GitHubRepoViewer

Navigate and fetch content from GitHub repositories.

Basic Information

• Type: haystack_integrations.components.connectors.github.repo_viewer.GitHubRepoViewer
• Components it can connect with:
  • Input: Receives repository path and branch as input.
  • Converters: Sends fetched documents to other components for processing.
  • ChatPromptBuilder: Sends documents as context for LLM-based analysis.

Inputs

Parameter	Type	Default	Description
repo	Optional[str]	None	Repository in format "owner/repo".
path	str		Path within repository (default: root).
branch	Optional[str]	None	Git reference (branch, tag, commit) to use.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		List of documents containing repository content.

Overview

GitHubRepoViewer navigates and fetches content from GitHub repositories. It returns different document structures based on the path type:

For directories:

• Returns a list of Documents, one for each item
• Each Document's content is the item name
• Full path and metadata stored in Document.meta

For files:

• Returns a single Document
• Document's content is the file content
• Full path and metadata stored in Document.meta

For errors:

• Returns a single Document with error message as content
• Document's meta contains type="error"

Authorization

To use this component, you must create a secret with your GitHub personal access token. Type GITHUB_TOKEN as the secret key. For detailed instructions on creating secrets, see Create Secrets.

Usage Example

This pipeline uses GitHubRepoViewer to fetch repository content for analysis:

components:
  GitHubRepoViewer:
    type: haystack_integrations.components.connectors.github.repo_viewer.GitHubRepoViewer
    init_parameters:
      github_token:
        type: env_var
        env_vars:
          - GITHUB_TOKEN
        strict: false
      raise_on_failure: true
      max_file_size: 1000000
      repo:
      branch: main

  ChatPromptBuilder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      template:
        - role: system
          content: "You are a code analysis assistant. Analyze the provided repository content and answer questions about the code."
        - role: user
          content: "Repository content:\n{% for doc in documents %}\nFile: {{ doc.meta.path }}\n{{ doc.content }}\n{% endfor %}\n\nQuestion: {{ query }}"

  OpenAIChatGenerator:
    type: haystack.components.generators.chat.openai.OpenAIChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
          - OPENAI_API_KEY
        strict: false
      model: gpt-4o-mini

  OutputAdapter:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: '{{ replies[0] }}'
      output_type: List[str]

  AnswerBuilder:
    type: haystack.components.builders.answer_builder.AnswerBuilder
    init_parameters:
      pattern:
      reference_pattern:

connections:
  - sender: GitHubRepoViewer.documents
    receiver: ChatPromptBuilder.documents
  - sender: ChatPromptBuilder.prompt
    receiver: OpenAIChatGenerator.messages
  - sender: OpenAIChatGenerator.replies
    receiver: OutputAdapter.replies
  - sender: OutputAdapter.output
    receiver: AnswerBuilder.replies
  - sender: GitHubRepoViewer.documents
    receiver: AnswerBuilder.documents

inputs:
  query:
    - ChatPromptBuilder.query
    - AnswerBuilder.query
  repo:
    - GitHubRepoViewer.repo
  path:
    - GitHubRepoViewer.path
  branch:
    - GitHubRepoViewer.branch

outputs:
  answers: AnswerBuilder.answers

max_runs_per_component: 100

metadata: {}

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
github_token	Optional[Secret]	None	GitHub personal access token for API authentication.
raise_on_failure	bool	True	If True, raises exceptions on API errors.
max_file_size	int	1000000	Maximum file size in bytes to fetch (default: 1MB).
repo	Optional[str]	None	Repository in format "owner/repo".
branch	str	main	Git reference (branch, tag, commit) to use.

Run Method Parameters

These are the parameters you can configure for the run() method. You can pass these parameters at query time through the API, in Playground, or when running a job.

Parameter	Type	Default	Description
repo	Optional[str]	None	Repository in format "owner/repo".
path	str		Path within repository (default: root).
branch	Optional[str]	None	Git reference (branch, tag, commit) to use.