Prerequisites

You need an active DeepL account and a DeepL API key. For guidance on how to obtain it, see API Key for DeepL's API.

Use DeepL

First, connect deepset Cloud to DeepL through the Connections page:

Click your initials in the top right corner and select Connections.
Click Connect next to the provider.
Enter your user access token and submit it.

Then, add the DeepsetDeepLDocumentTranslator component to your query pipeline.

Usage Examples

This is an example of how to use DeepL in your pipeline

 components:
    query_embedder:
      type: haystack.components.embedders.sentence_transformers_text_embedder.SentenceTransformersTextEmbedder
      init_parameters:
        model: "intfloat/multilingual-e5-base"
        device: null
  
    embedding_retriever: # Selects the most similar documents from the document store
      type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
      init_parameters:
        document_store:
          init_parameters:
            use_ssl: True
            verify_certs: False
            http_auth:
              - "${OPENSEARCH_USER}"
              - "${OPENSEARCH_PASSWORD}"
          type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        top_k: 20 # The number of results to return
  
    ranker:
      type: haystack.components.rankers.transformers_similarity.TransformersSimilarityRanker
      init_parameters:
        model: "jeffwan/mmarco-mMiniLMv2-L12-H384-v1"
        top_k: 20
        device: null
        model_kwargs:
          torch_dtype: "torch.float16"
  
    deepl_translator:
      type: deepset_cloud_custom_nodes.converters.deepl_document_translator.DeepsetDeepLDocumentTranslator
      # For more information about DeepL supported languages, see https://developers.deepl.com/docs/resources/supported-languages
      init_parameters:
        api_key: {"type": "env_var", "env_vars": ["DEEPL_API_KEY"], "strict": False}
        target_languages: ["DE"] # Translate documents into German
        source_language: null # Auto-detects the source language when set to "null"
        preserve_formatting: true # Prevent automatic correction of formatting
  
  connections:  # Defines how the components are connected
  - sender: query_embedder.embedding
    receiver: embedding_retriever.query_embedding
  - sender: embedding_retriever.documents
    receiver: ranker.documents
  - sender: ranker.documents
    receiver: deepl_translator.documents
  
  max_loops_allowed: 100
  
  inputs:  # Define the inputs for your pipeline
    query:  # These components will receive the query as input
    - "query_embedder.text"
    - "ranker.query"
  
    filters:  # These components will receive a potential query filter as input
    - "embedding_retriever.filters"
  
  outputs:  # Defines the output of your pipeline
    documents: "deepl_translator.translated_documents"  # The output of the pipeline is the retrieved documents translated into German.