Community builder · FunctionalTV
Centered on this profile · drag to explore
Showing 1 of 1
A database system that can synchronize all or a part of its contents over a limited bandwidth link is described. The lowest layer of the system, the bedrock layer, implements a transactional block store. On top of this is a B+-tree that can efficiently compute a digest (hash) of the records within any range of key values in O(log n) time. The top level is a communication protocol that directs the synchronization process such that minimization of bits communicated, rounds of communication, and local computation are simultaneously addressed.
Showing 12 of 12
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful representations learned from datasets to speed up the formulation of novel hypotheses with the potential to impact material discovery broadly. We present the Generative Toolkit for Scientific Discovery (GT4SD). This extensible open-source library enables scientists, developers, and researchers to train and use state-of-the-art generative models to accelerate scientific discovery focused on organic material design.
Showing 24 of 518
Alexy Khrabrov talks with Romain Priour of LangChain’s AI infrastructure team about deploying LangSmith for enterprise customers. They discuss Kubernetes, a hybrid SaaS and self-hosted model on AWS, customer-facing infrastructure, and expanding the platform across clouds.
Alexy Khrabrov talks with Hotdata co-founder and principal engineer Zac Farrell about building cloud databases for AI agents. They discuss Hotdata’s Rust and Apache DataFusion foundation, isolated database workspaces, SQL, performance engineering, and choosing Rust-native infrastructure over legacy stacks.
Alexy Khrabrov walks through the new LangChain office before the San Francisco Apache DataFusion Meetup and checks in with organizers and speakers. Divya Ranganathan, Emil Sadek, Shehab Amin, and Alexander Bianchi preview talks spanning ADBC, LakeSail, distributed query execution, and the growing DataFusion community.
Alexy Khrabrov talks with LangChain co-founder and CTO Ankush Gola about SmithDB, the Rust and Apache DataFusion-powered data layer behind LangSmith. They discuss agent-observability workloads, database extensibility, production performance, and where Rust fits into modern AI infrastructure.
Join us for the inaugural Rust + AI meetup in San Francisco. What to expect: The night will introduce you to peers from the SF Bay Area who are working on, or interested in leveraging Rust in novel new ways. * You'll hear from leading Rust AI companies in the Bay Area and beyond through a series of lighting talks. * We'll finish up the evening with networking opportunities, and feedback for where to take this new community. We'll have talks by: LakeSail: Shehab Amin, rebuilding the Spark Lakehouse ecosystem in Rust LaserData: Kranti Parisa, building a fast streaming service in Rust with Apache Iggy CocoIndex: Linghua Jin, streaming context change Valkey: Manvika Tuteja, Valkey GLIDE, Community, Overview Databricks: Nick Lanham, Why we built delta-kernel-rs. Temporal: Melanie Warrick & Melissa Herrera, What an Agent Is Made Of: Managing the Agentic Loop in Rust pgGraph: Native Graph Performance inside Postgres, Dale Prescott Ng, Evokoa Columnar: Emil Sadek, Universal Data
Join us for the inaugural Rust + AI meetup in San Francisco. What to expect: The night will introduce you to peers from the SF Bay Area who are working on, or interested in leveraging Rust in novel new ways. * You'll hear from leading Rust AI companies in the Bay Area and beyond through a series of lighting talks. * We'll finish up the evening with networking opportunities, and feedback for where to take this new community. We'll have talks by: LakeSail: Shehab Amin, rebuilding the Spark Lakehouse ecosystem in Rust LaserData: Kranti Parisa, building a fast streaming service in Rust with Apache Iggy CocoIndex: Linghua Jin, streaming context change Valkey: Manvika Tuteja, Valkey GLIDE, Community, Overview Databricks: Nick Lanham, Why we built delta-kernel-rs. Temporal: Melanie Warrick & Melissa Herrera, What an Agent Is Made Of: Managing the Agentic Loop in Rust pgGraph: Native Graph Performance inside Postgres, Dale Prescott Ng, Evokoa Columnar: Emil Sadek, Universal Data
Join us for the inaugural Rust + AI meetup in San Francisco. What to expect: The night will introduce you to peers from the SF Bay Area who are working on, or interested in leveraging Rust in novel new ways. * You'll hear from leading Rust AI companies in the Bay Area and beyond through a series of lighting talks. * We'll finish up the evening with networking opportunities, and feedback for where to take this new community. We'll have talks by: LakeSail: Shehab Amin, rebuilding the Spark Lakehouse ecosystem in Rust LaserData: Kranti Parisa, building a fast streaming service in Rust with Apache Iggy CocoIndex: Linghua Jin, streaming context change Valkey: Manvika Tuteja, Valkey GLIDE, Community, Overview Databricks: Nick Lanham, Why we built delta-kernel-rs. Temporal: Melanie Warrick & Melissa Herrera, What an Agent Is Made Of: Managing the Agentic Loop in Rust pgGraph: Native Graph Performance inside Postgres, Dale Prescott Ng, Evokoa Columnar: Emil Sadek, Universal Data
Pale Fire combines the use of Large Language Models and Knowledge Graphs (semantic artifacts) to support navigation through collections. Situated in the research area of Retrieval Augmented Generation, this specific workflow represents the creation of local and adaptable chatbots. Based on the tool-suite EverythingData at the backend, GhostWriter provides an interface that enables querying and “chatting” with a collection. Applied iteratively, the workflow supports the information needs of researchers when interacting with a collection of papers, whether it be to gain an overview, to learn more about a specific concept and its context, and helps the researcher ultimately to refine their research question in a controlled way. Pale Fire is developed by Slava Tykhonov, Head of AI and Interoperability at CODATA, the European open data consortium. Codata collaborates with the Community Research Center for Reliable AI at Northeastern Oakland, lead by Alexy Khrabrov, who is presenting th
