/ docs-website / versioned_docs / version-2.18 / tools / ready-made-tools / githubissueviewertool.mdx
githubissueviewertool.mdx
1 --- 2 title: "GitHubIssueViewerTool" 3 id: githubissueviewertool 4 slug: "/githubissueviewertool" 5 description: "A Tool that allows Agents and ToolInvokers to fetch and parse GitHub issues into documents." 6 --- 7 8 # GitHubIssueViewerTool 9 10 A Tool that allows Agents and ToolInvokers to fetch and parse GitHub issues into documents. 11 12 | | | 13 | ----------------- | ---------------------------------------------------------------------------------------- | 14 | **API reference** | [Tools](/reference/tools-api) | 15 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/github | 16 17 ## Overview 18 19 `GitHubIssueViewerTool` wraps the [`GitHubIssueViewer`](../../pipeline-components/connectors/githubissueviewer.mdx) component, providing a tool interface for use in agent workflows and tool-based pipelines. 20 21 The tool takes a GitHub issue URL and returns a list of documents where: 22 23 - The first document contains the main issue content, 24 - Subsequent documents contain the issue comments (if any). 25 26 Each document includes rich metadata such as the issue title, number, state, creation date, author, and more. 27 28 ### Parameters 29 30 - `name` is _optional_ and defaults to "issue_viewer". Specifies the name of the tool. 31 - `description` is _optional_ and provides context to the LLM about what the tool does. 32 - `github_token` is _optional_ but recommended for private repositories or to avoid rate limiting. 33 - `raise_on_failure` is _optional_ and defaults to `True`. If False, errors are returned as documents instead of raising exceptions. 34 - `retry_attempts` is _optional_ and defaults to `2`. Number of retry attempts for failed requests. 35 36 ## Usage 37 38 Install the GitHub integration to use the `GitHubIssueViewerTool`: 39 40 ```shell 41 pip install github-haystack 42 ``` 43 44 :::note 45 Repository Placeholder 46 47 To run the following code snippets, you need to replace the `owner/repo` with your own GitHub repository name. 48 ::: 49 50 ### On its own 51 52 ```python 53 from haystack_integrations.tools.github import GitHubIssueViewerTool 54 55 tool = GitHubIssueViewerTool() 56 result = tool.invoke(url="https://github.com/deepset-ai/haystack/issues/123") 57 58 print(result) 59 ``` 60 61 ```bash 62 {'documents': [Document(id=3989459bbd8c2a8420a9ba7f3cd3cf79bb41d78bd0738882e57d509e1293c67a, content: 'sentence-transformers = 0.2.6.1 63 haystack = latest 64 farm = 0.4.3 latest branch 65 66 In the call to Emb...', meta: {'type': 'issue', 'title': 'SentenceTransformer no longer accepts \'gpu" as argument', 'number': 123, 'state': 'closed', 'created_at': '2020-05-28T04:49:31Z', 'updated_at': '2020-05-28T07:11:43Z', 'author': 'predoctech', 'url': 'https://github.com/deepset-ai/haystack/issues/123'}), Document(id=a8a56b9ad119244678804d5873b13da0784587773d8f839e07f644c4d02c167a, content: 'Thanks for reporting! 67 Fixed with #124 ', meta: {'type': 'comment', 'issue_number': 123, 'created_at': '2020-05-28T07:11:42Z', 'updated_at': '2020-05-28T07:11:42Z', 'author': 'tholor', 'url': 'https://github.com/deepset-ai/haystack/issues/123#issuecomment-635153940'})]} 68 ``` 69 70 ### With an Agent 71 72 You can use `GitHubIssueViewerTool` with the [Agent](../../pipeline-components/agents-1/agent.mdx) component. The Agent will automatically invoke the tool when needed to fetch GitHub issue information. 73 74 ```python 75 from haystack.components.generators.chat import OpenAIChatGenerator 76 from haystack.dataclasses import ChatMessage 77 from haystack.components.agents import Agent 78 from haystack_integrations.tools.github import GitHubIssueViewerTool 79 80 issue_tool = GitHubIssueViewerTool(name="github_issue_viewer") 81 82 agent = Agent( 83 chat_generator=OpenAIChatGenerator(), 84 tools=[issue_tool], 85 exit_conditions=["text"], 86 ) 87 88 agent.warm_up() 89 response = agent.run( 90 messages=[ 91 ChatMessage.from_user( 92 "Please analyze this GitHub issue and summarize the main problem: https://github.com/deepset-ai/haystack/issues/123", 93 ), 94 ], 95 ) 96 97 print(response["last_message"].text) 98 ``` 99 100 ```bash 101 The GitHub issue titled "SentenceTransformer no longer accepts 'gpu' as argument" (issue \#123) discusses a problem encountered when using the `EmbeddingRetriever()` function. The user reports that passing the argument `gpu=True` now causes an error because the method that processes this argument does not accept "gpu" anymore; instead, it previously accepted "cuda" without issues. 102 103 The user indicates that this change is problematic since it prevents users from instantiating the embedding model with GPU support, forcing them to default to using only the CPU for model execution. 104 105 The issue was later closed with a comment indicating it was fixed in another pull request (#124). 106 ```