@yourtwitterhandle | developer.confluent.io
What are the best practices to debug client applications
(producers/consumers in general but also Kafka Streams
applications)?
Starting soon…
STARTING SOOOOON..
Starting sooooon ..
Starting soon…
Starting soon…
@yourtwitterhandle | developer.confluent.io
What are the best practices to debug client applications
(producers/consumers in general but also Kafka Streams
applications)?
Starting soon…
STARTING SOOOOON..
Starting sooooon ..
Starting soon…
Copyright 2021, Confluent, Inc. All rights reserved. This document may not be reproduced in any manner without the express written permission of Confluent, Inc.
Real-time AI
Model
Config
Params,
Features
Vector Store
Object store
AI-powered
Apps
Telemetry
MLOps Pipelines
Training
Data
Output
Goal
Partners Tech Talks are webinars where subject matter experts from a Partner talk about a
specific use case or project. The goal of Tech Talks is to provide best practices and
applications insights, along with inspiration, and help you stay up to date about innovations
in confluent ecosystem.
@yourtwitterhandle | developer.confluent.io
I will add a slide about the next talk
@yourtwitterhandle | developer.confluent.io
Starting soon…
STARTING SOOOOON..
Starting sooooon ..
@yourtwitterhandle | developer.confluent.io
Starting soon…
STARTING SOOOOON..
Starting sooooon ..
Confluent Perspective : AI
8
The Rise of Data Streaming for GenAI
Kai Waehner
Field CTO
kai.waehner@confluent.io
linkedin.com/in/kaiwaehner
@KaiWaehner
confluent.io
kai-waehner.de
The Rise of Data Streaming
Real-time Data beats Slow Data.
Logistics
Real-time sensor
diagnostics
Delivery planning
ETA updates
Payment
Fraud detection
Risk systems
Mobile applications /
customer experience
Retail
Real-time inventory
Real-time POS
reporting
Personalization
Sales
Real-time
recommendations
Personalized
coupon feed
Pay by walking out
The Rise of Data Streaming
Data Streaming to Unlock the Value of Data
The Rise of Data Streaming
Universal Data Products
Write Your Data as a Stream or Table, Read It Anywhere
The Rise of Data Streaming
Challenge: Build a conversational chatbot service that
incorporates complex technologies such as fulfillment,
natural-language understanding, and real-time analytics
Solution: Use Confluent to build a fast, super-scalable
event-driven architecture that could handle immense traffic
spikes and also provide other guarantees around delivery
semantics
Results:
● Near-zero downtime even during huge traffic spikes
● Rapid acceleration of new-skill onboarding
● Doubling of NPS rating
Virtual Agent Platform:
(Marc Silbey, VP of Product at Expedia)
The Rise of Data Streaming
Data Products Versioned in git
Schema
Registry
Confluent Cloud
Consumer
Group
LLM API Gateway
LLM Instances
LLM Service
Schema Specs
Terraform
Web Chat Agent
MongoDB
Vector Search
Reasoning Agent
How Confluent Works with Gen AI - Big Picture
Enforce Business Logic and Compliance Requirements with LLM Outputs
Post- Processing
Consumer Group
RAG
Airport - Physical Location
Airline Website
Bag Tracking
Cancelation/Delays
Crew Scheduling
Online Bookings
Special Offers
Loyalty Rewards
Data Governance
Field Level Tags Data Rules
Real-Time Airport, Flight, and
Price Validation
Flink SQL
Valid Answer
User Question
Kafka Topics
Producer
Connector
Connector
Connector
Producer
Connector
Crew
Customer
Flight
Gate
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
Amazon Bedrock
The easiest way to build and scale generative AI
applications with foundation models
Solutions Architect
EMEA Data & AI ISV Champion & Worldwide Ambassador
Amazon Web Services (AWS)
Steffen Schneider
st-sch
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
16
What generative AI customers are asking for
Which model
should I use?
How can I
move quickly?
How can I keep
my data secure
and private?
