Tag Archives: fastapi

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

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

Unknown's avatar Namal Fernando 9:27 am on 14th May 2026
Tags: fastapi, OpenAI, , transator   

Building a Simple Translation REST API with OpenAI, FastAPI, and Python

1. Python code

Create a file named: openai_tr.py

from fastapi import FastAPI
from pydantic import BaseModel
from openai import OpenAI
import os
import logging
# Logging Configuration
logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s %(levelname)s %(name)s : %(message)s"
)
logger = logging.getLogger(__name__)
# OpenAI Client
client = OpenAI(
    api_key=os.getenv("OPENAI_API_KEY")
)
# FastAPI App
app = FastAPI()
# Request Model
class TranslationRequest(BaseModel):
    text: str
    targetLanguage: str
# Locale Mapping
LOCALE_MAP = {
    "es-PR": "Puerto Rico Spanish",
    "es-MX": "Mexican Spanish",
    "es-ES": "Spain Spanish",
    "es-US": "United States Spanish",
    "fr-CA": "Canadian French",
    "pt-BR": "Brazilian Portuguese"
}
# Translation API
@app.post("/api/translations")
def translate(request: TranslationRequest):
    locale_name = LOCALE_MAP.get(
        request.targetLanguage,
        request.targetLanguage
    )
    prompt = f"""
Translate the following text into natural {locale_name}.
Rules:
- Preserve tone and meaning
- Keep placeholders unchanged
- Keep HTML tags unchanged
- Avoid robotic translation
- Return only the translated text
Text:
{request.text}
"""
    # Logging
    logger.info("======================================")
    logger.info("Translation Request Received")
    logger.info("Target Language: %s", request.targetLanguage)
    logger.info("Locale Name: %s", locale_name)
    logger.info("Original Text: %s", request.text)
    logger.info("Prompt:\n%s", prompt)
    try:
        response = client.chat.completions.create(
            model="gpt-5",
            messages=[
                {
                    "role": "system",
                    "content": "You are a professional localization translator."
                },
                {
                    "role": "user",
                    "content": prompt
                }
            ]
        )
        translated_text = response.choices[0].message.content
        logger.info("Translated Text: %s", translated_text)
        logger.info("======================================")
        return {
            "translatedText": translated_text,
            "targetLanguage": request.targetLanguage
        }
    except Exception as e:
        logger.exception("Translation Error Occurred")
        return {
            "error": str(e)
        }

2. Provide the OpenAI API key as an environment variable

Go to the OpenAI API keys page and create a new secret key. OpenAI’s quickstart also uses the OPENAI_API_KEY environment variable pattern for SDK authentication.[see]

$env:OPENAI_API_KEY="<your api key>"

3. Run the API

Create and activate a virtual environment:

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

Install prerequisites:

pip install openai fastapi uvicorn

Run the API:

uvicorn openai_tr:app --reload

4. Test the result

POST request:

POST http://127.0.0.1:8000/api/translations

Body:

{
  "text": "The Strait of Hormuz has emerged as the central battleground of the Iran conflict. The passage of a handful of oil and gas tankers in recent days, apparently with Tehran’s consent, hints at tacit acceptance ​of its control. This foreshadows a more dangerous phase in what is fast turning into a Hormuz war.",
  "targetLanguage": "es-PR"
}

#fastapi, #openai, #python, #transator