SANS
GERARD
Spoken 199 times in 43 countries
Vertex AI
Complexity
Features
1
2
VertexAI
AI Platform
Gemini for Workspace
AI Assistant
AI Studio
AI Playground
Gemini
Foundational
Models
Gemini
Chatbot
Med-Palm
Vertex AI
Global
Vertex AI
Complexity
Features
Voice
text-speech speech-text
Medical
medlm-medium medlm-large
Code
code-bison codechat-bison code-gecko
Multimodal
gemini-pro gemini-pro-vision
gemini-ultra*
Gemini 1.0 Pro 128K tokens
(100 pages)
Gemini 1.5 Pro 1M
(800 pages)
Adjust model predictions using output
Wikipedia
Christopher  is
Christopher Columbus was
Input
Output
Christopher Columbus discovered  America
Christopher Columbus discovered America  in
Christopher Columbus discovered America in  1492
Christopher Columbus discovered America in 1492 Â .
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492 .
who
is
America
Columbus
discover
Latent Space
Word Embedding
Word Embedding
A prompt will put you in a certain area of the latent space
Note the density of data points and noise ratios
Biased
Non-factual
Inaccurate
1+1= 3
VectorDB Embeddings
Google Knowledge Graph
Google Search
Fact Checking
AI Studio
AI Playground
Gemini
API
Gemini
Fine-tuning
magazine style 4k photorealistic,
modern red armchair
natural lighting
Portrait of a french bulldog
at the beach,
85mm f/2.8
Assortment
of delicious,
freshly-baked donuts
Prompt
Imagen 2
Original + mask
Imagen 2
Input
Caption
Input
Question
Global
Vertex AI
Complexity
Features
Image Generation
Google Lens
Google Search
Listen Response
Share
+40 Languages
C++, Go, Java, Javascript, Python and Typescript
Generate
complex graphics
Access your GMail.
Deep integration with YouTube.
 US-only
Vertex AI
Complexity
Features
GoogleAI
VertexAI
Pro 1.0
Pro 1.5
Ultra 1.0
Nano 1.0
1h
video
11h
audio
30K
LOC
800
pages
1 Million tokens
Embeddings
models/embedding-001
Gemini Pro
gemini-pro
Gemini Pro Vision
gemini-pro-vision
Source: V7 Labs
A dog running
Digits 0-9
Ant
French cat
MNIST
60K
10 classes
COCO
330K
80 classes
ImageNet
14MÂ
Image + caption
LAION (Web)
5B
Image + text
Query Patch
Detail
Image
"ginger fur"
"standing on a stone in the garden"
"well-groomed"
Image
Features
Attention
Visual Chat
VQA
Multi-turn
Reasoning
Extract Data
Handwriting
Data entry
OCR
Metadata
Identify
Recognition
Captioning
Categorising
Structure
Elements
Relationships
Hierarchies
Time/Space
Tracking
Activity
Causality
3D/4D
Monday to Friday from 6:30 to 13:00 from 16:30 to 20:00
Extract the text for the opening hours and consolidate them in a single paragraph in English
Prompt
Output
HORARI DILLUNS A DIVENDRES DE 6'30H. A
Extract Text
OCR
Image Input
Task
Raw Data
13H 16'30H. A 20'00H
Extract Text
Hand-written OCR
Reason
Mash-up fragments
HORARI DILLUNS A DIVENDRES DE 6'30H. A 13H 16'30H. A 20'00H
Translate
Catalan to English
Monday to Friday from 6:30 to 13:00 from 16:30 to 20:00