generated from StanfordSpezi/SpeziTemplateApplication
-
-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Llm chat/finalize #42
Merged
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
Added SpeziLLM as a dependency to the project and created very basic infrastructure for the chief complaint (a button on the home screen leading to openAI onboarding and chat like what we saw in the demo on Jan 25th). # *Integrate basic LLM Functionality to the project* ## ♻️ Current situation & Problem Our project heavily depends on LLMs, but we did not yet have SpeziLLM as a dependency nor did we have any views set up for a chat interface with the LLM. ## ⚙️ Release Notes *Added SpeziLLM (including SpeziLLMOpenAI and SpeziLLMLocal) as a dependency to the project* *Created a Create Form tab on the home screen that links to a basic chat interface for the Chief Complaint* *Initialized for OpenAI LLM functionality, but not yet ready for local (i.e. no code written for downloading model)* ## 📚 Documentation The LLM modules are contained in the ChiefComplaint group for now. LLMInteraction is the chat UI, LLMOnboarding is the first time setup (for OpenAI, it requests an API Key, and once we get local LLM set up it will be able to initiate the setup for that). Onboarding files for OpenAI initialization are found in the OpenAI group, and onboarding files for local initialization are found in the Local group. ## ✅ Testing All the code in the ChiefComplaint group passes all the tests for a successful build at compile time. ## 📝 Code of Conduct & Contributing Guidelines By submitting creating this pull request, you agree to follow our [Code of Conduct](https://github.com/CS342/.github/blob/main/CODE_OF_CONDUCT.md) and [Contributing Guidelines](https://github.com/CS342/.github/blob/main/CONTRIBUTING.md): - [Y] I agree to follow the [Code of Conduct](https://github.com/CS342/.github/blob/main/CODE_OF_CONDUCT.md) and [Contributing Guidelines](https://github.com/CS342/.github/blob/main/CONTRIBUTING.md).
… into llmChat/finalize
… into llmChat/finalize
… into llmChat/finalize
Final LLM Chat UI with Greeting and Function Calling. ## ♻️ Current situation & Problem The basic LLM chat infrastructure was done, but it did not include a welcome greeting and did not have function calling capabilities to summarize the chat into a concise chief complaint. ## ⚙️ Release Notes Added function calling to the LLMInteraction struct's LLM model (currently commented out, as the function is not yet complete), and enabled a greeting message upon opening the app. Fine tuned the system prompt. ## 📚 Documentation NA ## ✅ Testing NA ## 📝 Code of Conduct & Contributing Guidelines By submitting creating this pull request, you agree to follow our [Code of Conduct](https://github.com/CS342/.github/blob/main/CODE_OF_CONDUCT.md) and [Contributing Guidelines](https://github.com/CS342/.github/blob/main/CONTRIBUTING.md): - [X] I agree to follow the [Code of Conduct](https://github.com/CS342/.github/blob/main/CODE_OF_CONDUCT.md) and [Contributing Guidelines](https://github.com/CS342/.github/blob/main/CONTRIBUTING.md). --------- Co-authored-by: Nina Boord <[email protected]>
Philipp came in clutch here.
… into llmChat/finalize
… into llmChat/finalize
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 DEMO PR
See llmchat/finalize PR to main for details about this PR.
This is temp just for the demo.
📝 Code of Conduct & Contributing Guidelines
By submitting creating this pull request, you agree to follow our Code of Conduct and Contributing Guidelines: