1  ---
 2  title: "AnswerJoiner"
 3  id: answerjoiner
 4  slug: "/answerjoiner"
 5  description: "Merges multiple answers from different Generators into a single list."
 6  ---
 7  
 8  # AnswerJoiner
 9  
10  Merges multiple answers from different Generators into a single list.
11  
12  <div className="key-value-table">
13  
14  |  |  |
15  | --- | --- |
16  | **Most common position in a pipeline** | In query pipelines, after [Generators](../generators.mdx)  and, subsequently, components that return a list of answers such as [`AnswerBuilder`](../builders/answerbuilder.mdx)    |
17  | **Mandatory run variables**            | `answers`: A nested list of answers to be merged, received from the Generator. This input is `variadic`, meaning you can connect a variable number of components to it. |
18  | **Output variables**                   | `answers`: A merged list of answers                                                                                                                                     |
19  | **API reference**                      | [Joiners](/reference/joiners-api)                                                                                                                                              |
20  | **GitHub link**                        | https://github.com/deepset-ai/haystack/blob/main/haystack/components/joiners/answer_joiner.py                                                                         |
21  
22  </div>
23  
24  ## Overvew
25  
26  `AnswerJoiner` joins input lists of [`Answer`](../../concepts/data-classes.mdx#answer) objects from multiple connections and returns them as one list.
27  
28  You can optionally set the `top_k` parameter, which specifies the maximum number of answers to return. If you don’t set this parameter, the component returns all answers it receives.
29  
30  ## Usage
31  
32  In this simple example pipeline, the `AnswerJoiner` merges answers from two instances of Generators:
33  
34  ```python
35  from haystack.components.builders import AnswerBuilder
36  from haystack.components.joiners import AnswerJoiner
37  
38  from haystack.core.pipeline import Pipeline
39  
40  from haystack.components.generators.chat import OpenAIChatGenerator
41  from haystack.dataclasses import ChatMessage
42  
43  query = "What's Natural Language Processing?"
44  messages = [
45      ChatMessage.from_system(
46          "You are a helpful, respectful and honest assistant. Be super concise.",
47      ),
48      ChatMessage.from_user(query),
49  ]
50  
51  pipe = Pipeline()
52  pipe.add_component("gpt-4o", OpenAIChatGenerator(model="gpt-4o"))
53  pipe.add_component("llama", OpenAIChatGenerator(model="gpt-3.5-turbo"))
54  pipe.add_component("aba", AnswerBuilder())
55  pipe.add_component("abb", AnswerBuilder())
56  pipe.add_component("joiner", AnswerJoiner())
57  
58  pipe.connect("gpt-4o.replies", "aba")
59  pipe.connect("llama.replies", "abb")
60  pipe.connect("aba.answers", "joiner")
61  pipe.connect("abb.answers", "joiner")
62  
63  results = pipe.run(
64      data={
65          "gpt-4o": {"messages": messages},
66          "llama": {"messages": messages},
67          "aba": {"query": query},
68          "abb": {"query": query},
69      },
70  )
71  ```