Last updated
Graphlit now supports the and (reranking), in the Specification object. Now you can choose between COHERE, PONGO and JINA for your reranking serviceType.
Graphlit now supports Microsoft Teams feeds for reading messages from Teams channels.
Given changes in YouTube video player HTML, we have rewritten the YouTube downloader to support the new page format.
Added better handling of HTTP errors when validating URIs. Previously some websites were returning HTTP 403 (Forbidden) errors when validating their URI, or downloading content. Now Graphlit is able to scrape these sites, which previously returned errors.
Added support for updating content metadata in updateContent mutation. Now the video, audio, document, etc. metadata can be updated after the content workflow has finished.
Added query_contents_graph (and queryContentsGraph) functions to SDKs, which can be used to return nodes and edges from knowledge graph for visualization.
Citation indices have been changed to be one-based from zero-based. For example, you will now see "This is a citation. [1]" as the first citation in the list.
Added isSynchronous flag to deleteAll and multiple delete mutations. By default, bulk delete operations are now asynchronous (and completed after the mutation returns), unless the isSynchronous flag is set to true.
Added missing count mutations, such as countAlerts, countFeeds, etc.
Renamed query_content_facets to query_contents_facets in Python SDK
Renamed queryContentFacets to queryContentsFacets in Node.js SDK
GPLA-2544: Page relevance not filled-in in all situations
GPLA-2546: Not extracting links from PDF with Azure AI Doc Intelligence
GPLA-2557: Sporadically returning HTTP 500 from GraphQL API
GPLA-2573: Failed to re-ingest content which was deleted immediately after initial ingestion
GPLA-2575: Not validating for empty (non-null) parameters in mutations
GPLA-2578: Need to handle invalid JSON from LLMs; improper escaping or formatting
GPLA-2585: Failed to ingest encoded file with colon (:) in name
