1  ---
  2  title: "GitHubIssueCommenter"
  3  id: githubissuecommenter
  4  slug: "/githubissuecommenter"
  5  description: "This component posts comments to GitHub issues using the GitHub API."
  6  ---
  7  
  8  # GitHubIssueCommenter
  9  
 10  This component posts comments to GitHub issues using the GitHub API.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | After a Chat Generator that provides the comment text to post or right at the beginning of a pipeline |
 17  | **Mandatory init variables** | `github_token`: GitHub personal access token. Can be set with `GITHUB_TOKEN` env var. |
 18  | **Mandatory run variables** | `url`: A GitHub issue URL  <br /> <br />`comment`: Comment text to post |
 19  | **Output variables** | `success`: Boolean indicating whether the comment was posted successfully |
 20  | **API reference** | [GitHub](/reference/integrations-github) |
 21  | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/github |
 22  
 23  </div>
 24  
 25  ## Overview
 26  
 27  `GitHubIssueCommenter` takes a GitHub issue URL and comment text, then posts the comment to the specified issue.
 28  
 29  The component requires authentication with a GitHub personal access token since posting comments is an authenticated operation.
 30  
 31  ### Authorization
 32  
 33  This component requires GitHub authentication with a personal access token. You can set the token using the `GITHUB_TOKEN` environment variable, or pass it directly during initialization via the `github_token` parameter.
 34  
 35  To create a personal access token, visit [GitHub's token settings page](https://github.com/settings/tokens). Make sure to grant the appropriate permissions for repository access and issue management.
 36  
 37  ### Installation
 38  
 39  Install the GitHub integration with pip:
 40  
 41  ```shell
 42  pip install github-haystack
 43  ```
 44  
 45  ## Usage
 46  
 47  :::info[Repository Placeholder]
 48  
 49  To run the following code snippets, you need to replace the `owner/repo` with your own GitHub repository name.
 50  :::
 51  
 52  ### On its own
 53  
 54  Basic usage with environment variable authentication:
 55  
 56  ```python
 57  from haystack_integrations.components.connectors.github import GitHubIssueCommenter
 58  
 59  commenter = GitHubIssueCommenter()
 60  result = commenter.run(
 61      url="https://github.com/owner/repo/issues/123",
 62      comment="Thanks for reporting this issue! We'll look into it.",
 63  )
 64  
 65  print(result)
 66  ```
 67  
 68  ```bash
 69  {'success': True}
 70  ```
 71  
 72  ### In a pipeline
 73  
 74  The following pipeline analyzes a GitHub issue and automatically posts a response:
 75  
 76  ```python
 77  from haystack import Pipeline
 78  from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder
 79  from haystack.components.generators.chat import OpenAIChatGenerator
 80  from haystack.dataclasses import ChatMessage
 81  from haystack_integrations.components.connectors.github import (
 82      GitHubIssueViewer,
 83      GitHubIssueCommenter,
 84  )
 85  
 86  issue_viewer = GitHubIssueViewer()
 87  issue_commenter = GitHubIssueCommenter()
 88  
 89  prompt_template = [
 90      ChatMessage.from_system(
 91          "You are a helpful assistant that analyzes GitHub issues and creates appropriate responses.",
 92      ),
 93      ChatMessage.from_user(
 94          "Based on the following GitHub issue:\n"
 95          "{% for document in documents %}"
 96          "{% if document.meta.type == 'issue' %}"
 97          "**Issue Title:** {{ document.meta.title }}\n"
 98          "**Issue Description:** {{ document.content }}\n"
 99          "{% endif %}"
100          "{% endfor %}\n"
101          "Generate a helpful response comment for this issue. Keep it professional and concise.",
102      ),
103  ]
104  
105  prompt_builder = ChatPromptBuilder(template=prompt_template, required_variables="*")
106  llm = OpenAIChatGenerator(model="gpt-4o-mini")
107  
108  pipeline = Pipeline()
109  pipeline.add_component("issue_viewer", issue_viewer)
110  pipeline.add_component("prompt_builder", prompt_builder)
111  pipeline.add_component("llm", llm)
112  pipeline.add_component("issue_commenter", issue_commenter)
113  
114  pipeline.connect("issue_viewer.documents", "prompt_builder.documents")
115  pipeline.connect("prompt_builder.prompt", "llm.messages")
116  pipeline.connect("llm.replies", "issue_commenter.comment")
117  
118  issue_url = "https://github.com/owner/repo/issues/123"
119  result = pipeline.run(
120      data={"issue_viewer": {"url": issue_url}, "issue_commenter": {"url": issue_url}},
121  )
122  
123  print(f"Comment posted successfully: {result['issue_commenter']['success']}")
124  ```
125  
126  ```
127  Comment posted successfully: True
128  ```