AI HubRelease notes

Known issues

These are the known issues in this release.

Administration

  • AI Hub doesn’t support digitizing documents of more than 800 pages.
  • If you rename a workspace, you can then encounter errors in Build when trying to load files and images. Do not rename workspaces until this issue is resolved.

Converse

  • When querying multiple documents in Converse:

    • With the multistep model, the information source is accurately returned only at a page level.

    • Only the multistep model can return visualizations such as graphs and charts.

    • Single specific tables can’t be extracted.

  • Table extraction is in public preview, and Converse can’t yet reliably do the following:

    • Correctly extract a single table that’s continued on a different page, unless the table header is present on the subsequent page. If there is no consistent table header across all pages, the tables on each page are detected separately.

    • Select a table from an Excel sheet that contains multiple tables on one sheet. If a single Excel sheet contains more than one table, Converse can extract only the top left table.

    • Select a table from a document with many (approximately 30 or more) tables in a single document.

    • Use non-English language queries for table extraction from non-English documents.

    • Respond to prompts about tables that aren’t found by Converse’s object detection.

    • List the exact source of information in a table. Instead, Converse cites the entire table as the information source.

  • When you publish a new chatbot version, including updating any of the chatbot’s details or settings, all users of the chatbot lose their chat history and are redirected to the chatbot’s latest version.

  • Chatbots don’t currently support querying information retrieved using object detection, such as tables and checkboxes. If a chatbot’s origin conversation has object detection enabled, the same query can yield different responses in the chatbot.

Build

  • Using a reasoning prompt to extract tables doesn’t return a confidence score.