BranchJoiner

Merge multiple branches of a pipeline into a single output.

Basic Information

• Type: haystack.components.joiners.branch.BranchJoiner
• Components it can connect with:
  • Routers: Receives outputs from conditional branches (for example, ConditionalRouter, TextLanguageRouter).

Inputs

Parameter	Type	Default	Description
**kwargs	Any		The input data. Must be of the type declared by type_ during initialization.

Outputs

Parameter	Type	Default	Description
--	--	--	The output is the first value BranchJoiner receives from connected components.

Overview

BranchJoiner merges multiple input branches of a pipeline into a single branch. It receives inputs of the same data type and forwards the first received value to its output. It handles one input of one data type at a time. You can declare the data type when configuring the component.

If the component receives more than one value for the input, it raises the following error: ValueError: BranchJoiner expects only one input, but <number of inputs> were received..

Common Use Cases

• Loop Handling: BranchJoiner helps close loops in pipelines. For example, if a pipeline component validates or modifies incoming data and produces an error-handling branch, BranchJoiner can merge both branches and send (or resend in the case of a loop) the data to the component that evaluates errors.

• Decision-Based Merging: BranchJoiner reconciles branches coming from Router components (such as ConditionalRouter, TextLanguageRouter). Suppose a TextLanguageRouter directs user queries to different retrievers based on the detected language. Each retriever processes its assigned query and passes the results to BranchJoiner, which consolidates them into a single output before passing them to the next component.

BranchJoiner can manage only one data type at a time. When creating BranchJoiner, you must specify the type of data it will receive and pass (for example, List[ChatMessage], str, List[Document]).

Usage Example

This example shows a pipeline where ConditionalRouter routes queries based on whether they contain a question mark (indicating a question vs. a statement), and BranchJoiner consolidates the outputs from different processing approaches.

components:
  ConditionalRouter:
    type: haystack.components.routers.conditional_router.ConditionalRouter
    init_parameters:
      routes:
      - condition: "{{ '?' in query }}"
        output: "{{ query }}"
        output_name: question
        output_type: str
      - condition: "{{ '?' not in query }}"
        output: "{{ query }}"
        output_name: statement
        output_type: str
  QuestionPromptBuilder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: "Provide a detailed answer to this question: {{ query }}"
  StatementPromptBuilder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: "Acknowledge and expand on this statement: {{ query }}"
  QuestionGenerator:
    type: haystack.components.generators.openai.OpenAIGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - OPENAI_API_KEY
        strict: false
      model: gpt-4o-mini
      generation_kwargs:
        temperature: 0.3
        max_tokens: 500
  StatementGenerator:
    type: haystack.components.generators.openai.OpenAIGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - OPENAI_API_KEY
        strict: false
      model: gpt-4o-mini
      generation_kwargs:
        temperature: 0.7
        max_tokens: 200
  BranchJoiner:
    type: haystack.components.joiners.branch.BranchJoiner
    init_parameters:
      type_: list[str]

connections:
- sender: ConditionalRouter.question
  receiver: QuestionPromptBuilder.query
- sender: ConditionalRouter.statement
  receiver: StatementPromptBuilder.query
- sender: QuestionPromptBuilder.prompt
  receiver: QuestionGenerator.prompt
- sender: StatementPromptBuilder.prompt
  receiver: StatementGenerator.prompt
- sender: QuestionGenerator.replies
  receiver: BranchJoiner.value
- sender: StatementGenerator.replies
  receiver: BranchJoiner.value

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - ConditionalRouter.query

outputs:
  replies: BranchJoiner.value

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
type_	Type		The expected data type of inputs and outputs.

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
**kwargs	Any		The input data. Must be of the type declared by type_ during initialization.