Alexy Khrabrov, the AI Community Architect at Neo4j, presented OAKS ASKG — the Agent-Server Knowledge Graph from the OAKS project, aiming to catalog all the MCP servers for agents workflows. ASKG vibecoded repository: https://github.com/oakstack/askg Collaboratory: https://oaks.town
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Parth is a Software Engineer at Ollama. He's worked on on-device ML systems for Siri at Apple, and large-scale distributed systems at Tesla.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Presentation: https://youtu.be/JHWvGF5rWFA Introducing the Bee AI Agent Platform Max Maximilien, IBM Research Bee is an Open Source AI Agent platform that is LLM agnostic and comes with a full OSS stack to create no-code agents. In this talk we will give a hands on demonstration of various agents and use cases using Bee. This includes creating new agents and tools live and using them with audience participation. Additionally, we will discuss plans and roadmap for the next 6 months, including showing Bee Hive which extends Bee with multiagency. Michael Maximilien (aka Max or Dr. Max) is distinguished engineer at IBM Research where he leads the open multiagent research team. In that capacity he leads the research and development of the Bee Hive addition to the Bee Platform. Max has over 25 years experience in software research and development. He is an avid Leica photographer and cyclist.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Presentation: Nikita is a founder of Humatron AI. He was also the original creator of Apache Ignite and Apache NLPCraft as well as the founder of GridGain Systems . But his most passionate creation is the CosPlay engine - one and only pure ASCII game engine.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Michael Goin Presentation: https://youtu.be/aM8cEAaGURA
A review of the OSS AI ecosystem proposing a big tent approach to organizing knowledge for AI applications and building an ecosystem of OSS AI practitioners in LFAI.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Check Out the Talk Here ➡️ https://youtu.be/2UTddUNIIh4 Leann is a Generative AI Developer Advocate at Diffbot, who currently focuses on enhancing the performance of LLM-based applications by integrating the strengths of knowledge graphs. She creates content about Generative AI and Knowledge Graph Content on YouTube and LinkedIn.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Check Out the Talk Here ➡️ https://youtu.be/H04t-Oy2-RU Tomaž Bratanic is a network scientist at heart, working at the intersection of graphs and machine learning. He has applied these graph techniques to projects in various domains including fraud detection, biomedicine, business-oriented analytics, and recommendations.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Jiang Chen is the Head of Ecosystem and Developer Relations at Zilliz, the company behind the open-source vector database Milvus. He had previously served as a tech lead and product manager at Google, where he led the development of web-scale semantic understanding and search indexing that powers innovative search products such as short video search. He has years of industry experience handling massive unstructured data and multi-modal content retrieval. Jiang holds a Master's degree in Computer Science from the University of Michigan.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Roie Schwaber-Cohen is a Staff Developer Advocate at Pinecone, specializing in AI and data-intensive applications. With nearly 20 years of experience in software engineering, Roie has expertise in full-stack development, microservices architectures and data intensive applications.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference GraphRAG is one of the most promising architectures for enterprise AI. In this talk, we’ll explore technical and community efforts required to make GenAI ready for production, with the focus on the most recent advances in GraphRAGw with LangChain and LlamaIndex integrations. Dr. Alexy Khrabrov is the founder and organizer of bay.area.ai and the AI Community Architect at Neo4. He is also a founder of opensource.science at NumFOCUS and a cofounder of thealliance.ai. Alexy founded and runs scale.bythebay.io, a conference of the Bay Area developer meetups, for ten years.
ai.bythebay.io Nov 2025, Oakland, full-stack AI conference Michael Ryan is a masters student at Stanford University working on optimization for Language Model Programs in DSPy and Personalizing Language Models. His work has been recognized with a Best Social Impact award at ACL 2024, and an honorable mention for outstanding paper at ACL 2023. Michael co-lead the creation of the MIPRO & MIPROv2 optimizers, DSPy’s most performant optimizers for Language Model Programs. His prior work has showcased unintended cultural and global biases expressed in popular LLMs. He is currently a research intern at Snowflake.
GraphRAG is one of the most promising architectures for enterprise AI. A review of technical and community efforts required to make GenAI ready for production, focusing on recent advances in GraphRAG with LangChain and LlamaIndex integrations.
Showing 7 of 7
Meetup photo album
Open gallery ↗Meetup photo album
Open gallery ↗Conference photo album
Open gallery ↗Conference photo album
Open gallery ↗Conference photo album
Open gallery ↗Conference photo album
Open gallery ↗Conference photo album
Open gallery ↗