# September 1: Support for FHIR enrichment, latest Cohere models, bug fixes

### New Features

* :bulb: Graphlit now supports entity enrichment from [Fast Healthcare Interoperability Resources (FHIR)](https://en.wikipedia.org/wiki/Fast_Healthcare_Interoperability_Resources) servers. You can provide the `endpoint` for a FHIR server, and Graphlit will enrich medical-related entities from the data found in the FHIR server.
* Added support for latest Cohere models (`COMMAND_R_202408`, `COMMAND_R_PLUS_202408)` and added datestamped model enums for the previous versions (`COMMAND_R_202403`, `COMMAND_R_PLUS_202404`).  The latest model enums (`COMMAND_R` and `COMMAND_R_PLUS`) currently point to the models (`COMMAND_R_202403` and `COMMAND_R_PLUS_202404`) as specified by the Cohere API.
* Added support for the latest Azure AI Document Intelligence v4.0 preview API (2024-07-31), now used by default.
* :zap: We have changed the name of the `LinkReferenceType` to `LinkReference` to follow the existing data model standard.

### Bugs Fixed

* GPLA-3120: LLM is adding source tags to end of completed messages
* GPLA-3133: Failed to load sitemap on child page of website.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://changelog.graphlit.dev/september-2024/september-1-support-for-fhir-enrichment-latest-cohere-models-bug-fixes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.