08-13-2024 NYC Meetup Unstructured Data Processing From Cloud to Edge (Milvus)
0 likes282 views
The document outlines the Zilliz Unstructured Data Meetup, hosted by Tim Spann, focusing on vector databases like Milvus and their applications in AI and analytics. It provides information on the agenda, speakers, and code of conduct, while also highlighting resources, hiring opportunities, and the importance of community engagement. The event is targeted at professionals in the field of unstructured data, including roles such as data scientists and software engineers.
08-13-2024 NYC Meetup Unstructured Data Processing From Cloud to Edge (Milvus)
- 1. 1 | © Copyright 2024 Zilliz 1 Presented by: New York Unstructured Data Meetup
- 2. 2 | © Copyright 2024 Zilliz 2 2 | © Copyright 10/22/23 Zilliz 2 | © Copyright 2024 Zilliz Tim Spann Principal Developer Advocate, Zilliz tim.spann@zilliz.com https://www.linkedin.com/in/timothyspann/ https://x.com/PaaSDev Unstructured Data Meetup | Host
- 3. 3 | © Copyright 2024 Zilliz 3 Code of Conduct Be respectful and kind When communicating with all event participants, speakers, and hosts. Be considerate All ideas are welcome Be present and participate actively in discussions. Ask questions and reach out for help when needed. Report inappropriate behavior Any inappropriate behavior is not tolerated at this event. Inform a Zilliz team member immediately if you see any behavior deemed inappropriate
- 4. 4 | © Copyright 2024 Zilliz 4 4 | © Copyright 10/22/23 Zilliz 4 | © Copyright 2024 Zilliz Milvus Open Source Self-Managed Zilliz Cloud SaaS Fully-Managed github.com/milvus-io/milvus Getting Started with Vector Databases zilliz.com/cloud
- 5. 5 | © Copyright 2024 Zilliz 5 Zilliz is Hiring! Join our Team Zilliz.com/careers • Developer Advocate • Senior Software Engineer • Staff Software Engineer • Solutions Architect
- 6. 6 | © Copyright 2024 Zilliz 6 Join the Milvus Discord!
- 7. 7 | © Copyright 2024 Zilliz 7 Become a Speaker! Interesting in speaking at and/or sponsoring a Zilliz Unstructured Data Meetup? Fill out this form! 🎤🎤🎤
- 8. 8 | © Copyright 2024 Zilliz 8 Have you built something cool using Milvus or Zilliz? We want to hear all about it. Share Your Story
- 9. 9 | © Copyright 2024 Zilliz 9 Star Milvus for a chance to win a prize tonight!
- 10. 10 | © Copyright 2024 Zilliz 10 Share your photos! #ZillizUnstructuredData @zilliz_universe, @milvusio Zilliz, Milvus
- 11. 11 | © Copyright 2024 Zilliz 11 11 | © Copyright 10/22/23 Zilliz 11 | © Copyright 2024 Zilliz Welcome Speakers Modern Analytics & Reporting with Milvus Vector DB and GenAI cuVSMilvus Combining Hugging Face Transformer Models and Visual Data with FiftyOne TECH TALK 1 TECH TALK 2 TECH TALK 3 Bill Reynolds CTO, Quarbine Corey Nolet Principal Engineer, NVIDIA Jacob Marks Senior Machine Learning Engineer & Researcher, Voxel51
- 12. 12 | © Copyright 2024 Zilliz 12 Join us at our next meetup! lu.ma/unstructured-data-meetup
- 13. 13 | © Copyright 2024 Zilliz 13 13 | © Copyright 10/22/23 Zilliz 13 | © Copyright 2024 Zilliz Quick Intro to Unstructured Data, Edge AI and Milvus Tim Spann Principal Developer Advocate, Zilliz
- 14. 14 | © Copyright 2024 Zilliz 14 Welcome to New York! Tim Spann @ Zilliz
- 15. Slides X
- 16. 16 | © Copyright Zilliz 16
- 17. 17 | © Copyright Zilliz 17 01 Introduction
- 18. 18 | © Copyright Zilliz 18 Three Pillars of GenAI & the opportunities they bring Models AI Hardware Data Vector Database ● Data Encryption ● Data ETL ● Data Security ● Data Pipeline ● Data Observability ● Data Compliance
- 19. 19 | © Copyright Zilliz 19 https://milvus.io/milvus-demos/reverse-image-search Show Me
- 20. 20 | © Copyright Zilliz 20 https://zilliz-semantic-search-example.vercel.app/ Show Me Another Demo
