Spaces:
Sleeping
Sleeping
Commit History
-
🕷️ Intelligent Web Scraping for Nutrition Recommendations
✨ Revolutionary Features: • Real-time web scraping from trusted sources (CDC, NIH, Mayo Clinic) • Intelligent content extraction and summarization • Query-specific URL selection based on user intent • Cached responses for performance (1-hour cache) • Contextual source recommendations with credibility scores 🧠 Smart Intelligence: • 'I want to lose weight' → Scrapes CDC weight loss guidelines + NIH resources • 'Heart health' → Scrapes AHA + DASH diet information • 'Diabetes' → Scrapes CDC diabetes nutrition + ADA resources • Auto-summarizes scraped content based on user query 🔧 Technical Improvements: • Added BeautifulSoup4, lxml, html5lib for robust web scraping • Concurrent scraping of multiple URLs with aiohttp • Content extraction from headings, paragraphs, and lists • Intelligent summarization based on query relevance • Fallback to static responses if scraping fails 🎯 Result: Users get current, evidence-based nutrition information directly from trusted health organizations, no…7ddbe04
-
🤖 Enhanced chatbot with two-option system and reinforcement learning
✨ Features: • Two-option chatbot flow: Nutrition recommendations OR Recipe recommendations • Nutrition info with trustworthy sources (NIH, CDC, Nutrition.gov) • User feedback system for reinforcement learning • Personalized recipe recommendations that improve over time 🔧 New API endpoints: • /api/chatbot-options - Initial option selection • /api/nutrition-info - Evidence-based nutrition information • /api/user-feedback - Records user feedback for ML improvements 🎯 This update transforms the chatbot into an intelligent assistant that learns user preferences and provides credible nutrition information.8a8f67f
-
🚀 Enhanced Recipe AI with Conversation Intelligence & Personalization
Features Added: • Conversation Memory: Context-aware recommendations across chat sessions • User Personalization: Learn from likes/dislikes with preference tracking • Proactive Intelligence: Smart suggestions based on user patterns • Enhanced API: Support for user profiles, session context, and dietary filters • RL-Ready: Foundation for reinforcement learning integration Technical Improvements: • Extended RecipeRequest model with personalization fields • Added personalization filters and ranking algorithms • Enhanced search with user preference weighting • Conversation context integration for contextual recommendations • Backend optimization for real-time personalization 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>cb4c2f7
-
Add debug endpoint to check recipe database content
vkce218c9 -
Integrate USDA FoodData Central API for intelligent food understanding
vk- Replace hardcoded ingredient detection with USDA API calls - Use government food database to understand 'burger' -> 'ground beef patty' etc - Combine USDA suggestions with DialoGPT and original query - Truly intelligent food term recognition without any hardcoding - Free unlimited API usage from USDA28db69a -
Simplify to intelligent search: remove hardcoded ingredient lists
vk- Keep DialoGPT for query enhancement - Remove all hardcoded ingredient/cuisine/meal type lists - Pass full user query directly to TF-IDF search - Simple but effective boosting for dessert/food word detection - Much cleaner and more scalable approach - Should now properly handle 'burger recipes' and 'chocolate dessert'5c5dfcc -
Improve recipe recommendations: better dessert detection and lightweight LLM
vk- Replace heavy Llama 2 with DialoGPT-small for HF Spaces - Add comprehensive dessert/chocolate ingredient detection - Implement priority-based recipe matching (dessert queries get 3x boost) - Enhanced search algorithm with 18+ dessert-specific patterns - Remove heavy dependencies (peft, accelerate, bitsandbytes) - Fix issue where 'chocolate dessert' returned shrimp recipes6e6fe5a
-
🌟 Fix recipe rating display: use actual avg_rating as confidence and increase minimum review threshold
- Updated confidence calculation to use avg_rating/5.0 instead of similarity score - This ensures iOS app displays correct star ratings (4-5 stars for filtered recipes) - Increased min_reviews from 2 to 5 for better quality filtering - Now only high-quality recipes (4+ stars, 5+ reviews) will be recommended 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>233b45a
-
Fix NaN values causing Pydantic validation errors
- Handle NaN description values properly (convert to empty string) - Handle NaN name values with fallback - Handle NaN/invalid minutes values with 30min default - Add explicit type conversion to ensure string fields are strings - Fix validation error that was preventing recipe display 🤖 Generated with [Claude Code](https://claude.ai/code)cba21f2 -
Fix import warnings and ensure minutes from RAW_recipes.csv
- Remove unused re import - Add missing urllib.request import - Verify minutes field uses recipe['minutes'] from database - Clean up servings to use proper field or n_ingredients estimate 🤖 Generated with [Claude Code](https://claude.ai/code)92d7a7f -
Remove all fallback data and add rating-based recipe filtering
- Remove all mock/fallback recipe data - Add proper rating filter using RAW_interactions.csv - Only return recipes with rating >= 4.0 and >= 2 reviews - Service fails cleanly if database cannot be loaded - No fake data - real database or nothing 🤖 Generated with [Claude Code](https://claude.ai/code)be9504b -
Fix indexing error in recipe search
b079cdb -
Upgrade to Database-Powered Recipe System
- Replace text generation with real database recipe search - Add GPT-2 enhanced query understanding for better search - Load recipes directly from nutrientartcd/recipe-dataset - Return structured DatabaseRecipe objects with IDs, ingredients, steps - Add TF-IDF semantic search with ingredient/cuisine boosting - Include nutritional information and recipe metadata - Add comprehensive fallback system and error handling 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>0a28346
-
Fix colorTo metadata for HF validation
35804b3 -
Deploy FastAPI Recipe AI Assistant
- Added FastAPI app with clean REST endpoints - Integrated GPT-2 LoRA model from nutrientartcd/recipe-gpt2-lora - Added CORS support for mobile app integration - Added health checks and proper error handling - Added automatic API documentation at /docs19cdfc2 -
initial commit
Verified signature934e108