In the last month, we improved the config-authoring experience in the Sensible app, added advanced features for sections and for the Custom Computation method, and made minor improvements to several SenseML methods.
In the last month, we added the ability to batch upload and extract from documents in the Sensible app. We also improved the user experience by adding a new Integrations tab for developers, and by auto-extracting data from new user's first documents. We improved LLM-based methods, and added advanced options for layout-based extractions, including the ability to transform extracted fields with your own custom logic.
In the last month, we released an open-source Python SDK that offers convenient access to the Sensible API, added advanced configuration options for the LLM-powered List and NLP Table methods, and made minor improvements to other features.
In the last month, we launched a powerful new dashboard to help you monitor historic and real-time extraction metrics, added new user management features to the Sensible app, and made LLM prompt configuration available at the config level for Sensible Instruct.
In the last month, we released new quality scores for extractions, enabled extracting large tables with the NLP Table method, and made advanced LLM prompt configuration options available in the Sensible Instruct editor for the List and Table methods.
In the last month, we introduced new traceability for the LLM-powered Query method by highlighting the source text for the LLM's answer in the document, made advanced LLM prompt configuration options available in the Sensible Instruct editor for the Query method, made filtering past extractions available in the app and API, and released a new preprocessor for handling page-rotation edge cases.
In the last month, we released new advanced prompt configuration options for methods powered by large-language models (LLMs), introduced confidence signals as a more nuanced alternative to confidence scores for data extracted by LLMs, and made several improvements to existing features.
In the last month, we released improvements to NLP methods, to the SenseML and Sensible Instruct editors, and to API key configurability and security. We added the ability to extract from portfolios in the Sensible app's quick extract tab.
In the last month, we released a new API for classifying a document by its user-defined type, improvements to the Zapier-Sensible integration, to the quick extraction tab in the Sensible app, and to natural-languages methods.