HetznerChatGenerator

Generate chat responses using models served by the Hetzner Inference API.

Key Features

• Connects to the Hetzner Inference API, which is compatible with the OpenAI Chat Completions format.
• Supports open-weight models such as Qwen/Qwen3.6-35B-A3B-FP8.
• Accepts multimodal inputs, including text and images in ChatMessage objects.
• Supports streaming responses through a configurable callback.
• Supports tool calling and structured output via JSON schema or Pydantic models.
• Configurable structured output (response_format) for enforcing a specific response shape.

Configuration

1. Drag the HetznerChatGenerator 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 Hetzner model you want to use (for example, Qwen/Qwen3.6-35B-A3B-FP8). For the current model list, query the /v1/models endpoint of the Hetzner Inference API.
   2. Create a secret with your Hetzner API token and set it as api_key. Use HETZNER_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

HetznerChatGenerator 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 chat_generator.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  HetznerChatGenerator:
    type: haystack_integrations.components.generators.hetzner.chat.chat_generator.HetznerChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - HETZNER_API_KEY
        strict: false
      model: Qwen/Qwen3.6-35B-A3B-FP8
      generation_kwargs:
        max_tokens: 1024
        temperature: 0.7

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.hetzner.chat.chat_generator.HetznerChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - HETZNER_API_KEY
        strict: false
      model: Qwen/Qwen3.6-35B-A3B-FP8
      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("HETZNER_API_KEY")	The Hetzner Inference API token.
model	str	Qwen/Qwen3.6-35B-A3B-FP8	The name of the model to use. Query /v1/models for the current list.
streaming_callback	Optional[Callable]	None	A callback function for streaming responses.
api_base_url	Optional[str]	https://inference.hetzner.com/api/v1	The Hetzner Inference API base URL.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional generation parameters such as max_tokens, temperature, top_p, and response_format.
tools	Optional[ToolsType]	None	A list of tools the model can use.
timeout	Optional[float]	None	Request timeout in seconds.
max_retries	Optional[int]	None	Maximum number of retries on API errors. Defaults to the OPENAI_MAX_RETRIES environment variable or five.
http_client_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for the underlying httpx.Client or httpx.AsyncClient.

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.

Related Information

• Pipeline Components
• Integrations Overview