AnthropicGenerator

Generate text using large language models (LLMs) by Anthropic.

Key Features

• Supports all Anthropic Claude models available through the Anthropic API.
• Accepts a text prompt and returns a list of generated replies.
• Provides a simplified string-based interface compared to the chat API.
• Supports streaming responses through a configurable callback function.
• Compatible with PromptBuilder for building structured prompts with documents.

info

Although Anthropic natively supports a much richer messaging API, this component intentionally simplifies it so that the main input and output interface is string-based. For more complete support, consider using AnthropicChatGenerator.

Configuration

Authentication

To use this component, connect Haystack Platform with Anthropic first. You need an Anthropic API key. For details, see Use Anthropic Models.

1. Drag the AnthropicGenerator component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name, for example claude-sonnet-4-20250514.
4. Go to the Advanced tab to configure the API key, generation parameters, and streaming callback.

Connections

AnthropicGenerator accepts a prompt string as input, along with optional generation_kwargs and streaming_callback.

Connect PromptBuilder to the prompt input to provide instructions with context. Connect the replies output to DeepsetAnswerBuilder to build final answers with references.

Usage Example

This is a RAG pipeline that uses Claude Sonnet 4:

components:
  retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.open_search_hybrid_retriever.OpenSearchHybridRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: ''
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return
      fuzziness: 0
      embedder:
        type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
        init_parameters:
          normalize_embeddings: true
          model: intfloat/multilingual-e5-base

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: svalabs/cross-electra-ms-marco-german-uncased
      top_k: 8

  meta_field_grouping_ranker:
    type: haystack.components.rankers.meta_field_grouping_ranker.MetaFieldGroupingRanker
    init_parameters:
      group_by: file_id
      subgroup_by:
      sort_docs_by: split_id

  prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      required_variables: "*"
      template: |-
        Du bist ein technischer Experte.
        Du beantwortest die Fragen wahrheitsgemäß auf Grundlage der vorgelegten Dokumente.
        Wenn die Antwort in mehreren Dokumenten enthalten ist, fasse diese zusammen.
        Ignoriere Dokumente, die keine Antwort auf die Frage enthalten.
        Antworte nur auf der Grundlage der vorgelegten Dokumente. Erfinde keine Fakten.
        Wenn in dem Dokument keine Informationen zu der Frage gefunden werden können, gib dies an.
        Verwende immer Verweise in der Form [NUMMER DES DOKUMENTS], wenn du Informationen aus einem Dokument verwendest, z. B. [3] für Dokument [3] .
        Nenne die Dokumente nie, sondern gebe nur eine Zahl in eckigen Klammern als Referenz an.
        Der Verweis darf sich nur auf die Nummer beziehen, die in eckigen Klammern hinter der Passage steht.
        Andernfalls verwende in deiner Antwort keine Klammern und gib NUR die Nummer des Dokuments an, ohne das Wort Dokument zu erwähnen.
        Gebe eine präzise, exakte und strukturierte Antwort ohne die Frage zu wiederholen.

        Hier sind die Dokumente:
        {%- if documents|length > 0 %}
        {%- for document in documents %}
        Dokument [{{ loop.index }}] :
        Name der Quelldatei: {{ document.meta.file_name }}
        {{ document.content }}
        {% endfor -%}
        {%- else %}
        Keine Dokumente gefunden.
        Sage "Es wurden leider keine passenden Dokumente gefunden, bitte passen sie die Filter an oder versuchen es mit einer veränderten Frage."
        {% endif %}

        Frage: {{ question }}
        Antwort:

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm
      # extract_xml_tags:  # uncomment to move thinking part into answer's meta
      # - thinking

  attachments_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      weights:
      top_k:
      sort_by_score: true

  AnthropicGenerator:
    type: haystack_integrations.components.generators.anthropic.generator.AnthropicGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - ANTHROPIC_API_KEY
        strict: false
      model: claude-sonnet-4-20250514
      streaming_callback:
      system_prompt:
      generation_kwargs:
  S3Downloader:
    type: haystack_integrations.components.downloaders.s3.s3_downloader.S3Downloader
    init_parameters:
      aws_access_key_id:
        type: env_var
        env_vars:
        - AWS_ACCESS_KEY_ID
        strict: false
      aws_secret_access_key:
        type: env_var
        env_vars:
        - AWS_SECRET_ACCESS_KEY
        strict: false
      aws_session_token:
        type: env_var
        env_vars:
        - AWS_SESSION_TOKEN
        strict: false
      aws_region_name:
        type: env_var
        env_vars:
        - AWS_DEFAULT_REGION
        strict: false
      aws_profile_name:
        type: env_var
        env_vars:
        - AWS_PROFILE
        strict: false
      boto3_config:
      file_root_path:
      file_extensions:
      file_name_meta_key: file_name
      max_workers: 32
      max_cache_size: 100
      s3_key_generation_function: deepset_cloud_custom_nodes.utils.storage.get_s3_key

connections:  # Defines how the components are connected
- sender: retriever.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: prompt_builder.prompt
  receiver: answer_builder.prompt
- sender: meta_field_grouping_ranker.documents
  receiver: attachments_joiner.documents
- sender: attachments_joiner.documents
  receiver: answer_builder.documents

- sender: attachments_joiner.documents
  receiver: prompt_builder.documents
- sender: prompt_builder.prompt
  receiver: AnthropicGenerator.prompt
- sender: AnthropicGenerator.replies
  receiver: answer_builder.replies
- sender: retriever.documents
  receiver: S3Downloader.documents
- sender: S3Downloader.documents
  receiver: attachments_joiner.documents

inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "retriever.query"
  - "ranker.query"
  - "prompt_builder.question"
  - "answer_builder.query"

  filters:  # These components will receive a potential query filter as input
  - "retriever.filters_bm25"
  - "retriever.filters_embedding"

outputs:  # Defines the output of your pipeline
  documents: "attachments_joiner.documents"  # The output of the pipeline is the retrieved documents
  answers: "answer_builder.answers"  # The output of the pipeline is the generated answers

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
prompt	str		The instructions for the model.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	An optional callback function to handle streaming chunks.

Outputs

Parameter	Type	Default	Description
replies	List[str]		A list of generated replies.
meta	List[Dict[str, Any]]		A list of metadata dictionaries for each reply.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var('ANTHROPIC_API_KEY')	The Anthropic API key.
model	str	claude-sonnet-4-20250514	The name of the Anthropic model to use.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	An optional callback function to handle streaming chunks.
system_prompt	Optional[str]	None	An optional system prompt to use for generation.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for generation.
timeout	Optional[float]	None	The timeout for request.
max_retries	Optional[int]	None	The maximum number of retries if a request fails.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
prompt	str		The prompt with instructions for the model.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for generation. For a complete list, see Anthropic API documentation.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	An optional callback function to handle streaming chunks.