Aparna Dhinakaran

The tradeoffs between building bespoke code-based agents and the major agent frameworks. Aparna Dhinakaran · Follow Published in Towards Data Science · 12 min read · Just now — Image by author Thanks to John Gilhuly for his contributions to this piece. Agents are having a moment. With multiple new frameworks and fresh investment in the space, modern AI agents are overcoming shaky origins to rapidly supplant RAG as an implementation priority. So will 2024

Image created by author using Dall-E Results point to a promising approach Aparna Dhinakaran · Follow Published in Towards Data Science · 4 min read · 10 hours ago — A special shoutout to Manas Singh and Evan Jolley for collaborating with us on this research! A potential application of LLMs that has attracted attention and investment is around their ability to generate SQL queries. Querying large databases with natural language unlocks several compelling use

Image created by author using Dall-E 3 Results from experiments to evaluate and compare GPT-4, Claude 2.1, and Claude 3.0 Opus Aparna Dhinakaran · Follow Published in Towards Data Science · 6 min read · 22 hours ago — My thanks to Evan Jolley for his contributions to this piece New evaluations of RAG systems are published seemingly every day, and many of them focus on the retrieval stage of the framework. However, the generation

Image created by author using Dall-E 3 Understanding the difference for LLM applications Aparna Dhinakaran · Follow Published in Towards Data Science · 9 min read · 8 hours ago — For a moment, imagine an airplane. What springs to mind? Now imagine a Boeing 737 and a V-22 Osprey. Both are aircraft designed to move cargo and people, yet they serve different purposes — one more general (commercial flights and freight), the other very