AnthropicFoundryChatGenerator

Generate chat responses using Claude models deployed on Azure Foundry.

Key Features

• Connects to Claude models (Opus, Sonnet, Haiku) through your Azure Foundry resource.
• Accepts and returns messages in ChatMessage format.
• Supports streaming responses through a configurable callback.
• Supports tool calling for agentic workflows.
• Supports Anthropic server-side tools such as web search and code execution.
• Supports Azure AD token authentication as an alternative to API keys.

Configuration

Add Workspace-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Workspace>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Organization>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

1. Drag the AnthropicFoundryChatGenerator component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Set the model to the Claude model name that matches your Foundry deployment (for example, claude-sonnet-4-5).
   2. Set the resource to your Azure Foundry resource name, or set endpoint to the full Foundry endpoint URL.
   3. Create a secret with your Foundry API key and set it as api_key. Use ANTHROPIC_FOUNDRY_API_KEY as the environment variable name. For instructions, see Create Secrets.
4. Go to the Advanced tab to configure generation_kwargs, timeout, and max_retries.

Connections

AnthropicFoundryChatGenerator receives a list of ChatMessage objects, typically from PromptBuilder or ChatPromptBuilder. It outputs a list of reply ChatMessage objects you can connect to AnswerBuilder or other downstream components.

Source Code

To check this component's source code, open foundry_chat_generator.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  AnthropicFoundryChatGenerator:
    type: haystack_integrations.components.generators.anthropic.chat.foundry_chat_generator.AnthropicFoundryChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - ANTHROPIC_FOUNDRY_API_KEY
        strict: false
      resource: my-foundry-resource
      model: claude-sonnet-4-5
      generation_kwargs:
        max_tokens: 1024

Using the Component in a Pipeline

# haystack-pipeline
components:
  prompt_builder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      required_variables: "*"
      template:
      - role: user
        content: "Answer the following question: {{ question }}"

  llm:
    type: haystack_integrations.components.generators.anthropic.chat.foundry_chat_generator.AnthropicFoundryChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - ANTHROPIC_FOUNDRY_API_KEY
        strict: false
      resource: my-foundry-resource
      model: claude-sonnet-4-5
      generation_kwargs:
        max_tokens: 1024

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

connections:
- sender: prompt_builder.prompt
  receiver: llm.messages
- sender: llm.replies
  receiver: answer_builder.replies

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - answer_builder.query
  - prompt_builder.question

outputs:
  answers: answer_builder.answers

Parameters

Inputs

Parameter	Type	Description
messages	List[ChatMessage]	A list of chat messages representing the conversation so far.

Outputs

Parameter	Type	Description
replies	List[ChatMessage]	A list of generated reply messages from the model.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var("ANTHROPIC_FOUNDRY_API_KEY")	The Foundry API key. Can be None when using azure_ad_token_provider.
resource	Optional[str]	None	The Azure Foundry resource name. Can also be set via the ANTHROPIC_FOUNDRY_RESOURCE environment variable. Either resource or endpoint must be provided.
endpoint	Optional[str]	None	The full Foundry endpoint URL (for example, https://your-resource.openai.azure.com/anthropic). Either resource or endpoint must be provided.
model	str	claude-sonnet-4-5	The Claude model name to use, which must match your Foundry deployment.
streaming_callback	Optional[Callable]	None	A callback function for streaming responses.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional generation parameters such as max_tokens, temperature, top_p, top_k, stop_sequences, and system.
ignore_tools_thinking_messages	bool	True	Whether to suppress chain-of-thought thinking messages from tool use responses.
tools	Optional[List[Tool]]	None	A list of tools the model can use.
anthropic_server_tools	Optional[List[Dict]]	None	Native Anthropic server-side tools (for example, {"type": "web_search_20250305"}).
timeout	Optional[float]	None	Request timeout in seconds.
max_retries	Optional[int]	None	Maximum number of retries on API errors.
azure_ad_token_provider	Optional[Callable]	None	A function that returns an Azure AD token for authentication. Use instead of api_key for enhanced security.

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
messages	List[ChatMessage]		A list of chat messages representing the conversation.
streaming_callback	Optional[Callable]	None	A callback function to override the init-time streaming callback.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional generation parameters to override init-time values.
tools	Optional[List[Tool]]	None	Tools to make available to the model, overriding init-time tools.

Related Information

• AnthropicChatGenerator
• Pipeline Components