> For the complete documentation index, see [llms.txt](https://changelog.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://changelog.graphlit.dev/august-2024/august-20-support-for-medical-entities-anthropic-prompt-caching-bug-fixes.md).

# August 20: Support for medical entities, Anthropic prompt caching, bug fixes

### New Features

* :bulb: Graphlit now supports the extraction of medical-related entities: MedicalStudy, MedicalCondition, MedicalGuideline, MedicalDrug, MedicalDrugClass, MedicalIndication, MedicalContraindication, MedicalTest, MedicalDevice, MedicalTherapy, and MedicalProcedure.
* :bulb: Graphlit now supports medical-related entities in GraphRAG, and via API for queries and mutations.
* Added support for [Anthropic prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#how-prompt-caching-works). 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.