Category Archives: Google Cloud

Unknown's avatar Namal Fernando 11:06 am on 14th May 2026
Tags: Cloud, google, image_moderation   

Implementing Image Moderation with Google Vision

1. Get the Cloud Vision API Key (refer this)

  • Search for and enable: Cloud Vision API
  • Double check: APIs & Services > Enabled APIs
  • Then:
    APIs & Services > Credentials
    Create Credentials > API Key > Create > Copy (as GOOGLE_VISION_API_KEY)

2. Test the Implemenatation

curl --location 'https://vision.googleapis.com/v1/images:annotate?key={{GOOGLE_VISION_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
  "requests": [
    {
      "image": {
        "source": {
          "imageUri": "http://static1.squarespace.com/static/54ca877ce4b014ea90e14bda/54ca9f5de4b021f8b6d68cc1/54caa175e4b021f8b6d6bfff/1422565749614/screen_shot_2011_11_30_at_1528461.jpg"
        }
        
      },
      "features": [
        {
          "type": "SAFE_SEARCH_DETECTION"
        }
      ]
    }
  ]
}'

Sample response : 

{
    "responses": [
        {
            "safeSearchAnnotation": {
                "adult": "VERY_LIKELY",
                "spoof": "UNLIKELY",
                "medical": "POSSIBLE",
                "violence": "UNLIKELY",
                "racy": "VERY_LIKELY"
            }
        }
    ]
}

Field Description :

FieldWhat it detects
adultPornography / explicit sexual content
racySuggestive (not explicit)
violencePhysical harm, weapons, blood
medicalMedical/surgical content
spoofFake / manipulated images

Possible values and meaning :

ValueMeaningPractical Interpretation
UNKNOWNModel couldn’t determineTreat as risky / fallback
VERY_UNLIKELYAlmost certainly safeSafe
UNLIKELYProbably safeSafe
POSSIBLEMight contain contentReview
LIKELYHigh chanceBlock
VERY_LIKELYAlmost certainBlock

#cloud, #google, #image_moderation

Unknown's avatar Namal Fernando 10:29 am on 14th May 2026
Tags: ,   

Building a Simple Translation REST API using Google Cloud Translation API, FastAPI, and Python

1. Python Code

Create a file named: google_cloud_tr.py

from fastapi import FastAPI
from google.cloud import translate_v3 as translate
app = FastAPI()
PROJECT_ID = "<your-project-id>"
LOCATION = "global"
@app.get("/translate")
def translate_text(text: str, target: str):
    client = translate.TranslationServiceClient()
    parent = f"projects/{PROJECT_ID}/locations/{LOCATION}"
    response = client.translate_text(
        request={
            "parent": parent,
            "contents": [text],
            "mime_type": "text/plain",
            "target_language_code": target,
        }
    )
    return {
        "translatedText": response.translations[0].translated_text
    }

2. Provide the Google Cloud JSON Key as an Environment Variable

  • Search for and enable: Cloud Translation API
  • Double check: APIs & Services > Enabled APIs
  • Then: IAM & Admin > Service Accounts

Steps:

  • Create a Service Account
  • Add one of these roles:
    • Cloud Translation API User
    • Cloud Translation Admin
    • or a higher role
  • Create and download the JSON key (e.g.: service-account.json)
  • Save it inside your project directory (D:\path\to\directory\google-cloud-translation\)

Provide the JSON key path as an environment variable:

$env:GOOGLE_APPLICATION_CREDENTIALS="D:\path\to\directory\google-cloud-translation\service-account.json"

3. Run the API

Create and activate a virtual environment:

python -m venv venv
.\venv\Scripts\Activate.ps1

Install prerequisites:

pip install google-cloud-translate fastapi uvicorn

Run the API:

uvicorn google_cloud_tr:app --reload

4. Test the Result

Request:

GET http://127.0.0.1:8000/translate?text=The Strait of Hormuz has emerged as the central battleground of the Iran conflict.&target=es

Example response:

{
"translatedText": "El Estrecho de Ormuz ha surgido como el principal campo de batalla del conflicto con Irán."
}

Note:

Google Cloud Translation mainly handles language translation.
For advanced regional localization (such as Puerto Rico Spanish, slang, or tone-specific translation), an LLM-based approach like OpenAI may provide more natural results. Please refer this.

#fastapi, #python