17-October-2024 NYC AI Camp - Step-by-Step RAG 101
0 likes•290 views
The document provides an overview of Milvus, an open-source vector database designed to manage and utilize embedding vectors for deep learning applications. It introduces concepts related to retrieval-augmented generation (RAG), emphasizing its benefits in improving data accuracy and maintaining data sovereignty. Additionally, the document highlights upcoming events related to unstructured data and vector databases, underscoring the growing significance of this technology in machine learning and data science.
![48 | © Copyright Zilliz
48
Vector Similarity Measures: L2 Euclidean)
Queen = [0.3, 0.9]
King = [0.5, 0.7]
d(Queen, King) = √(0.3-0.5)2
+ (0.9-0.7)2
= √(0.2)2
+ (0.2)2
= √0.04 + 0.04
= √0.08 ≅ 0.28](https://image.slidesharecdn.com/17oct2024-nycaicamp-step-by-steprag101-241014220538-20f66acd/85/17-October-2024-NYC-AI-Camp-Step-by-Step-RAG-101-48-320.jpg)
![49 | © Copyright Zilliz
49
Vector Similarity Measures: Inner Product IP
Queen = [0.3, 0.9]
King = [0.5, 0.7]
Queen · King = (0.3*0.5) + (0.9*0.7)
= 0.15 + 0.63 = 0.78](https://image.slidesharecdn.com/17oct2024-nycaicamp-step-by-steprag101-241014220538-20f66acd/85/17-October-2024-NYC-AI-Camp-Step-by-Step-RAG-101-49-320.jpg)
![50 | © Copyright Zilliz
50
Queen = [0.3, 0.9]
King = [0.5, 0.7]
Vector Similarity Measures: Cosine
𝚹
cos(Queen, King) = (0.3*0.5)+(0.9*0.7)
√0.32
+0.92
* √0.52
+0.72
= 0.15+0.63 _
√0.9 * √0.74
= 0.78 _
√0.666
≅ 0.03](https://image.slidesharecdn.com/17oct2024-nycaicamp-step-by-steprag101-241014220538-20f66acd/85/17-October-2024-NYC-AI-Camp-Step-by-Step-RAG-101-50-320.jpg)
17-October-2024 NYC AI Camp - Step-by-Step RAG 101
- 1. 1 | © Copyright 2024 Zilliz 1 Step-by-Step - RAG 101 Tim Spann @ Zilliz Principal Developer Advocate
- 2. 2 | © Copyright 2024 Zilliz 2 Slides XX
- 3. 3 | © Copyright 2024 Zilliz 3 3 | © Copyright 10/22/23 Zilliz 3 | © Copyright 2024 Zilliz Tim Spann Principal Developer Advocate, Zilliz [email protected] https://www.linkedin.com/in/timothyspann/ https://x.com/PaaSDev
- 4. 4 | © Copyright 2024 Zilliz 4 Agenda About Zilliz, Milvus and Vector Databases 01 Level 100 Basic RAG References 03 02
- 5. 5 | © Copyright 2024 Zilliz 5 | © Copyright 9/25/23 Zilliz 5 VECTOR DATABASE
- 6. 6 | © Copyright 2024 Zilliz 6 | © Copyright 9/25/23 Zilliz 6 The Forrester Wave™ Vector Database Providers, Q3 2024 Zilliz is the right partner for your Vector Database needs.
- 7. 7 | © Copyright 2024 Zilliz 7 | © Copyright 9/25/23 Zilliz 7 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 283 stars 30K docker pulls 67M forks 2.8K + Milvus: The most widely-adopted vector database
- 8. 8 | © Copyright Zilliz 8 Easy Open RAG Stack Highlighted Framework Hardware Infrastructure Embedding Models LLMs Software Infrastructure Vector Database
- 9. 9 | © Copyright Zilliz 9
- 10. 10 | © Copyright Zilliz 10 Image from Nvidia Vector Search Overview
- 11. Vn, 1 … … … 1 2 3 4 5 Transform into Vectors Unstructured Data Images User Generated Content Video Documents Audio Vector Embeddings Perform Approximate Nearest Neighbor Similarity Search Perform Query Get Results Store in Vector Database How Similarity Search Works
- 12. 12 | © Copyright 2024 Zilliz 12 | © Copyright 9/25/23 Zilliz 12 RAG Retrieval Augmented Generation)
- 13. 13 | © Copyright 2024 Zilliz 13 Basic Idea Use RAG to force the LLM to work with your data by injecting it via a vector database like Milvus
- 14. 14 | © Copyright 2024 Zilliz 14 Basic RAG Architecture
- 15. 1 5 Retrieval-Augmented Generation (RAG) 2024 A technique that combines the strength of retrieval-based and generative models: ● Improve accuracy and relevance ● Eliminate hallucination ● Provide domain-specific knowledge
