Assistant doesn't seem to handle fhir adaptors very well
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 5
- Forks
- 10
- Avg merge
- 2d 20h
- Merged PRs (30d)
- 17
Description
Problems working with the fhir-eswatini adaptor. This is all kinds of wrong and I can't seem to set the record straight.
I'm sure it's worked well in the past?
Looking at the docs, the signature is just patient(), not builders.patient or b.patient(). So maybe this is just a docs bug.
Also, the new fhir adaptors work a bit differently to others, so we need to makes sure we're pulling relevant guidance from the RAG
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source files or tests are named. Start by reproducing the assistant behavior with the fhir-eswatini adaptor, then compare the documented patient() signature and the guidance supplied through the RAG; done means the adaptor guidance and documentation accurately reflect how the new FHIR adaptors work.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, api
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100