Skip to content

laradocumenttranslator.mdx

Latest commit

 

History

History
111 lines (83 loc) · 4.54 KB

laradocumenttranslator.mdx

File metadata and controls

111 lines (83 loc) · 4.54 KB
title LaraDocumentTranslator
id laradocumenttranslator
slug /laradocumenttranslator
description This component translates the text content of Haystack documents using the Lara translation API.

LaraDocumentTranslator

This component translates the text content of Haystack documents using the Lara translation API.
Most common position in a pipeline After any component that produces documents, such as a Retriever or a Converter
Mandatory init variables access_key_id: Lara API access key ID. Can be set with LARA_ACCESS_KEY_ID env var.

access_key_secret: Lara API access key secret. Can be set with LARA_ACCESS_KEY_SECRET env var.
Mandatory run variables documents: A list of documents to be translated
Output variables documents: A list of translated documents
API reference Lara
GitHub link https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/lara

Overview

Lara is an adaptive translation AI by translated that combines the fluency and context handling of LLMs with low hallucination and latency. It adapts to domains at inference time using optional context, instructions, translation memories, and glossaries.

LaraDocumentTranslator takes a list of Haystack documents, translates their text content via the Lara API, and returns new documents containing the translations. The original document ID is preserved in each translated document's metadata under the original_document_id key.

Key features:

  • Automatic language detection: set source_lang to None and Lara auto-detects it.
  • Translation styles: choose "faithful", "fluid", or "creative" to control the tone.
  • Context and instructions: pass surrounding text or natural-language instructions to improve quality.
  • Translation memories and glossaries: supply memory or glossary IDs so Lara enforces consistent terminology.
  • Reasoning (Lara Think): enable multi-step linguistic analysis for higher-quality output.

Usage

Installation

To start using this integration with Haystack, install it with:

pip install lara-haystack

LaraDocumentTranslator needs Lara API credentials to work. It uses the LARA_ACCESS_KEY_ID and LARA_ACCESS_KEY_SECRET environment variables by default. Otherwise, you can pass them at initialization:

from haystack.utils import Secret
from haystack_integrations.components.translators.lara import LaraDocumentTranslator

translator = LaraDocumentTranslator(
    access_key_id=Secret.from_token("<your-access-key-id>"),
    access_key_secret=Secret.from_token("<your-access-key-secret>"),
    source_lang="en-US",
    target_lang="de-DE",
)

To get your Lara API credentials, sign up at laratranslate.com.

On its own

Remember to set the LARA_ACCESS_KEY_ID and LARA_ACCESS_KEY_SECRET environment variables or pass them in directly.

from haystack import Document
from haystack.utils import Secret
from haystack_integrations.components.translators.lara import LaraDocumentTranslator

translator = LaraDocumentTranslator(
    access_key_id=Secret.from_env_var("LARA_ACCESS_KEY_ID"),
    access_key_secret=Secret.from_env_var("LARA_ACCESS_KEY_SECRET"),
    source_lang="en-US",
    target_lang="de-DE",
)

doc = Document(content="Hello, world!")
result = translator.run(documents=[doc])
print(result["documents"][0].content)
# >> "Hallo, Welt!"

In a pipeline

Below is an example of the LaraDocumentTranslator in a pipeline that fetches a webpage, converts it to a document, and translates it from English to German.

from haystack import Pipeline
from haystack.components.converters import HTMLToDocument
from haystack.components.fetchers import LinkContentFetcher
from haystack_integrations.components.translators.lara import LaraDocumentTranslator

fetcher = LinkContentFetcher()
converter = HTMLToDocument()
translator = LaraDocumentTranslator(source_lang="en-US", target_lang="de-DE")

pipe = Pipeline()
pipe.add_component("fetcher", fetcher)
pipe.add_component("converter", converter)
pipe.add_component("translator", translator)

pipe.connect("fetcher", "converter")
pipe.connect("converter", "translator")

result = pipe.run(data={"fetcher": {"urls": ["https://haystack.deepset.ai/"]}})
translated_docs = result["translator"]["documents"]
for doc in translated_docs:
    print(doc.content)