⚡ OPTIMIZE: detector - 3x faster plate detection (single OCR, lightweight preprocessing)

Fix investigation display and donut chart: use correct column names, improve results formatting

Fix investigation hanging: add timeout protection and simplify chat handlers

🐛 CRITICAL FIX: Convert Chatbot format from tuple to dict with role/content keys

Fix: Remove duplicate code, improve chatbot tuple format handling

🔧 Fix: Correct chat message format in investigation chatbot

🎨 UI improvements: add visual charts, fix analytics dashboard, optimize investigation lag

Fix: Suppress asyncio cleanup errors and optimize detailed tabs for responsiveness

Optimize: Instant UI response - return immediately with loading message, fill in results in background

Fix: Use proper Gradio Chatbot format with role/content dictionaries

Fix: Remove asyncio event loop policy, fix MistralClient references, simplify chat message format

Fix: Resolve Chatbot message format error, asyncio event loop issues, and Mistral API compatibility

Fix: Resolve asyncio event loop issues and Mistral client API compatibility

Fix: Remove unsupported bubble_full_width parameter from Chatbot

Fix: Remove unsupported show_copy_button parameter from Chatbot and remove undefined function wrappers

UI Redesign: Chat-based investigation interface with conversational flow and scrollable history

Major redesign: AI Investigation agent with conversational multi-turn flow, follow-up questions, and better error handling

Feature: Advanced NLP-to-SQL with Mistral agent

Improve: Redesign AI Investigation UI and output formatting

Refactor: Consolidate AI Investigation into single unified agent tab with RAG capabilities

Fix: Remove unsupported show_copy_button parameter from Gradio Textbox components for compatibility

Integrate: AI Investigation Assistant into new tab (replaces AI Assistant)

Fix: Replace gr.Date with gr.Textbox for Gradio compatibility

Enhance: Vehicle Intelligence Map with smart location grouping and date colors

Clean up: Remove duplicate functions and add map_to_html - Vehicle Intelligence Map

Fix: TAB 5 context manager indentation error - Vehicle Intelligence Map

Fix: Gradio context manager error in TAB 5 - Vehicle Intelligence

Fix: TAB 5 indentation and imports - Vehicle Intelligence Map

Fix: Complete Vehicle Intelligence Map overhaul - Removed duplicates, fixed Folium HTML rendering with branca, added plate normalization, handle NaN coordinates, proper error handling, dark map theme

Fix: Remove invalid 'enable_queue' parameter from demo.launch()

Fix: Asyncio event loop cleanup issue - Added platform-specific event loop policy, disabled SSR mode, suppressed warnings

Fix: Vehicle Intelligence Map - Fixed map HTML display, added location geocoding, improved error handling, working with database schema

Add: Vehicle Intelligence Map - geospatial tracking, route visualization, radius surveillance, heatmaps, suspicious movement detection

Fix: Remove unsupported 'show_copy_button' parameter from gr.Chatbot()

Fix: Remove invalid 'interactive' parameter from gr.Markdown() components

Update app.py

Fix: Major UI responsiveness improvements - remove demo.load() blocking, fix Chatbot format for Gradio 6.14.0, add timeout handling to all queries, fix save_detection column mapping

Debug: Add comprehensive error logging and debug output to all functions - query_database, chatbot_query, refresh_analytics

Fix: Correct Gradio Row/Column syntax for 6.14.0 - replace invalid .style() method

Improve: Add detailed configuration status display, better error messages, and debug info at startup

Fix: Remove invalid 'type' parameter from gr.Chatbot() for Gradio 6.14.0 compatibility

Update: Refactored app.py with improved UI and error handling

Improve: Add configuration checks, environment validation, and better error messages for missing HF_TOKEN and DATABASE_URL

Update: Integrate Mistral-7B-Instruct-v0.2 model for NLP-to-SQL engine and add database functions

fix: convert query results to pandas DataFrame for proper Gradio table display

update: latest changes to app.py and detector.py

refactor: modularize codebase with SQL validation, improved schema, and security measures

feat: integrate SQLCoder LLM, Supabase PostgreSQL, and improved NLP-to-SQL layer

Use stable versions: ultralytics 8.4.46, torch 2.1.2, transformers 4.40.0 + add error handlers

Fix ultralytics version for C3k2 support & set OMP_NUM_THREADS