- 21. 21 | © Copyright Zilliz 21 Milvus: From Dev to Prod AI Powered Search made easy Milvus is an Open-Source Vector Database to store, index, manage, and use the massive number of embedding vectors generated by deep neural networks and LLMs. contributors 285 stars 28K downloads 50M forks 2K
- 22. 22 2024 Higher scalability 10B vectors of 1536 dimensions in a single Milvus/Zilliz Cloud instance 100B vectors in one of the largest deployment
- 23. https://medium.com/@tspann/unstructured-data-processing-with-a-raspberry-pi-ai-kit-c959dd7fff47 Raspberry Pi AI Kit Hailo Edge AI
- 25. 25 | © Copyright Zilliz 25 | © Copyright Zilliz 25 RESOURCES
- 26. 26 | © Copyright Zilliz 26 Vector Database Resources Give Milvus a Star! Chat with me on Discord! https://github.com/milvus-io/milvus
- 27. 27 | © Copyright Zilliz 27 https://zilliz.com/learn/generative-ai
- 28. 28 Unstructured Data Meetup https://www.meetup.com/unstructured-data-meetup-new-york/ This meetup is for people working in unstructured data. Speakers will come present about related topics such as vector databases, LLMs, and managing data at scale. The intended audience of this group includes roles like machine learning engineers, data scientists, data engineers, software engineers, and PMs. This meetup was formerly Milvus Meetup, and is sponsored by Zilliz maintainers of Milvus.
- 32. https://medium.com/@tspann/shining-some-light-on-the-new-milvus-lite-5a0565eb5dd9
- 33. Extracting Value from Unstructured Data Example • A company has 100,000s+ pages of proprietary documentation to enable their staff to service customers. Problem • Searching can be slow, inefficient, or lack context. Solution • Create internal chatbot with ChatGPT and a vector database enriched with company documentation to provide direction and support to employees and customers. https://osschat.io/chat
- 34. 34 | © Copyright Zilliz 34 Well-connected in LLM infrastructure to enable RAG use cases Framework Hardware Infrastructure Embedding Models LLMs Software Infrastructure Vector Database
- 35. 35 | © Copyright 2024 Zilliz 35 35 This week in Milvus, Towhee, Attu, GPT Cache, Gen AI, LLM, Apache NiFi, Apache Flink, Apache Kafka, ML, AI, Apache Spark, Apache Iceberg, Python, Java, Vector DB and Open Source friends. https://bit.ly/32dAJft https://github.com/milvus-io/milvus AIM Weekly by Tim Spann
- 36. 36 | © Copyright 2024 Zilliz 36 milvus.io github.com/milvus-io/ @milvusio @paasDev /in/timothyspann Connect with me! Thank you!
- 37. 37 | © Copyright 2024 Zilliz 37 Join us at our next meetup! meetup.com/unstructured-data-meetup- new-york/
- 38. 38 | © Copyright Zilliz 38 T H A N K Y O U
- 39. 39 | © Copyright Zilliz 39 Feature Pinecone Milvus Remarks Deployment Modes SaaS-only Milvus Lite, On-prem Standalone & Cluster, Zilliz Cloud Saas & BYOC Milvus offers greater flexibility in deployment modes. Supported SDKs Python, JavaScript/TypeScript Python, Java, NodeJS, Go, Restful API, C#, Rust Milvus supports a wider array of programming languages. Open-source Status Closed Open-source Milvus is a popular open-source vector database.
- 40. 40 | © Copyright Zilliz 40 Feature Pinecone Milvus Remarks Scalability Scale up/down only Scale out/in and Scale up/down Milvus features a distributed architecture for enhanced scalability. Availability Pod-based architecture within available zones Available zone failover and cross-region HA Milvus CDC Change Data Capture) enables primary/standby modes for higher availability. Perf-Cost Dollar per million queries) Starts at $0.178 for a medium dataset, $1.222 for a large dataset Zilliz Cloud starts at $0.148 for a medium dataset, $0.635 for a large dataset; free version available Refer to Cost Ranking report.
- 41. 41 | © Copyright Zilliz 41 Feature Pinecone Milvus Remarks GPU Acceleration Not supported Support NVIDIA GPU GPU acceleration significantly enhances performance, often by orders of magnitude.