Llm chat/finalize #41
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
… into llmChat/finalize
… into llmChat/finalize
… into llmChat/finalize
Philipp came in clutch here.
… into llmChat/finalize
… into llmChat/finalize
nriedman
approved these changes
Feb 7, 2024
… into llmChat/finalize
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## main #41 +/- ##
==========================================
+ Coverage 39.34% 42.01% +2.68%
==========================================
Files 34 35 +1
Lines 1045 1107 +62
==========================================
+ Hits 411 465 +54
- Misses 634 642 +8
Continue to review full report in Codecov by Sentry.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
*LLM Chief Complaint Functionality, Prompt, and Summary View *
♻️ Current situation & Problem
Before the pull request, we had a minimal implementation of the LLM chatbot. Our summary appeared but it looked ugly, and the LLM did not ask very detailed or specific questions.
⚙️ Release Notes
The LLM makes a summary of the chief complaint with a textbox that the patient is able to edit. The summary is now much more robust, and the LLM asks the patient more relevant questions than it did before. It's not limited anymore to just duration and severity. The textbox is now editable.
📚 Documentation
We commented out the naviagtion stack for now and plan on incorporating that after merging. We changed the LLM function call to now be more non-parametric and dynamic. We got rid of the parameters and instructed it to give us a summary instead. With less structure, we are able to harness all of the LLM's abilities.
✅ Testing
We have tested the LLM on a variety of medical concerns that are not included in the examples given in the system prompt, and we have gotten really great results with specific questions to the complaint.
📝 Code of Conduct & Contributing Guidelines
By submitting creating this pull request, you agree to follow our Code of Conduct and Contributing Guidelines: