Upskill your Team on Generative AI. Start here >

The Future of Search Dynamics: A Deep Dive into Large Language Models and Vector Databases with Suvrat Bharadwaj and Chinmaya Kumar Jena

Exploring the transformative potential of Large Language Models and Vector Databases in redefining search dynamics, as elucidated by Suvrat Bharadwaj and Chinmaya Kumar Jena at Cypher 2023.

In a captivating presentation at Cypher 2023, Suvrat Bharadwaj and Chinmaya Kumar Jena, both Directors at Tredence, took the audience on a journey through the transformative landscape of Large Language Models (LLMs) and Vector Databases. The session was a comprehensive look at how these technologies are redefining the way we interact with databases, search engines, and even the broader digital world.

The Rise of Large Language Models

Suvrat Bharadwaj began by discussing the emergence of LLMs like GPT-3, which have become increasingly adept at understanding and generating human-like text. These models have opened up new avenues for natural language processing, enabling more intuitive and context-aware search functionalities. Bharadwaj emphasized that LLMs are not just about generating text; they are about understanding the context and semantics behind the words, thereby making them invaluable in search applications.

The Role of Vector Databases

Chinmaya Kumar Jena took over to explain the concept of Vector Databases, which are specifically designed to store and query vector embeddings generated by machine learning models. He pointed out that traditional databases are ill-equipped to handle the complexities of modern data, particularly when it comes to unstructured data like text, images, and audio. Vector databases fill this gap by allowing for efficient storage and retrieval of complex data types.

Real-world Applications

The speakers then shifted focus to the practical applications of these technologies. They discussed how businesses are using LLMs and Vector Databases in semantic search, recommendation systems, fraud detection, and even autonomous vehicles. They showcased Tredence’s enterprise-ready architecture, which incorporates various open-source models and technologies to handle large volumes of unstructured data, convert it into vector embeddings, and store it in a vector database for efficient retrieval.

Q&A and Conclusion

The presentation concluded with a Q&A session, where the speakers addressed various questions from the audience. Topics ranged from the optimal size of vector embeddings to the need for domain-specific training for LLMs. Both speakers agreed that while the technology is promising, there is still much work to be done in terms of scalability and efficiency.

Picture of Association of Data Scientists

Association of Data Scientists

The Chartered Data Scientist Designation

Achieve the highest distinction in the data science profession.

Elevate Your Team's AI Skills with our Proven Training Programs

Strengthen Critical AI Skills with Trusted Generative AI Training by Association of Data Scientists.

Our Accreditations

Get global recognition for AI skills

Chartered Data Scientist (CDS™)

The highest distinction in the data science profession. Not just earn a charter, but use it as a designation.

Certified Data Scientist - Associate Level

Global recognition of data science skills at the beginner level.

Certified Generative AI Engineer

An upskilling-linked certification initiative designed to recognize talent in generative AI and large language models

Join thousands of members and receive all benefits.

Become Our Member

We offer both Individual & Institutional Membership.