Changes and deprecations to document and template endpoints
As we evolve the document generation endpoint and related GET templates/sections, we are announcing several changes and deprecations. Find the full details including impact and timeline to shutdown in the breaking changes changelogNew, improved documentation guardrails!
- We have re-architected our documentation guardrails to be faster and more accurate.
- Documentation guardrails are the by default automatic step that quality-controls the generated document to correct outputs ungrounded in the source input.
- In this re-architected, new approach, we in parallel for each section identify hallucinations and provide targeted fixes by reference (sentence/segment index), preventing mismatched edits and skipping ambiguous duplicates. The result is format-preserving precise, auditable corrections that deliver safer, more trustworthy clinical summaries.
Reduced token usage for text generation
We are now leveraging cached input tokens when generating documents or facts. This is part of a continuous effort to provide text gen capabilities by Corti’s LLMs at even more competitive token consumption behaviour.Note: We plan to expose cached tokens as separate usage info response in the future.
New endpoint to extract facts from a provided text string input now available!
- so far FactsR™ was dependent on streaming audio over WSS to extract facts
- this new endpoint facilitates a REST endpoint as alternative to extract facts
- atomic endpoint, not part of interaction collection
- output is not stored into Corti database (zeroRetention is the only default)
Update to Generate Document functionality, including the following:
- Improve handling of sections that do not have content generated so that an empty string is returned instead of a placeholder (e.g.,
<empty>). - Fix to issue causing json text to be included in note output.
- nfc: Improve logging and exception handling in LLM hallucination guardrails service.
New: Set a zeroRetention header in the request to disable storing of the generated document to the DB.
Updated endpoint tags in API Reference page to indicate those with limited availability (codes, alignment, classification, contextual, explainability). Endpoints labeled as
limited availability are not available for public use at this time. Please contact us to learn more about these expert models and expected functionality to be generally released as AI tools.