- Remove top-level torch import from providers.py
- Add lazy imports in HuggingFaceLLMProvider and HuggingFaceModelLoader
- Remove hardcoded API key from notebook
- PyTorch now only loads when HuggingFace providers are instantiated
Fixes#129
- Added DoclingParser class in semantica/parse/ module
- Created earnings call analysis notebook with Docling integration
- Added docling to pyproject.toml as optional dependency
- Maintained backward compatibility with existing parsers
Closes#124
- Deleted cookbook/use_cases/healthcare/02_Drug_Interactions_Analysis.ipynb
- Removed Healthcare section from README.md
- Removed Healthcare section from docs/cookbook.md
- Removed Drug Interactions references from STRATEGIES_SUMMARY.md
- Updated cookbook count from 18 to 17 in all documentation
- Updated docs/index.md to reflect 17 cookbooks
- Add real CSV and JSON data sources for transactions and accounts
- Fix ConflictDetector, TemporalGraphQuery, and Reasoner errors
- Simplify code to use Semantica modules properly
- Enhance GraphRAG section with Context Graph and Groq LLM
- Add temporal interactive visualization using TemporalVisualizer
- Fix CSV export to use CSVExporter instead of GraphExporter
- Update README.md to mention Context Graph and Context Retriever
- Switch entity and relation extraction to ML-based methods (spaCy)
- Fix conflict detection to use detect_temporal_conflicts directly
- Fix graph building to use correct Relation attributes (subject/object/predicate)
- Improve GraphRAG with LLM-based multi-hop reasoning
- Enhance graph analytics output to show all entity types
- Update markdown descriptions with concise bullet points
- Enhanced progress tracker with automatic Jupyter/Colab detection
- Added detailed progress tracking to all deduplication modules
- Added detailed progress tracking to all semantic_extract modules
- Progress tracker now always enabled automatically
- Shows remaining items, percentages, ETA, and processing rates
- Works in both Jupyter notebooks and Google Colab
- Dynamic update intervals based on dataset size
- Improved display handling for Colab compatibility
- Fixed ConflictDetector to use update_progress() with counts/ETA for type, temporal, and logical conflict detection
- Fixed NERExtractor batch operations to show progress with ETA
- Fixed RelationExtractor batch operations to show progress with ETA
- All modules now display clear progress bars with percentage, counts, and estimated time remaining
- Enhanced ProgressItem with ETA fields (progress_percentage, total_items, processed_items, estimated_remaining)
- Added update_progress() and _calculate_eta() methods to ProgressTracker
- Updated ConsoleProgressDisplay and JupyterProgressDisplay to show progress with ETA
- Added progress tracking to deduplication modules (DuplicateDetector, EntityMerger, SimilarityCalculator, ClusterBuilder)
- Added progress tracking to conflicts modules (ConflictDetector, ConflictResolver)
- Added progress tracking to ingest, parse, kg, core, embeddings, and triplet_store modules
- All modules now display progress percentage, item counts, ETA, and processing rate
- Add fast path for dictionary entities/relationships to bypass _process_item overhead
- Improve entity recognition to handle 'text' and 'type' fields directly
- Significantly improve processing speed from ~0.8/s to thousands/s
- Fixes performance bottleneck in knowledge graph building
- Add semantica.llms module with Groq, OpenAI, HuggingFace, and LiteLLM providers
- Add query_with_reasoning() method for multi-hop reasoning with LLM-generated responses
- Update ContextRetriever and AgentContext with reasoning capabilities
- Add comprehensive documentation for LLM providers and GraphRAG reasoning
- Update README and docs with new features
- Update notebook examples to use new query_with_reasoning() method
- Fix TemporalGraphQuery: Change detect_temporal_patterns to query_temporal_pattern
- Fix GraphAnalyzer: Replace find_paths with direct relationship queries and BFS implementation
- Fix KGVisualizer: Change visualize() to visualize_network() with interactive visualization
- Fix GraphExporter: Remove unsupported CSV format, use export_csv for CSV export
- Add proper imports and improve error handling
- Enhance visualization with force-directed layout and better interactivity
- Added support for detecting and merging list of dict sources with entities/relationships
- Progress tracking now shows ETA and remaining items when sources is a list
- Fixes issue where progress wasn't displayed when passing list of dicts to build()
- Enhanced GraphBuilder with real-time progress updates showing percentage, ETA, and processing rate
- Added time tracking for entity processing, relationship processing, entity resolution, and graph structure building
- Added final summary with total build time
- Simplified notebook cell to rely on Semantica's built-in progress tracking instead of manual Python code
- Use ML-only approach for entity extraction (spaCy)
- Improve knowledge graph visualization with interactive layout
- Fix ontology export to use RDFExporter for TTL format
- Enhance visualization with better interactivity and explanations
- Fix LoadProgress attribute access in TripletStore (use loaded_triplets instead of processed_triplets)
- Fix None source handling in ContextRetriever RetrievedContext objects
- Add error handling for Blazegraph connection in notebook
- Ensure source field always has a default value in vector/memory retrieval
- Updated extract_entities_llm to use custom entity_types in prompts
- Updated extract_relations_llm to use custom relation_types in prompts
- Made entity type filtering case-insensitive and flexible
- Added verbose mode to RelationExtractor for progress tracking
- Improved error handling and progress reporting in notebook
- Made prompts more flexible to accept variations of entity/relation types
- Refactor 01_Risk_Assessment.ipynb with GraphStore, DBIngestor, conflict detection
- Refactor 02_News_Sentiment_Analysis.ipynb with TripletStore, StreamIngestor, deduplication
- Complete all 8 phases in both notebooks with different module approaches
- Add comprehensive graph analytics, ontology generation, and export functionality
- Rebuilt 01_Energy_Market_Analysis.ipynb with temporal pattern detection, trend prediction, and seed data integration
- Rebuilt 02_Smart_Grid_Management.ipynb with stream processing, real-time monitoring, and anomaly detection
- Removed core orchestrator usage, implemented cell-specific imports
- Added comprehensive data sources and Mermaid pipeline diagrams
- Minimal print statements, proper error handling with redirect_stderr
- Unique module combinations per use case for differentiation
- Enhanced 18 cookbooks across 9 domains with real data sources, advanced chunking, temporal KGs, and GraphRAG
- Updated docs/cookbook.md with all 18 cookbook links and enhanced descriptions
- Updated docs/use-cases.md with corrected links and removed duplicates
- Updated README.md with comprehensive Industry Use Cases section
- Fixed all outdated notebook links and ensured consistency across all docs
- Added real data ingestion (RSS feeds, APIs, MCP servers, streams)
- Integrated advanced chunking strategies (entity-aware, relation-aware, ontology-aware, semantic_transformer, etc.)
- Added temporal knowledge graphs, GraphRAG, deduplication, conflict detection, and other Semantica modules
- Added tests/reasoning/ directory with unit and integration tests
- Fixed indentation bug in Reasoner.add_fact for dictionary-based relationships
- Fixed regex variable matching in Reasoner._match_pattern
- Fixed variable handling in SPARQLReasoner query expansion
- Cleaned up cookbook and documentation references
KaifAhmad1