09-18-2024 NYC Meetup Vector Databases 102

1 | © Copyright 2024 Zilliz
1
Presented by:
New York
Unstructured Data Meetup

2
2 | © Copyright 10/22/23 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
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
Milvus
Open Source Self-Managed
Zilliz Cloud
SaaS Fully-Managed
github.com/milvus-io/milvus
Getting Started with Vector Databases
zilliz.com/cloud

5
Zilliz is
Hiring!
Join our
Team
Zilliz.com/careers
• Developer Advocate
• Senior Software Engineer
• Staff Software Engineer
• Solutions Architect

6
Join the
Milvus
Discord!

7
Become a
Speaker!
Interesting in speaking at and/or
sponsoring a Zilliz Unstructured
Data Meetup? Fill out this form!
🎤🎤🎤

8
Have you built
something cool
using Milvus or
Zilliz? We want to
hear all about it.
Share Your Story

9
Star Milvus
for a chance
to win a prize
tonight!

10
Share your
photos!
#ZillizUnstructuredData
@zilliz_universe, @milvusio
Zilliz, Milvus

11
Welcome Speakers
How Inkeep and Zilliz built
an AI Assistant
Introduction to the Data
Prep Kit
RGBX Model Development:
Exploring Four Channel ML
Workflows
TECH TALK 1 TECH TALK 2 TECH TALK 3
Robert Tran
Founder, CTO  Inkeep
Santosh Borse
Senior Engineer, watsonx Data
Engineering at IBM Research
Daniel Gural
Machine Learning and
DevRel, Voxel 51

12
Join us at our next meetup!
lu.ma/unstructured-data-meetup

13
Quick Intro to Unstructured Data, Edge AI and Milvus
Tim Spann
Principal Developer Advocate, Zilliz

14
Welcome to New York!
Tim Spann @ Zilliz

17 | © Copyright Zilliz
17
01 Introduction

19
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

20
https://milvus.io/milvus-demos/reverse-image-search
Show Me
https://multimodal-demo.milvus.io/

21
https://zilliz-semantic-search-example.vercel.app/
Show Me Another Demo

22
About Milvus
Milvus is an open-source vector database for
GenAI projects. pip install on your laptop, plug into
popular AI dev tools, and push to production with
a single line of code.
29K
GitHub Stars
25M
Downloads
250
Contributors
2,600
Forks
Easy Setup
Pip-install to start coding in a notebook within seconds
Integration
Plug into OpenAI, Langchain, LlmaIndex, and many more
Reusable Code
Write once, and deploy with one line of code into the production
environment
Feature-rich
Dense & sparse embeddings, ﬁltering, reranking and beyond

23
2024
Higher scalability
10B vectors
of 1536 dimensions
in a single Milvus/Zilliz Cloud
instance
100B vectors
in one of the largest deployment

https://zilliz.com/learn/large-language-models-and-search

25
02 Hybrid Search

26
Hybrid Search
●
https://zilliz.com/blog/metadata-filtering-hybrid-search-or-agent-in-rag-applications

27
Hybrid Search
Support the fusion of vector search and full-text search
Support the fusion of multimodal vectors from various unstructured
data types such as images, videos, audio, and text files
Utilize various types of vector embeddings. This includes dense
embeddings from models like BERT and Transformers and sparse
embeddings from algorithms like BM25, BGEM3, and SPLADE.

28
Hybrid Search
● Milvus supports the creation of up to 10 vector fields for the same
dataset within a single collection. Based on this support, hybrid
search allows users to search across multiple vector columns
simultaneously. This capability allows for combining multimodal
search, hybrid sparse and dense search, and hybrid dense and
full-text search, offering versatile and flexible search functionality.
● These vectors in different columns represent diverse facets of data,
originating from different embedding models or undergoing distinct
processing methods. The results of hybrid searches are integrated
using various re-ranking strategies.

29
Hybrid Search
This feature enables different columns to:
● Represent multiple perspectives of information. For instance, in e-commerce, product images
include front, side, and top views. Different views can be represented with different types or
dimensions of vectors.
● Utilize various types of vector embeddings. This includes dense embeddings from models like BERT
and Transformers and sparse embeddings from algorithms like BM25, BGE-M3, and SPLADE.
● Support the fusion of multimodal vectors from various unstructured data types such as images,
videos, audio, and text ﬁles. For example, in criminal investigations, suspects can be represented
through biometric modalities such as ﬁngerprints, voiceprints, and facial recognition, aiding in
identifying individuals across different modalities.
● Support the fusion of vector search and full-text search.
https://milvus.io/docs/multi-vector-search.md

30
When is Hybrid Search Recommended?
Hybrid search is ideal for complex situations demanding high
accuracy, especially when an entity can be represented by multiple,
diverse vectors. This applies to cases where the same data, such as
a sentence, is processed through different embedding models or
when multimodal information (like images, fingerprints, and
voiceprints of an individual) is converted into various vector formats.
By assigning weights to these vectors, their combined influence can
significantly enrich recall and improve the effectiveness of search
results.

