1  ---
  2  title: "LaraDocumentTranslator"
  3  id: laradocumenttranslator
  4  slug: "/laradocumenttranslator"
  5  description: "This component translates the text content of Haystack documents using the Lara translation API."
  6  ---
  7  
  8  # LaraDocumentTranslator
  9  
 10  This component translates the text content of Haystack documents using the Lara translation API.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | After any component that produces documents, such as a Retriever or a Converter |
 17  | **Mandatory init variables** | `access_key_id`: Lara API access key ID. Can be set with `LARA_ACCESS_KEY_ID` env var.  <br /> <br />`access_key_secret`: Lara API access key secret. Can be set with `LARA_ACCESS_KEY_SECRET` env var. |
 18  | **Mandatory run variables** | `documents`: A list of documents to be translated |
 19  | **Output variables** | `documents`: A list of translated documents |
 20  | **API reference** | [Lara](/reference/integrations-lara) |
 21  | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/lara |
 22  
 23  </div>
 24  
 25  ## Overview
 26  
 27  [Lara](https://developers.laratranslate.com/docs/introduction) is an adaptive translation AI by [translated](https://translated.com/) 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.
 28  
 29  `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.
 30  
 31  Key features:
 32  
 33  - **Automatic language detection**: set `source_lang` to `None` and Lara auto-detects it.
 34  - **Translation styles**: choose `"faithful"`, `"fluid"`, or `"creative"` to control the tone.
 35  - **Context and instructions**: pass surrounding text or natural-language instructions to improve quality.
 36  - **Translation memories and glossaries**: supply memory or glossary IDs so Lara enforces consistent terminology.
 37  - **Reasoning (Lara Think)**: enable multi-step linguistic analysis for higher-quality output.
 38  
 39  ## Usage
 40  ### Installation
 41  
 42  To start using this integration with Haystack, install it with:
 43  
 44  ```shell
 45  pip install lara-haystack
 46  ```
 47  
 48  `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:
 49  
 50  ```python
 51  from haystack.utils import Secret
 52  from haystack_integrations.components.translators.lara import LaraDocumentTranslator
 53  
 54  translator = LaraDocumentTranslator(
 55      access_key_id=Secret.from_token("<your-access-key-id>"),
 56      access_key_secret=Secret.from_token("<your-access-key-secret>"),
 57      source_lang="en-US",
 58      target_lang="de-DE",
 59  )
 60  ```
 61  
 62  To get your Lara API credentials, sign up at [laratranslate.com](https://laratranslate.com/).
 63  ### On its own
 64  
 65  Remember to set the `LARA_ACCESS_KEY_ID` and `LARA_ACCESS_KEY_SECRET` environment variables or pass them in directly.
 66  
 67  ```python
 68  from haystack import Document
 69  from haystack.utils import Secret
 70  from haystack_integrations.components.translators.lara import LaraDocumentTranslator
 71  
 72  translator = LaraDocumentTranslator(
 73      access_key_id=Secret.from_env_var("LARA_ACCESS_KEY_ID"),
 74      access_key_secret=Secret.from_env_var("LARA_ACCESS_KEY_SECRET"),
 75      source_lang="en-US",
 76      target_lang="de-DE",
 77  )
 78  
 79  doc = Document(content="Hello, world!")
 80  result = translator.run(documents=[doc])
 81  print(result["documents"][0].content)
 82  # >> "Hallo, Welt!"
 83  ```
 84  
 85  ### In a pipeline
 86  
 87  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.
 88  
 89  ```python
 90  from haystack import Pipeline
 91  from haystack.components.converters import HTMLToDocument
 92  from haystack.components.fetchers import LinkContentFetcher
 93  from haystack_integrations.components.translators.lara import LaraDocumentTranslator
 94  
 95  fetcher = LinkContentFetcher()
 96  converter = HTMLToDocument()
 97  translator = LaraDocumentTranslator(source_lang="en-US", target_lang="de-DE")
 98  
 99  pipe = Pipeline()
100  pipe.add_component("fetcher", fetcher)
101  pipe.add_component("converter", converter)
102  pipe.add_component("translator", translator)
103  
104  pipe.connect("fetcher", "converter")
105  pipe.connect("converter", "translator")
106  
107  result = pipe.run(data={"fetcher": {"urls": ["https://haystack.deepset.ai/"]}})
108  translated_docs = result["translator"]["documents"]
109  for doc in translated_docs:
110      print(doc.content)
111  ```