Translate

You can get machine translation and translation quality scores from the /translate REST API endpoint or any of the official SDKs (Python, Go, Rust, JS, or cURL).

Under the hood, the /translate endpoint simultaneously leverages multiple state-of-the-art LLM and machine translation models to perform translations. The translations from these models are scored and ranked using reference-free quality estimation models. This allows us to select the highest quality machine translation for the given source and target languages.

The /translate endpoint will return a JSON object response with two fields:

• Best translation - The translated text.
• Score - A score from -1.0 to 1.0 representing the translation quality. Higher the score better the quality.

Additionally, you can opt to use third-party translation engines such as OpenAI, DeepL, and Google. By default, the use of these commercial engines is set to false.

Our translation API supports a wide range of languages, including but not limited to English, Hindi, French, Spanish, German, and more.

Generate a Translation

To generate a translation, you can use the following code examples. Depending on your preference or requirements, select the appropriate method for your application.

1
import os
2
import json
3
4
from predictionguard import PredictionGuard
5
6
# Set your Prediction Guard token as an environmental variable.
7
os.environ["PREDICTIONGUARD_API_KEY"] = "<api key>"
8
9
client = PredictionGuard()
10
11
# Translate the text.
12
result = client.translate.create(
13
    		text="The sky is blue",
14
            source_lang="eng",
15
            target_lang="fra",
16
            use_third_party_engine=True
17
    )
18
19
print(json.dumps(
20
    result,
21
    sort_keys=True,
22
    indent=4,
23
    separators=(',', ': ')
24
))

The output will look something like:

1
{
2
    "translations": [
3
        {
4
            "score": 0.888733446598053,
5
            "translation": "Le ciel est bleu.",
6
            "model": "hermes_2_pro_llama_3_8b",
7
            "status": "success"
8
        },
9
        {
10
            "score": 0.888733446598053,
11
            "translation": "Le ciel est bleu.",
12
            "model": "hermes_2_pro_mistral_7b",
13
            "status": "success"
14
        },
15
        {
16
            "score": 0.888733446598053,
17
            "translation": "Le ciel est bleu.",
18
            "model": "openai",
19
            "status": "success"
20
        },
21
        {
22
            "score": 0.888733446598053,
23
            "translation": "Le ciel est bleu.",
24
            "model": "deepl",
25
            "status": "success"
26
        },
27
        {
28
            "score": 0.888733446598053,
29
            "translation": "Le ciel est bleu.",
30
            "model": "google",
31
            "status": "success"
32
        }
33
    ],
34
    "best_translation": "Le ciel est bleu.",
35
    "best_score": 0.888733446598053,
36
    "best_translation_model": "hermes_2_pro_llama_3_8b",
37
    "created": 1726862165,
38
    "id": "translation-88d58be2858d4adc86bc6b8e3ac34aae",
39
    "object": "translation"
40
}

This approach presents a straightforward way for readers to choose and apply the code example that best suits their needs for generating text completions using either Python, Go, Rust, JS, or cURL.