Mediate token limits of LLM service providers

[philippzagar]

Problem

As shown in #33, one hits the token limits of a single prompt to the OpenAI LLM provider quite quickly in the Multiple FHIR Resource Chat functionality of LLMonFHIR.

Solution

#33 provides an easy and quick fix for this limitation, however, we should investigate how to properly summarize FHIR resource data points.
However, these limitations are quite hard to explore/reproduce as we don't have the necessary extensive FHIR data points available (except for @aalami5).

Ideas to explore:

• Experiment with OpenAI prompt that summarizes FHIR resources
• Give the summarization output a more fixed (JSON?) structure, not just free-flowing text
• Omit unnecessary FHIR data points (such as identifiers, ...)

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct and Contributing Guidelines