Confluence Collection

SearchBlox provides a crawler that lets you index pages and blog posts from selected Confluence spaces. You can create a Confluence Collection using the steps below.

Creating Confluence Collection

You can create a Confluence Collection by following these steps:

• Log in to the Admin Console, go to the Collections tab, and click Create a New Collection or the "+" icon.

• Select Confluence Collection as the Collection Type.

• Enter a unique name for the collection (e.g., Confluence).

• Enable or disable RAG based on your requirement. Enable it if you want ChatBot or Hybrid RAG search.

• Choose whether the collection should be Private or Public, and set Collection Encryption as needed.

• Select the content language (choose another language if it’s not English).

• Click Save to create the collection.

• After the collection is created, you will automatically be taken to the Authentication tab.

---

Settings Tab

• Provide the apiToken, Username and atlassianDomain.
• Choose the settings for Generate Using LLM and Hybrid Search.

• Click on Save and Test Connection.

Spaces Tab

Once authentication is successful, you will be taken to the Spaces tab, where you can see all the Spaces from your Confluence account.

Configure Spaces

• Select the Spaces that need to be indexed (ensure the user has access to those Spaces), then click Save.
• You can see all the selected Spaces, and you can also deselect any Space if needed.
• After selecting or deselecting Spaces, click Save to confirm the changes.

---

Schedule and Index

SearchBlox lets you set how often and when the collection should be indexed. The available schedule options are:

• Once
• Hourly
• Daily
• Every 48 Hours
• Every 96 Hours
• Weekly
• Monthly

---

The following operation can be performed in Confluence collections

Manage Documents Tab

• Using the Manage Documents tab, you can perform these actions:

  1. Filter – Search for specific documents
  2. View Content – See the file’s content
  3. View Metadata – Check document details
  4. Refresh – Update the document list
  5. Delete – Remove a document from the collection

• To delete a file, enter its file path and click Delete.

• To check the status of a file, click View Metadata.

Data Fields Tab

Using the Data Fields tab, you can create custom fields for search, and you can also view the default data fields for non-encrypted collections. SearchBlox supports four types of Data Fields:

1. Keyword
2. Number
3. Date
4. Text

After configuring Data Fields, the collection must be cleared and re-indexed for the changes to apply.

To know more about Data Fields please refer to Data Fields Tab

Models

The Models page allows you to configure and override AI models used for embeddings, reranking, and LLM-based features within the collection.

Embedding

• Provider specifies the embedding provider used to generate vector representations of documents.
• Model defines the embedding model used to convert document content into vectors for semantic search.

Reranker

• Provider specifies the reranker provider used for improving search result relevance.
• Model defines the reranker model used to re-score and reorder search results based on relevance.

LLM

• Provider specifies the Large Language Model provider used for AI-powered features.

• Model defines the LLM used for tasks such as document enrichment, summaries, and SmartFAQs.

• These settings override global configurations and apply only to the current collection.