Day 5: AI APIs and Vertex AI | Google Cloud in 5 Days

Pre-built AI APIs

GCP offers AI APIs that require zero ML knowledge — just HTTP calls. They're trained by Google and ready to use.

Terminal

pip install google-cloud-vision google-cloud-language google-cloud-aiplatform

Vision API

from google.cloud import vision

client = vision.ImageAnnotatorClient()

with open('photo.jpg', 'rb') as f:
    content = f.read()

image = vision.Image(content=content)

# Detect labels
response = client.label_detection(image=image)
for label in response.label_annotations:
    print(f'{label.description}: {label.score:.2f}')

# Read text from image
response = client.text_detection(image=image)
print(response.text_annotations[0].description)

Gemini via Vertex AI

import vertexai
from vertexai.generative_models import GenerativeModel

vertexai.init(project='YOUR_PROJECT_ID', location='us-central1')

model = GenerativeModel('gemini-1.5-flash')

response = model.generate_content(
    'Explain cloud computing in one paragraph for a beginner.'
)
print(response.text)

# With a system prompt
model = GenerativeModel(
    'gemini-1.5-flash',
    system_instruction='You are a concise technical writer. Always use bullet points.'
)
response = model.generate_content('What is Kubernetes?')
print(response.text)

ℹ️

Vertex AI is GCP's unified ML platform. It hosts both Google's models (Gemini, Imagen) and lets you deploy your own. For most applications, the pre-built Gemini models via Vertex AI are all you need.

📝 Day 5 Exercise

Build an AI Data Pipeline

U
s
e
t
h
e
V
i
s
i
o
n
A
P
I
t
o
e
x
t
r
a
c
t
t
e
x
t
f
r
o
m
3
i
m
a
g
e
s
(
o
r
u
s
e
t
h
e
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
A
P
I
t
o
a
n
a
l
y
z
e
s
e
n
t
i
m
e
n
t
i
n
a
l
i
s
t
o
f
r
e
v
i
e
w
s
)
.
F
e
e
d
t
h
e
r
e
s
u
l
t
s
i
n
t
o
B
i
g
Q
u
e
r
y
.
W
r
i
t
e
a
q
u
e
r
y
t
o
s
u
m
m
a
r
i
z
e
t
h
e
f
i
n
d
i
n
g
s
.

Day 5 Summary

Vision API: labels, text (OCR), faces, objects — all from a single image upload.
Natural Language API: sentiment, entities, syntax — for text analysis without training a model.
Vertex AI hosts Gemini. The Python SDK mirrors the Gemini API syntax.
Pre-built APIs cost per call but require zero training data or ML expertise.

→

← Previous

Day 4: BigQuery for Analytics

Course Complete

Back to Google Cloud in 5 Days

→