To prove it out, we experimented with how far we could get using a generative model such as ChatGPT to help us execute a relatively involved attack, such as a Golden Ticket Attack.