Integrating Multimodal AI in Your Apps with Floom

Webinar to explore the integration of multimodal AI functions in applications with insights from the co-founder and CEO of Floom AI.

1. Integrating Multimodal AI in Your Apps

2. Max Brin, Co-Founder & CEO
CTO Cyber @ Amdocs
Co-Founder & CEO@ Cards
Research & Innovation Lead @ CyberArk
Co-Founder & CEO of Hoger
Chief Architect @ Enabley
About me

3. What is Floom trying to solve?
The gapbetween AI Potential
and AIIntegration

4. Where’s the gap?
No robustdev/dep infra
Technicalbarrier
No CentralizedManagement
Inspiration Deficit

5. Existing AI Integration Flow
AI
Model
App
Code
Library
Gateway
Logging, Caching,
Routing, Security etc.
Logic Coating
Data Ingestion, RAG,
Embeddings
Centralization

6. Floom, AI Orchestrator
Open-Source
Floom
AI Orchestrator
AI Model
Multimodal
App

7. AI Functions
Direct Inference + Agents
Extract Physical Addresses
Generate Speech from Text
Detect Objects in Image
Detect Emotion in Text
Classify PG rating in VideoAsk questions about data
Invoke Toolsfor action Generate Image

8. AI Functions
Deploy

9. RAG (Context)

10. Now... Run it!

12. Why did we choose Milvus DB?
Lowest latency
Friendly, well documented APIs
Predictable under load!
Passed our rigorous production testing

13. How does Milvus DB enable Floom?
Floom relies on Milvus for RAG and general embeddings search (CS/L2/IP)
DefaultVector DB for Floom Docker (part of docker-compose)
DefaultVector DB for Floom Cloud (Zilliz Cloud)
Full RAG + Multimodal (Video!) experimentation

14. Most companies keep GenAI as POC
Most product managers focus on the classic GenAI examples
(text+code generation)
Generalizing GenAI is hard, but feasibleand well worth it.
GenAI integration is currently reserved to GenAI enthusiasts, Data
Scienceor Innovationteam
Using currentdev/dep methodologies, GenAI is not yet
production-grade
Key Lessons

15. Roadmap:
AI Definition Markup Language
●Generalizedapproach towards developing and maintaining AI integrations
●Distilledto “AIFunctions” (including both agentsand direct inference)
●Easytounderstand, build, debug and maintain across versatile teams
●Designedfordeveloperswithnotolittleprior AI/GenAI knowledge
●Easily packedinadistributable format
○Definition(AI Functions: Inference + Agents)
○Configuration
○Orchestration

16. Let’s Floom.
Questions?