V1 annotations and weaviate dashboard #32
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
Creates centralized LLM model definitions for both OpenAI and Anthropic Replaces hardcoded model strings with constants for better maintainability Adds YAML formatting for extracted information output Improves code formatting and readability
Implements MongoDB term-based search with text highlighting functionality as an alternative to hybrid search Introduces new schema for Swiss franc loan judgment information extraction Adds environment variable support for Weaviate configuration - Adds toggle in UI to switch between hybrid and term-based search - Improves search results display with highlighted matches - Introduces judgment data model enums for consistent field access
Improves readability of search result highlights by: - Adding yellow background with black text for better dark mode visibility - Replacing info boxes with cleaner markdown separators - Making model loading conditional on hybrid search mode Restructures the highlight display to be more visually appealing while maintaining readability across different UI themes.
Standardizes database field access using Judgment enum values Adds court name and date information to search results Centralizes returned attributes configuration for better maintainability Improves user experience by displaying more comprehensive judgment information in search results while reducing potential for field name errors
Improves the clarity and structure of the legal document analysis prompt by: - Adding detailed instructions for different field types (boolean, enum, dates) - Including validation and objectivity requirements - Expanding schema with new result-related fields - Providing more specific guidance on information extraction Makes extraction more reliable and consistent by enforcing stricter rules for data extraction while maintaining language flexibility.
Reorganizes dashboard structure to use new Streamlit navigation system Adds new case law trends analysis module for Swiss Franc loan cases Introduces visualization tools for temporal analysis of court decisions Includes Dziubak judgment reference date and stacked/unstacked distribution plots Removes redundant page configurations and consolidates them in main app.py
Includes DVC tracking configuration for three new konfiskata-related dataset samples: - 10 sample entries with retrieved information - 10 sample entries base dataset - 100 sample entries base dataset Updates gitignore to exclude the actual CSV files from Git tracking
Configures Streamlit dashboard environment for improved development experience: - Enables automatic reloading on file changes - Optimizes performance with fast reruns - Sets up headless mode for production deployment
Simplifies the dashboard entry point filename from emoji-based naming to standard naming convention for better maintainability and compatibility
Applies consistent code formatting across multiple files: - Unwraps long lines to improve readability - Standardizes line endings to LF - Removes unnecessary line breaks in multiline statements - Normalizes whitespace and indentation These changes improve code consistency and maintainability without affecting functionality.
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.
No description provided.