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
17
Amazon Bedrock
The easiest way to build and scale
generative AI applications with
foundation models (FMs)
Choice of leading FMs through a single API
Model customization
Retrieval Augmented Generation (RAG)
Agents that execute multistep tasks
Security, privacy, and safety
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
18
Integration
Choice Customization Security and
governance
Amazon Bedrock
simplifies
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
19
Summarization,
complex reasoning,
writing, coding
Contextual answers,
summarization,
paraphrasing
High-quality images
and art
Text generation,
search, classification
Q&A and reading
comprehension
Text summarization,
generation,
Q&A, search,
image generation
Amazon Titan
Text Premier
Amazon Titan
Text Lite
Amazon Titan
Text Express
Amazon Titan Text
Embeddings
Amazon Titan Text
Embeddings V2
Amazon Titan
Multimodal
Embeddings
Amazon Titan
Image Generator
Claude 3.5 Sonnet
Claude 3 Opus
Claude 3 Sonnet
Claude 3 Haiku
Claude 2.1
Claude 2
Claude Instant
Llama 3 8B
Llama 3 70B
Llama 2 13B
Llama 2 70B
Command
Command Light
Embed English
Embed Multilingual
Command R+
Command R
Stable Diffusion XL1.0
Stable Diffusion
XL 0.8
Jamba-Instruct
Jurassic-2 Ultra
Jurassic-2 Mid
Mistral Small
Mistral Large
Mistral 7B
Mixtral 8x7B
Text summarization,
text classification,
text completion,
code generation, Q&A
BROAD CHOICE OF MODELS
Amazon Bedrock
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
20
Enabling semantic
(vector) search
across our services
Amazon
DocumentDB
Amazon Neptune
Amazon DynamoDB
via zero-ETL
Amazon MemoryDB
for Redis
Amazon
OpenSearch Service
Amazon RDS for PostgreSQL
Amazon
OpenSearch Serverless
Amazon Aurora
PostgreSQL
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
21
Storing vectors and data together
Avoid additional
licensing and
management
Provide a faster
experience to
end users
Reduce the need
for data sync
and movement
Use familiar tools
that meet your
requirements
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
22
ENABLE GENERATIVE AI APPLICATIONS TO EXECUTE MULTISTEP TASKS USING COMPANY SYSTEMS AND DATA
SOURCES
Agents for Amazon Bedrock
Breaks down and orchestrates tasks
Securely accesses and retrieves company data for RAG
Takes action by invoking API calls on your behalf
Chain-of-thought trace and ability to modify agent prompts
SELECT YOUR
FOUNDATION MODEL
PROVIDE BASIC
INSTRUCTIONS
SELECT RELEVANT
DATA SOURCES
SPECIFY AVAILABLE
ACTIONS
1 2 3 4
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
23
Guardrails for
Amazon Bedrock
Configure harmful content filtering
based on your responsible AI policies
Define and disallow denied topics with
short natural language descriptions
Redact or block sensitive information
such as PIIs, and custom Regex
IMPLEMENT SAFEGUARDS CUSTOMIZED TO
YOUR APPLICATION REQUIREMENTS
AND RESPONSIBLE AI POLICIES
Apply guardrails to multiple foundation
models and Agents for Amazon Bedrock
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved
24
None of the customer’s data is used
to train the underlying models
All data is encrypted in transit and at rest;
data used for customization is securely
transferred through customer’s VPC
Support for GDPR, SOC, ISO, CSA
compliance, and HIPAA eligibility
Data remains in the Region where the
API is processed
Amazon Bedrock
HELPS KEEP YOUR DATA
SECURE AND PRIVATE
Partner Integration Designer
PID is an internal tool that helps build customer and partner facing demos faster.
PID has the following features and capabilities:
● Drag and drop UI for designing demos
● Includes many building blocks from the Kafka and the wider ecosystem including but not limited to:
○ Relational/NoSql databases
○ Source and Target Connectors
○ KSQL
○ Producers/consumers
● Allows industry specific random data to be streamed into your demo
● Allow demos to be shared with others
25
@yourtwitterhandle | developer.confluent.io
Enables real-time updates and handles
high-dimensional data effectively, while
integrating with other database features for
robust functionality.
Components
1. Documents are published using
connectors or Kafka APIs.
2. Each document is split into chunks for
better granularity and to enable parallel
processing.
3. Embeddings are created for each chunk
using the Bedrock embeddings service.
4. The embeddings/chunks are indexed in a
vector database using sink connectors.
Key Points
● Achieve real-time relevance with the vector
database.
● Utilize a microservice architecture for
scalability.
● Enable each microservice to independently
scale for enhanced performance,
responsiveness, and stability.
● Leverage Bedrock embeddings to enhance
vector quality.
Unstructured Document Indexing
@yourtwitterhandle | developer.confluent.io
Chatbot use case
Utilizes artificial intelligence tailored for
genomic data, assisting users in tasks like
data analysis, interpretation, and
exploration within the realm of genomics.
Components
1. Chat interaction serves as the human
interface to the system.
2. An embedding is generated for each
human interaction.
3. Embeddings are utilized to discover similar
documents, aiding the prompt engineering
service.
4. Prompts are crafted from various data
sources (Vector search results, Conversation
history/summary, …)
5. The prompt is forwarded to Bedrock LLM.
6. Conversations can be summarized for
utilization by the prompt engineering
service.
Key Points
● Utilize a microservice architecture for
scalability.
● Enable each microservice to independently
scale for enhanced performance,
responsiveness, and stability.
● Leverage Bedrock LLM
@yourtwitterhandle | developer.confluent.io
All together
@yourtwitterhandle | developer.confluent.io
All together
@yourtwitterhandle | developer.confluent.io
Q&A

Unleashing the Future: Building a Scalable and Up-to-Date GenAI Chatbot with Amazon Bedrock, Rockset and Confluent Cloud

  • 1.
    @yourtwitterhandle | developer.confluent.io Whatare the best practices to debug client applications (producers/consumers in general but also Kafka Streams applications)? Starting soon… STARTING SOOOOON.. Starting sooooon .. Starting soon… Starting soon…
  • 2.
    @yourtwitterhandle | developer.confluent.io Whatare the best practices to debug client applications (producers/consumers in general but also Kafka Streams applications)? Starting soon… STARTING SOOOOON.. Starting sooooon .. Starting soon…
  • 3.
    Copyright 2021, Confluent,Inc. All rights reserved. This document may not be reproduced in any manner without the express written permission of Confluent, Inc. Real-time AI Model Config Params, Features Vector Store Object store AI-powered Apps Telemetry MLOps Pipelines Training Data Output
  • 4.
    Goal Partners Tech Talksare webinars where subject matter experts from a Partner talk about a specific use case or project. The goal of Tech Talks is to provide best practices and applications insights, along with inspiration, and help you stay up to date about innovations in confluent ecosystem.
  • 5.
    @yourtwitterhandle | developer.confluent.io Iwill add a slide about the next talk
  • 6.
    @yourtwitterhandle | developer.confluent.io Startingsoon… STARTING SOOOOON.. Starting sooooon ..
  • 7.
    @yourtwitterhandle | developer.confluent.io Startingsoon… STARTING SOOOOON.. Starting sooooon ..
  • 8.
  • 9.
    The Rise ofData Streaming for GenAI Kai Waehner Field CTO kai.waehner@confluent.io linkedin.com/in/kaiwaehner @KaiWaehner confluent.io kai-waehner.de
  • 10.
    The Rise ofData Streaming Real-time Data beats Slow Data. Logistics Real-time sensor diagnostics Delivery planning ETA updates Payment Fraud detection Risk systems Mobile applications / customer experience Retail Real-time inventory Real-time POS reporting Personalization Sales Real-time recommendations Personalized coupon feed Pay by walking out
  • 11.
    The Rise ofData Streaming Data Streaming to Unlock the Value of Data
  • 12.
    The Rise ofData Streaming Universal Data Products Write Your Data as a Stream or Table, Read It Anywhere
  • 13.
    The Rise ofData Streaming Challenge: Build a conversational chatbot service that incorporates complex technologies such as fulfillment, natural-language understanding, and real-time analytics Solution: Use Confluent to build a fast, super-scalable event-driven architecture that could handle immense traffic spikes and also provide other guarantees around delivery semantics Results: ● Near-zero downtime even during huge traffic spikes ● Rapid acceleration of new-skill onboarding ● Doubling of NPS rating Virtual Agent Platform: (Marc Silbey, VP of Product at Expedia)
  • 14.
    The Rise ofData Streaming Data Products Versioned in git Schema Registry Confluent Cloud Consumer Group LLM API Gateway LLM Instances LLM Service Schema Specs Terraform Web Chat Agent MongoDB Vector Search Reasoning Agent How Confluent Works with Gen AI - Big Picture Enforce Business Logic and Compliance Requirements with LLM Outputs Post- Processing Consumer Group RAG Airport - Physical Location Airline Website Bag Tracking Cancelation/Delays Crew Scheduling Online Bookings Special Offers Loyalty Rewards Data Governance Field Level Tags Data Rules Real-Time Airport, Flight, and Price Validation Flink SQL Valid Answer User Question Kafka Topics Producer Connector Connector Connector Producer Connector Crew Customer Flight Gate
  • 15.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved Amazon Bedrock The easiest way to build and scale generative AI applications with foundation models Solutions Architect EMEA Data & AI ISV Champion & Worldwide Ambassador Amazon Web Services (AWS) Steffen Schneider st-sch
  • 16.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 16 What generative AI customers are asking for Which model should I use? How can I move quickly? How can I keep my data secure and private?
