UI: generator — output card, import flow, edit-in-place #20
Conversation
This file contains hidden or 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
- Add tabbed interface to generator.html with Manual Form and AI Assistant tabs - Implement AI chat assistant using Azure Ollama (qwen model) for TOML spec generation - Add parseMarkdown() function to properly format code blocks in chat responses - Update chat_service.py to wrap TOML specs in markdown code block markers - Fix Azure Ollama authentication: use OCP-Apim-Subscription-Key header instead of Bearer token - Extend API timeout from 60s to 300s to accommodate Ollama inference latency - Add python-dotenv to dependencies for local environment variable loading - Update docker-compose.yml to load environment variables from .env file - Configure environment variables: OLLAMA_BASE_URL, OLLAMA_API_KEY, OLLAMA_MODEL - Add Magic Wand SVG icon for AI Assistant tab with sparkle effects - Implement secure API proxy pattern: all external URLs/keys handled server-side only - Add error handling with timeout detection and user-friendly error messages - Chat messages displayed in bubbles with proper markdown formatting - Maintain conversation history for multi-turn interactions This enables users to generate medical calculator specifications through an intuitive AI-assisted workflow while keeping all authentication credentials secure on the backend.
…ismiss for LLM specs; add back/start-new buttons; add edit-in-place for generated code; show spinner during requests
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Outdated suggestions cannot be applied.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.
Hide output card initially; show on generate/import; add import/dismiss for LLM specs; add back/start-new buttons; add edit-in-place for generated code; show spinner during requests.