speaker detail

Siddhant Agarwal

Developer Relations Lead - APAC

company logo

Siddhant Agarwal is a community builder with a decade-long career in India, where he has built communities, facilitated innovation, and scaled ecosystems. Currently, he leads Developer Communities across APAC at Neo4j and is a leader in the Graph Database and Analytics Industry.

Sid previously empowered professional and student developers and led Google's Developer Relations initiatives in India, including Google Developer Experts, Developer Student Clubs, and TensorFlow User Groups. In 2019, he collaborated with the Indian government to launch the "Build for Digital India" program, mobilizing over 7,000 students to tackle national challenges with code. Sid is a design-thinking expert who mentors startups in UX and AI. He has been recognized as one of ACM's Distinguished Speakers and was a finalist for the CMX Community Industry Awards.

In the era of big data, large language models (LLMs) are becoming increasingly important for tasks like question answering, document analysis, and chatbot development. However, traditional LLMs often need help with factual accuracy, reasoning, and complex information handling.

This talk introduces GraphRAG, a novel technique that leverages the power of knowledge graphs to empower LLMs. We’ll delve into the limitations of traditional LLMs and vector-only approaches of RAG and explore how GraphRAG bridges the gap. GraphRAG equips LLMs with a deeper understanding of the world by utilizing enterprise data, boosting their accuracy and reasoning abilities, and handling complex information.

This talk will explore the exciting world of GraphRAG and showcase its potential to revolutionize various fields. We will also discuss real-world applications and case studies to illustrate the benefits of GraphRAG for practitioners compared to a vector-only approach.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More
Book tickets View all speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details