31
Hybrid Search - FAQ 2
● How does a weighted ranker normalize distances between different vector fields?
A weighted ranker normalizes the distances between vector fields using assigned weights to each field. It
calculates the importance of each vector field according to its weight, prioritizing those with higher
weights. Itʼs advised to use the same metric type across ANN search requests to ensure consistency. This
method ensures that vectors deemed more significant have a greater influence on the overall ranking.
● Is it possible to conduct multiple hybrid search operations at the same time?
Yes, simultaneous execution of multiple hybrid search operations is supported.
● Can I use the same vector field in multiple AnnSearchRequest objects to perform hybrid searches?
Technically, it is possible to use the same vector field in multiple AnnSearchRequest objects for hybrid
searches. It is not necessary to have multiple vector fields for a hybrid search.

33
Choosing Vector Embedding Types

34
RESOURCES

09-18-2024 NYC Meetup Vector Databases 102

36
Well-connected in LLM infrastructure to enable RAG
use cases
Framework
Hardware
Infrastructure
Embedding Models LLMs
Software Infrastructure
Vector Database

https://medium.com/@tspann/unstructured-data-processing-with-a-raspberry-pi-ai-kit-c959dd7fff47
Raspberry Pi AI Kit Hailo
Edge AI

https://medium.com/@tspann/edgeai-edge-vector-database-6a9b5238bffb
https://github.com/tspannhw/AIM-XavierEdgeAI

39
Vector Database Resources
Give Milvus a Star! Chat with me on Discord!
https://github.com/milvus-io/milvus

40
https://zilliz.com/learn/generative-ai

41
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.

https://medium.com/@tspann/unstructured-street-data-in-new-york-8d3cde0a1e5b

https://medium.com/@tspann/not-every-field-is-just-text-numbers-or-vectors-976231e90e4d

https://medium.com/@tspann/shining-some-light-on-the-new-milvus-lite-5a0565eb5dd9

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

47
Well-connected in LLM infrastructure to enable RAG
use cases
Framework
Hardware
Infrastructure
Embedding Models LLMs
Software Infrastructure
Vector Database

48
48
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

49
milvus.io
github.com/milvus-io/
@milvusio
@paasDev
/in/timothyspann
Connect with me!
Thank you!

50
These capabilities make us the perfect partner to
uplifting your initiatives on vector search and AI/ML
Data
processing &
connectivity
Security
& Availability
Operational
burden &
resources
Milvus Zilliz
Tedious configuration. Manual &
resource-intensive day-to-day operations
to deploy, manage, and scale clusters.
Custom-built security tools & integrations
that creates tech & operational debt.
Resource-intensive failover design &
operations.
Instant cluster provisioning and scaling.
Automated capacity mgmt and upgrades.
Improved performance for compute intensive
use cases.
Battle-tested and enterprise-grade security
tools and compliance ready out-of-the-box.
Highly available and consistent access to
data across all of your environments.
Siloed solutions and custom integrations,
escalating complexity & costs to manage
and maintain platform as it scales
Well-integrated into AI and data ecosystems.
Out-of-box pipeline builders transform
unstructured data into searchable vectors
efficiently.

51
Cool AI News
OpenAI and Thrive Capital recently backed Chai Discovery, a six-month-old AI biology startup founded by ex-OpenAI and Meta
researchers that raised $30 million to develop AI models for drug discovery.
The details:
● Chai’s AI model, Chai-1, predicts biochemical molecule structures, potentially speeding up drug development.
● The company claims Chai-1 outperforms Google DeepMind’s AlphaFold on certain benchmarks.
● Chai-1 can work with proteins, small molecules, DNA, and RNA, making it versatile for various applications.
● Chai is making its first model free and open-source for non-commercial use.
https://github.com/chaidiscovery/chai-lab

52

53

54
Join us at our next meetup!
meetup.com/unstructured-data-meetup-
new-york/

55
T H A N K Y O U

09-18-2024 NYC Meetup Vector Databases 102

More Related Content

Similar to 09-18-2024 NYC Meetup Vector Databases 102 (20)

More from Timothy Spann (18)

Recently uploaded (20)

09-18-2024 NYC Meetup Vector Databases 102