Confluence Document Loader

​

Node Details

• Name: confluence
• Type: Document
• Version: 1.0
• Category: Document Loaders

​

Credentials

The node requires one of the following credential types:

• confluenceCloudApi
• confluenceServerDCApi

​

Input Parameters

1. Text Splitter (optional)

   • Type: TextSplitter
   • Description: A text splitter to break down large documents into smaller chunks.

2. Base URL (required)

   • Type: string
   • Description: The base URL of your Confluence instance.
   • Example: https://example.atlassian.net/wiki

3. Space Key (required)

   • Type: string
   • Description: The key of the Confluence space to load documents from.
   • Example: ~EXAMPLE362906de5d343d49dcdbae5dEXAMPLE

4. Limit (optional)

   • Type: number
   • Default: 0
   • Description: The maximum number of pages to load.

5. Additional Metadata (optional)

   • Type: JSON
   • Description: Additional metadata to be added to the extracted documents.

6. Omit Metadata Keys (optional)

   • Type: string
   • Description: A comma-separated list of metadata keys to omit from the extracted documents. Use * to omit all metadata keys except those specified in Additional Metadata.

​

Functionality

1. The node authenticates with Confluence using either Cloud or Server/Data Center credentials.
2. It loads pages from the specified Confluence space.
3. If a text splitter is provided, it splits the loaded documents.
4. Additional metadata is added to the documents if specified.
5. Metadata keys are omitted based on the “Omit Metadata Keys” input.

​

Output

The node outputs an array of document objects, each containing:

• Page content
• Metadata (original or modified based on inputs)

​

Use Cases

• Extracting knowledge base content from Confluence for processing in AI models
• Integrating Confluence documentation into chatbots or search systems
• Analyzing or summarizing Confluence content programmatically

​

Notes

• The node supports both Confluence Cloud and Confluence Server/Data Center APIs.
• Users should be cautious with the ‘limit’ parameter to avoid overloading their Confluence instance or exceeding API rate limits.
• The text splitter can be useful for breaking down large Confluence pages into more manageable chunks for processing.