1  ---
  2  title: "ListJoiner"
  3  id: listjoiner
  4  slug: "/listjoiner"
  5  description: "A component that joins multiple lists into a single flat list."
  6  ---
  7  
  8  # ListJoiner
  9  
 10  A component that joins multiple lists into a single flat list.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | In indexing and query pipelines, after components that return lists of documents such as multiple [Retrievers](../retrievers.mdx) or multiple [Converters](../converters.mdx) |
 17  | **Mandatory run variables**            | `values`: The dictionary of lists to be joined                                                                                                                              |
 18  | **Output variables**                   | `values`: A dictionary with a `values` key containing the joined list                                                                                                       |
 19  | **API reference**                      | [Joiners](/reference/joiners-api)                                                                                                                                                  |
 20  | **GitHub link**                        | https://github.com/deepset-ai/haystack/blob/main/haystack/components/joiners/list_joiner.py                                                                               |
 21  
 22  </div>
 23  
 24  ## Overview
 25  
 26  The `ListJoiner` component combines multiple lists into one list. It is useful for combining multiple lists from different pipeline components, merging LLM responses, handling multi-step data processing, and gathering data from different sources into one list.
 27  
 28  The items stay in order based on when each input list was processed in a pipeline.
 29  
 30  You can optionally specify a `list_type_` parameter to set the expected type of the lists being joined (for example, `List[ChatMessage]`). If not set, `ListJoiner` will accept lists containing mixed data types.
 31  
 32  ## Usage
 33  
 34  ### On its own
 35  
 36  ```python
 37  from haystack.components.joiners import ListJoiner
 38  
 39  list1 = ["Hello", "world"]
 40  list2 = ["This", "is", "Haystack"]
 41  list3 = ["ListJoiner", "Example"]
 42  
 43  joiner = ListJoiner()
 44  
 45  result = joiner.run(values=[list1, list2, list3])
 46  
 47  print(result["values"])
 48  ```
 49  
 50  ### In a pipeline
 51  
 52  ```python
 53  from haystack.components.builders import ChatPromptBuilder
 54  from haystack.components.generators.chat import OpenAIChatGenerator
 55  from haystack.dataclasses import ChatMessage
 56  from haystack import Pipeline
 57  from haystack.components.joiners import ListJoiner
 58  from typing import List
 59  
 60  user_message = [
 61      ChatMessage.from_user("Give a brief answer the following question: {{query}}"),
 62  ]
 63  
 64  feedback_prompt = """
 65      You are given a question and an answer.
 66      Your task is to provide a score and a brief feedback on the answer.
 67      Question: {{query}}
 68      Answer: {{response}}
 69      """
 70  feedback_message = [ChatMessage.from_system(feedback_prompt)]
 71  
 72  prompt_builder = ChatPromptBuilder(template=user_message)
 73  feedback_prompt_builder = ChatPromptBuilder(template=feedback_message)
 74  llm = OpenAIChatGenerator(model="gpt-4o-mini")
 75  feedback_llm = OpenAIChatGenerator(model="gpt-4o-mini")
 76  
 77  pipe = Pipeline()
 78  pipe.add_component("prompt_builder", prompt_builder)
 79  pipe.add_component("llm", llm)
 80  pipe.add_component("feedback_prompt_builder", feedback_prompt_builder)
 81  pipe.add_component("feedback_llm", feedback_llm)
 82  pipe.add_component("list_joiner", ListJoiner(List[ChatMessage]))
 83  
 84  pipe.connect("prompt_builder.prompt", "llm.messages")
 85  pipe.connect("prompt_builder.prompt", "list_joiner")
 86  pipe.connect("llm.replies", "list_joiner")
 87  pipe.connect("llm.replies", "feedback_prompt_builder.response")
 88  pipe.connect("feedback_prompt_builder.prompt", "feedback_llm.messages")
 89  pipe.connect("feedback_llm.replies", "list_joiner")
 90  
 91  query = "What is nuclear physics?"
 92  ans = pipe.run(
 93      data={
 94          "prompt_builder": {"template_variables": {"query": query}},
 95          "feedback_prompt_builder": {"template_variables": {"query": query}},
 96      },
 97  )
 98  
 99  print(ans["list_joiner"]["values"])
100  ```