Skip to main content
​
Mar 27, 2026

​
Features

Websites as a native data sourcePublic websites can now be connected as a data source directly from the Qontext UI. See the website docs for setup help.
  • Single or deep crawl: Add a URL and choose between fetching only the given page or crawling all nested pages.
  • Simple setup: Websites already connected in another vault of the same workspace are shown as reference for faster setup.
  • Notion sync performance: Further optimized syncing for large Notion workspaces with deeply nested pages.
​
Mar 20, 2026

​
Features

Confluence connectorDocs and content from Confluence can now be added to Qontext. See Confluence connection for setup help.
  • Supported content: Pages, blog posts, comments, and tasks are ingested automatically.
  • Select what to include: Add an entire space at once or filter by searching for the name or browsing through the spaces.
  • Parallel processing: Data syncs now process embeddings in parallel, significantly reducing sync times for data sources with large files.
  • Reliability: Additional fallback models are now in place, reducing the chance of failed syncs or retrievals due to temporary provider issues.
  • Notion performance improvements: Notion syncs are now more efficient, making them faster especially for workspaces with many pages.
  • Sync scheduling: Fixed a timezone issue that could cause scheduled syncs to run at the wrong time.
​
Mar 12, 2026

​
Features

Workspace settingsWorkspace configuration is now available directly in Qontext.
  • Edit name and URL: Change your workspace name and URL from the general tab.
  • View members: See who has access to the workspace. Member management is coming soon.
  • Request deletion: Request workspace deletion from the danger zone tab.
Manual syncs
  • Sync latest changes only: Manual syncs can now process only recent updates instead of resyncing all data, reducing manual sync times for connected data sources.
  • Ingestion and retrieval speed: Resolved an issue that occasionally caused delays during data reranking.
  • Manual resync scheduling: Triggering a manual resync no longer postpones the next scheduled automatic sync.
​
Mar 6, 2026

​
Features

Credentials ManagementCredentials can now be managed independently from vaults.
  • Separate credentials tab: View connected vaults, status, creation date, and creator for every credential directly from the credentials page.
  • Manage existing credentials: Verify, reconnect, or remove credentials.
  • Add new credentials: Start the credential setup directly by clicking the + Add button.
System instruction templates
  • Easier setup of system instructions: ready-made templates are now available for common retrieval and ingestion use cases.
  • Connect MCP modal: The modal now displays the MCP server URL to connect any MCP-capable tool directly to Qontext. Examples and setup instructions are included.
  • Sync logs: Auto syncs that return 0 records now show a SKIPPED status for clearer monitoring.
  • Slack source links: Direct links to Slack messages are now returned when retrieving context with includeSources = true. See the retrieval API for details.
  • Google Drive: Fixed an issue that caused all Google Drive files to be resynced every interval instead of only syncing updated files.
  • Data source instructions: Adding instructions now requires both a title and a body to prevent incomplete instructions from being saved.
  • Slack: Incremental syncs now correctly include messages from threads with late replies.
​
Feb 23, 2026

​
Features

Notion filters
  • Filters can now be managed directly from Qontext. See Notion connection for more information.
  • Reuse connection: The same Notion connection can now be reused with different filters across context vaults.
Slack connectorConversations from Slack can now be added to Qontext.
  • Select filters: Specify which channels to ingest. See Slack connection for setup help.
  • Date filter per channel: Decide from which date to include the messages per channel in the ingestion.
  • Bot messages toggle: Filter whether to include messages written by bots per channel.
  • Auth sessions: Fixed auth issues that required a page refresh after inactivity.
  • source_data_type: Added source_data_type mapping to ingestion API documentation.
​
Feb 13, 2026

​
Features

Syncs
  • Progress tracking: Data syncs now provide real-time progress updates during execution.
  • Cancel sync: Running syncs can be cancelled from the UI via a dedicated button.
Data sources
  • Credential name: Newly created credentials can now be named directly during the “new data source” flow.
Retrieval
  • Include sources: Retrieval API and MCP can now return where context was derived from. See Improvements and API changes for configuration details.
Syncs
  • Durability: Made syncs more durable and reliable.
  • Automatic initial sync: Syncs now start automatically when a data source is added.
  • Automatic sync after edit: Syncs now start automatically when filters are updated on a data source.
  • Sync already running: When a sync is triggered for a source that is already syncing, the current sync can be stopped or the new one skipped.
MCP
  • Improved vault selection: The “select vault” tool reply is now more informative for agents and works correctly with ChatGPT.
  • Multiple clients: Added support for connecting multiple MCP clients of the same type (e.g. Cursor, Claude) to different vaults.
  • Expired sessions: MCP sessions expire 7 days after creation and are now hidden from the UI once expired.
  • Source information: Added includeSources parameter to the retrieval tool so the LLM can request source information in the response.
API keys
  • Expiry column: Added an expiry column to the API keys table.
  • Revoked keys: Revoked API keys are now hidden from the API keys table.
  • Expired keys: Expired API keys can easily be deleted.
  • Retrieval logs: Retrieval logs now display the name of revoked or deleted API keys instead of “Deleted API Key”.
  • Automated syncs: Fixed an issue where they could fire twice (with one cancelled); exactly one sync runs now.
  • Website data sources: Automated syncing for websites connected via API now works.
  • Delete vault: Fixed a bug in the vault deletion. Button now works as expected.
  • API key instructions: Fixed creating and updating instructions for API keys.
  • knowledgeGraphId → vaultId: Renamed in ingestion and retrieval endpoints (ingestion: unstructured, website, any; retrieval).
  • workspaceId: Removed from ingestion and retrieval; use vault-scoped paths (ingestion: unstructured, website, any; retrieval).
  • includeSources: Added to retrieval (default false). When true, the response includes where context was derived from. Breaking change on Feb 27: default will become true. Set includeSources = false in requests or adopt source information before then.