- 16. 1 6 RAG : an economic perspective 2024 A business model that bridges public data and private data ● Data sovereignty ● You can't and shouldn't give your private data to others
- 17. 17 | © Copyright 2024 Zilliz 17 | © Copyright 9/25/23 Zilliz 17 Your Turn Time To Build a Simple RAG App
- 18. 18 | © Copyright 2024 Zilliz 18 Documents From Here https://bit.ly/3U7Okgu
- 19. 19 | © Copyright 2024 Zilliz 19 Notebook From Here https://bit.ly/3BV4IKX
- 20. 20 | © Copyright Zilliz 20
- 21. 21 | © Copyright Zilliz 21
- 22. 22 | © Copyright Zilliz 22 Python SDK Connect…
- 23. 23 | © Copyright Zilliz 23 Choose Your Embedding Function
- 24. 24 | © Copyright Zilliz 24 Vector Embedding
- 25. 25 | © Copyright Zilliz 25
- 26. 26 | © Copyright Zilliz 26
- 27. 27 | © Copyright Zilliz 27
- 28. 28 | © Copyright Zilliz 28
- 29. 29 | © Copyright Zilliz 29
- 30. 30 | © Copyright Zilliz 30
- 31. 31 | © Copyright Zilliz 31
- 32. 32 | © Copyright Zilliz 32
- 33. 33 | © Copyright 2024 Zilliz 33 | © Copyright 9/25/23 Zilliz 33 Advanced RAG
- 34. 34 | © Copyright Zilliz 34 https://bit.ly/4eFdMlK https://bit.ly/3BLeLCx
- 35. 35 | © Copyright Zilliz 35 https://bit.ly/3zXW8dX https://bit.ly/3NuK5ru
- 36. 36 | © Copyright Zilliz 36 https://bit.ly/4gZ4Lpn Metadata Filtering Hybrid Search Agents https://bit.ly/3UbqUqx https://bit.ly/3YpKd1K Smart Chunking Embedding Model Choice
- 37. 37 | © Copyright 2024 Zilliz 37 | © Copyright 9/25/23 Zilliz 37 Resources
- 38. 38 | © Copyright Zilliz 38 Wednesday, October 23, 2024 5:30 PM to 8:30 PM EDT NYC https://bit.ly/403JIvy Thursday, October 24, 2024 6:30 PM to 8:00 PM EDT Princeton https://bit.ly/3NopXY2 November 5-7, 10-12, 2024: CloudX https://www.developerweek.com/cloudx/ November 15, 2024: Build Stuff https://www.developerweek.com/cloudx/speakers/ November 19, 2024: Xtreme Python https://xtremepython.dev/2024/ November 21, 2024: bigdata Conference November 21, 2024: Unstructured Data NYC
- 39. 39 | © Copyright Zilliz 39 Vector Database Resources Give Milvus a Star! Chat with me on Discord! https://github.com/milvus-io/milvus
- 40. 40 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.
- 42. https://medium.com/@tspann/unstructured-data-processing-with-a-raspberry-pi-ai-kit-c959dd7fff47 Raspberry Pi AI Kit Hailo Edge AI
- 43. 43 | © Copyright 2024 Zilliz 43 43 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
- 44. 44 | © Copyright 2024 Zilliz 44 milvus.io github.com/milvus-io/ @milvusio @paasDev /in/timothyspann Connect with me! Thank you!
- 45. 45 | © Copyright 2024 Zilliz 45 Milvus Open Source Self-Managed Zilliz Cloud SaaS Fully-Managed github.com/milvus-io/milvus Getting Started with Vector Databases zilliz.com/cloud 29K - Star us on GitHub!
- 46. 46 | © Copyright 2024 Zilliz 46 Get started for free zilliz.com/cloud
- 47. 47 | © Copyright 2024 Zilliz 47 | © Copyright 9/25/23 Zilliz 47 Deep-Dive
- 48. 48 | © Copyright Zilliz 48 Vector Similarity Measures: L2 Euclidean) Queen = [0.3, 0.9] King = [0.5, 0.7] d(Queen, King) = √(0.3-0.5)2 + (0.9-0.7)2 = √(0.2)2 + (0.2)2 = √0.04 + 0.04 = √0.08 ≅ 0.28
- 49. 49 | © Copyright Zilliz 49 Vector Similarity Measures: Inner Product IP Queen = [0.3, 0.9] King = [0.5, 0.7] Queen · King = (0.3*0.5) + (0.9*0.7) = 0.15 + 0.63 = 0.78
- 50. 50 | © Copyright Zilliz 50 Queen = [0.3, 0.9] King = [0.5, 0.7] Vector Similarity Measures: Cosine 𝚹 cos(Queen, King) = (0.3*0.5)+(0.9*0.7) √0.32 +0.92 * √0.52 +0.72 = 0.15+0.63 _ √0.9 * √0.74 = 0.78 _ √0.666 ≅ 0.03
- 51. 51 | © Copyright Zilliz 51 Hybrid Search
- 52. 52 | © Copyright Zilliz 52