June 2024 Summaries

DataStax Enterprise (DSE) 6.9 is set to release soon, offering an upgrade path with vector database capabilities for generative AI use cases. The addition of vector search in DSE 6.9 is powered by the JVector search engine and is 10x faster than traditional Lucene-based search. This new feature allows developers to integrate powerful generative AI capabilities into their workloads running on DSE. Additionally, DSE 6.9 adds Java 11 support, improvements in Storage-Attached Indexes (SAI), and cloud-native operations and observability with Mission Control. The text also provides a step-by-step guide to create a classic talk-to-your-docs Q&A chatbot using DSE 6.9's vector search feature.

DataStax has introduced a visual framework called Langflow, which simplifies building generative AI applications by providing an easy-to-use drag-and-drop interface. Developers can use Langflow to experiment, design, and test RAG (retrieve, answer, generate) and GenAI apps without needing to install open-source Langflow on their machines. The cloud-hosted platform integrates with top GenAI tools such as OpenAI, Hugging Face, MongoDB, Pinecone, and more. It offers a secure environment, integrated Astra DB access, flexibility in choosing models and databases, fast iteration and control, and prebuilt components and projects for powerful RAG and agent data flows. Langflow is free to use and aims to make it easier for developers of all levels to explore the realm of generative AI applications.

This tutorial demonstrates how to add a related posts feature to an Astro-powered blog using DataStax Astra DB and OpenAI vector embeddings. The process involves creating vector embeddings for blog post content, storing them in Astra DB, and performing similarity searches to find the most relevant posts. By implementing this feature, users can explore more content on a website, increasing engagement and time spent on the site.

David Gilardi, a tech industry veteran with experience in various roles such as systems integration, database administration, consulting, defense, and product management, has recently returned to Developer Relations at DataStax. He is passionate about leveraging generative AI capabilities to build innovative applications that were previously unimaginable. Gilardi enjoys helping others learn and believes that explaining complex concepts simply is crucial for understanding them well. As a developer relations specialist, he looks forward to witnessing the impact of GenAI on elevating humanity and is excited to be part of this journey with fellow developers, engineers, and scientists.

Tejas Kumar has recently joined DataStax as a developer relations engineer after running a successful developer relations consultancy. He aims to help DataStax pivot to being the de-facto leader among developers for AI use cases by creating a world-class developer experience and developer tooling through design engineering, research, support, and product iteration. Tejas is currently working on research and support in the field of generative AI, including exploring problems with GenAI today and finding meaningful solutions to them. He invites others to join him at DataStax, as they are currently hiring for some roles.

Cohere has released a dataset containing all of Wikipedia chunked and embedded to vectors using their multilingual-v3 model. This makes creating a semantic, vector-based index of Wikipedia practical for an individual for the first time. The JVector library now supports indexing larger-than-memory datasets by performing construction-related searches with compressed vectors. By using Locally-Adaptive Quantization (LVQ) compression, it improves on previous methods and allows for faster searches while maintaining accuracy. This has enabled the indexing of all of English Wikipedia on a laptop, which was previously not practical.

Phil Nash, a developer relations engineer at DataStax, has joined the team to help developers build with generative AI and Astra DB. He will create demos, write blog posts, make videos, and speak at meetups and conferences. With a background in both front-end and back-end development, Phil is excited about the potential of generative AI technology and its applications. His experience in developer relations stems from his passion for community learning and sharing knowledge. He encourages developers to share their experiences with building generative AI projects and looks forward to engaging with the community through various platforms.