  • 17.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 17 Amazon Bedrock The easiest way to build and scale generative AI applications with foundation models (FMs) Choice of leading FMs through a single API Model customization Retrieval Augmented Generation (RAG) Agents that execute multistep tasks Security, privacy, and safety
  • 18.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 18 Integration Choice Customization Security and governance Amazon Bedrock simplifies
  • 19.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 19 Summarization, complex reasoning, writing, coding Contextual answers, summarization, paraphrasing High-quality images and art Text generation, search, classification Q&A and reading comprehension Text summarization, generation, Q&A, search, image generation Amazon Titan Text Premier Amazon Titan Text Lite Amazon Titan Text Express Amazon Titan Text Embeddings Amazon Titan Text Embeddings V2 Amazon Titan Multimodal Embeddings Amazon Titan Image Generator Claude 3.5 Sonnet Claude 3 Opus Claude 3 Sonnet Claude 3 Haiku Claude 2.1 Claude 2 Claude Instant Llama 3 8B Llama 3 70B Llama 2 13B Llama 2 70B Command Command Light Embed English Embed Multilingual Command R+ Command R Stable Diffusion XL1.0 Stable Diffusion XL 0.8 Jamba-Instruct Jurassic-2 Ultra Jurassic-2 Mid Mistral Small Mistral Large Mistral 7B Mixtral 8x7B Text summarization, text classification, text completion, code generation, Q&A BROAD CHOICE OF MODELS Amazon Bedrock
  • 20.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 20 Enabling semantic (vector) search across our services Amazon DocumentDB Amazon Neptune Amazon DynamoDB via zero-ETL Amazon MemoryDB for Redis Amazon OpenSearch Service Amazon RDS for PostgreSQL Amazon OpenSearch Serverless Amazon Aurora PostgreSQL
  • 21.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 21 Storing vectors and data together Avoid additional licensing and management Provide a faster experience to end users Reduce the need for data sync and movement Use familiar tools that meet your requirements
  • 22.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 22 ENABLE GENERATIVE AI APPLICATIONS TO EXECUTE MULTISTEP TASKS USING COMPANY SYSTEMS AND DATA SOURCES Agents for Amazon Bedrock Breaks down and orchestrates tasks Securely accesses and retrieves company data for RAG Takes action by invoking API calls on your behalf Chain-of-thought trace and ability to modify agent prompts SELECT YOUR FOUNDATION MODEL PROVIDE BASIC INSTRUCTIONS SELECT RELEVANT DATA SOURCES SPECIFY AVAILABLE ACTIONS 1 2 3 4
  • 23.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 23 Guardrails for Amazon Bedrock Configure harmful content filtering based on your responsible AI policies Define and disallow denied topics with short natural language descriptions Redact or block sensitive information such as PIIs, and custom Regex IMPLEMENT SAFEGUARDS CUSTOMIZED TO YOUR APPLICATION REQUIREMENTS AND RESPONSIBLE AI POLICIES Apply guardrails to multiple foundation models and Agents for Amazon Bedrock
  • 24.
    © 2024, AmazonWeb Services, Inc. or its affiliates. All rights reserved 24 None of the customer’s data is used to train the underlying models All data is encrypted in transit and at rest; data used for customization is securely transferred through customer’s VPC Support for GDPR, SOC, ISO, CSA compliance, and HIPAA eligibility Data remains in the Region where the API is processed Amazon Bedrock HELPS KEEP YOUR DATA SECURE AND PRIVATE
  • 25.
    Partner Integration Designer PIDis an internal tool that helps build customer and partner facing demos faster. PID has the following features and capabilities: ● Drag and drop UI for designing demos ● Includes many building blocks from the Kafka and the wider ecosystem including but not limited to: ○ Relational/NoSql databases ○ Source and Target Connectors ○ KSQL ○ Producers/consumers ● Allows industry specific random data to be streamed into your demo ● Allow demos to be shared with others 25
  • 26.
    @yourtwitterhandle | developer.confluent.io Enablesreal-time updates and handles high-dimensional data effectively, while integrating with other database features for robust functionality. Components 1. Documents are published using connectors or Kafka APIs. 2. Each document is split into chunks for better granularity and to enable parallel processing. 3. Embeddings are created for each chunk using the Bedrock embeddings service. 4. The embeddings/chunks are indexed in a vector database using sink connectors. Key Points ● Achieve real-time relevance with the vector database. ● Utilize a microservice architecture for scalability. ● Enable each microservice to independently scale for enhanced performance, responsiveness, and stability. ● Leverage Bedrock embeddings to enhance vector quality. Unstructured Document Indexing
  • 27.
    @yourtwitterhandle | developer.confluent.io Chatbotuse case Utilizes artificial intelligence tailored for genomic data, assisting users in tasks like data analysis, interpretation, and exploration within the realm of genomics. Components 1. Chat interaction serves as the human interface to the system. 2. An embedding is generated for each human interaction. 3. Embeddings are utilized to discover similar documents, aiding the prompt engineering service. 4. Prompts are crafted from various data sources (Vector search results, Conversation history/summary, …) 5. The prompt is forwarded to Bedrock LLM. 6. Conversations can be summarized for utilization by the prompt engineering service. Key Points ● Utilize a microservice architecture for scalability. ● Enable each microservice to independently scale for enhanced performance, responsiveness, and stability. ● Leverage Bedrock LLM
  • 28.
  • 29.
  • 30.