August 20: Support for medical entities, Anthropic prompt caching, bug fixes
New Features
💡 Graphlit now supports the extraction of medical-related entities: MedicalStudy, MedicalCondition, MedicalGuideline, MedicalDrug, MedicalDrugClass, MedicalIndication, MedicalContraindication, MedicalTest, MedicalDevice, MedicalTherapy, and MedicalProcedure.
💡 Graphlit now supports medical-related entities in GraphRAG, and via API for queries and mutations.
Added support for Anthropic prompt caching. When using Anthropic Sonnet 3.5 or Haiku 3, Anthropic will now cache the entity extraction and LLM document preparation system prompts, which saves on token cost and increases performance.
Bugs Fixed
GPLA-3104: Should default search type to VECTOR, when performing entity similarity filter.
GPLA-3112: Empty PDF fails entity extraction.
PreviousSeptember 1: Support for FHIR enrichment, latest Cohere models, bug fixesNextAugust 11: Support for Azure AI Document Intelligence by default, language-aware summaries
Last updated