GitHub

Use the GitHub Connector to ingest repository files and optionally issues from a GitHub repository into the mAItion knowledge base.

What It Does

fetches files from a GitHub repository at a given branch or commit
optionally fetches repository issues, with label filtering
converts file and issue content to Markdown for indexing
runs ingestion on configurable schedules

Authentication

Two authentication methods are supported (mutually exclusive):

Personal Access Token (personal_token): a GitHub PAT with access to the target repository.
GitHub App (github_app_id + github_app_installation_id + github_app_private_key): all three fields are required together when using GitHub App authentication.

Minimum permissions:

Repository contents: read — required for both PAT and GitHub App auth, to fetch repository files.
Issues: read — required in addition to the above when include_issues is true.
For GitHub App auth, the app installation must include the target repository.

Environment Variables

Set these in .env.rag:

GITHUB1_OWNER (required): repository owner or organization
GITHUB1_REPO (required): repository name
GITHUB1_PERSONAL_TOKEN (required, unless using GitHub App auth): GitHub Personal Access Token
GITHUB1_APP_ID, GITHUB1_APP_INSTALLATION_ID, GITHUB1_APP_PRIVATE_KEY (required together, alternative to GITHUB1_PERSONAL_TOKEN): GitHub App credentials
GITHUB1_SCHEDULES (optional): ingestion interval in seconds (default is 3600)

`config.yaml` Example

sources:
  - type: "github"
    name: "github1"
    enabled: true  # optional, default: true
    config:
      personal_token: "${GITHUB1_PERSONAL_TOKEN}"
      # GitHub App auth (mutually exclusive with personal_token):
      #github_app_id: "${GITHUB1_APP_ID}"
      #github_app_installation_id: "${GITHUB1_APP_INSTALLATION_ID}"
      #github_app_private_key: "${GITHUB1_APP_PRIVATE_KEY}"
      owner: "${GITHUB1_OWNER}"
      repo: "${GITHUB1_REPO}"
      branch: "main"                    # optional, default "main" (mutually exclusive with commit_sha)
      #commit_sha: ""                   # optional (mutually exclusive with branch)
      include_extensions: "md,py"       # optional, comma-separated (mutually exclusive with exclude_extensions)
      #exclude_extensions: ""           # optional (mutually exclusive with include_extensions)
      #include_directories: ""          # optional, comma-separated (mutually exclusive with exclude_directories)
      #exclude_directories: ""          # optional (mutually exclusive with include_directories)
      include_issues: false             # optional, default false
      #include_issues_labels: ""        # optional, comma-separated (mutually exclusive with exclude_issues_labels)
      #exclude_issues_labels: ""        # optional (mutually exclusive with include_issues_labels)
      concurrent_requests: 5            # optional, default 5
      schedules: "${GITHUB1_SCHEDULES}"

`.env.rag` Example

GITHUB1_PERSONAL_TOKEN=your-personal-access-token
# GitHub App auth (alternative to personal token):
#GITHUB1_APP_ID=
#GITHUB1_APP_INSTALLATION_ID=
#GITHUB1_APP_PRIVATE_KEY=
GITHUB1_OWNER=your-org-or-username
GITHUB1_REPO=your-repo-name
GITHUB1_SCHEDULES=3600

Configuration Reference

Field	Required	Default	Description
`enabled`	no	`true`	Set to `false` to skip this source entirely
`personal_token`	yes, unless using GitHub App auth	—	GitHub Personal Access Token (mutually exclusive with GitHub App credentials)
`github_app_id`	yes, when using GitHub App auth	—	GitHub App ID (required together with `github_app_installation_id` and `github_app_private_key`)
`github_app_installation_id`	yes, when using GitHub App auth	—	GitHub App installation ID
`github_app_private_key`	yes, when using GitHub App auth	—	GitHub App private key
`owner`	yes	—	Repository owner or organization
`repo`	yes	—	Repository name
`branch`	no	`main`	Branch to ingest from (mutually exclusive with `commit_sha`)
`commit_sha`	no	—	Commit SHA to ingest from (mutually exclusive with `branch`)
`include_extensions`	no	—	Comma-separated file extensions to include, e.g. `md,py` (mutually exclusive with `exclude_extensions`)
`exclude_extensions`	no	—	Comma-separated file extensions to exclude (mutually exclusive with `include_extensions`)
`include_directories`	no	—	Comma-separated directories to include (mutually exclusive with `exclude_directories`)
`exclude_directories`	no	—	Comma-separated directories to exclude (mutually exclusive with `include_directories`)
`include_issues`	no	`false`	Whether to also ingest repository issues
`include_issues_labels`	no	—	Comma-separated issue labels to include (mutually exclusive with `exclude_issues_labels`)
`exclude_issues_labels`	no	—	Comma-separated issue labels to exclude (mutually exclusive with `include_issues_labels`)
`concurrent_requests`	no	`5`	Number of concurrent API requests
`schedules`	no	`3600`	Ingestion interval in seconds

Multiple GitHub Sources

Add more sources entries (github2, github3, etc) with separate env vars per source.

Getting started

Features

Connectors

Tools

Configuration

What It Does

Authentication

Environment Variables

`config.yaml` Example

`.env.rag` Example

Configuration Reference

Multiple GitHub Sources

​What It Does

​Authentication

​Environment Variables

​config.yaml Example

​.env.rag Example

​Configuration Reference

​Multiple GitHub Sources

What It Does

Authentication

Environment Variables

`config.yaml` Example

`.env.rag` Example

Configuration Reference

Multiple GitHub Sources