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  |                                        |                                                                                                                                                                         |
13  | :------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
14  | **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)    |
15  | **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. |
16  | **Output variables**                   | “answers”: A merged list of answers                                                                                                                                     |
17  | **API reference**                      | [Joiners](/reference/joiners-api)                                                                                                                                              |
18  | **GitHub link**                        | https://github.com/deepset-ai/haystack/blob/main/haystack/components/joiners/answer_joiner.py                                                                         |
19  
20  ## Overvew
21  
22  `AnswerJoiner` joins input lists of [`Answer`](../../concepts/data-classes.mdx#answer) objects from multiple connections and returns them as one list.
23  
24  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.
25  
26  ## Usage
27  
28  In this simple example pipeline, the `AnswerJoiner` merges answers from two instances of Generators:
29  
30  ```python
31  from haystack.components.builders import AnswerBuilder
32  from haystack.components.joiners import AnswerJoiner
33  
34  from haystack.core.pipeline import Pipeline
35  
36  from haystack.components.generators.chat import OpenAIChatGenerator
37  from haystack.dataclasses import ChatMessage
38  
39  query = "What's Natural Language Processing?"
40  messages = [
41      ChatMessage.from_system(
42          "You are a helpful, respectful and honest assistant. Be super concise.",
43      ),
44      ChatMessage.from_user(query),
45  ]
46  
47  pipe = Pipeline()
48  pipe.add_component("gpt-4o", OpenAIChatGenerator(model="gpt-4o"))
49  pipe.add_component("llama", OpenAIChatGenerator(model="gpt-3.5-turbo"))
50  pipe.add_component("aba", AnswerBuilder())
51  pipe.add_component("abb", AnswerBuilder())
52  pipe.add_component("joiner", AnswerJoiner())
53  
54  pipe.connect("gpt-4o.replies", "aba")
55  pipe.connect("llama.replies", "abb")
56  pipe.connect("aba.answers", "joiner")
57  pipe.connect("abb.answers", "joiner")
58  
59  results = pipe.run(
60      data={
61          "gpt-4o": {"messages": messages},
62          "llama": {"messages": messages},
63          "aba": {"query": query},
64          "abb": {"query": query},
65      },
66  )
67  ```