- Removed all Pinecone references, adapters, and documentation to align with open-source, self-hosted focus.
- Removed PineconeAdapter and related dependencies.
- Updated VectorStore to enforce supported backends (FAISS, Weaviate, Qdrant, Milvus, InMemory).
- Updated cookbooks (e.g., 13_Vector_Store.ipynb) to use Weaviate/FAISS examples instead of Pinecone.
- Updated core documentation (modules.md, rchitecture.md, etc.) to reflect backend changes.
- Added new tests ( est_pinecone_removal.py, est_vector_store_deepdive.py) to verify removal and validate remaining backends.
- Verified all vector store tests pass.
- Renamed semantica/triple_store to semantica/triplet_store
- Updated all imports and class references in core modules and adapters
- Refactored Jupyter notebooks in cookbook/
- Updated documentation files (README, docs/, etc.)
- Updated tests and verified passing status
- Enhanced docs/reference/vector_store.md (~575 lines)
- All 32 classes documented
- All 10 convenience functions
- Complete adapter documentation
- Updated cookbook/introduction/13_Vector_Store.ipynb
- 10-step comprehensive guide
- Created cookbook/advanced/Advanced_Vector_Store_and_Search.ipynb
- 4 focused parts (removed error handling per user request)
- Part 1: Index selection (Flat, HNSW, IVF)
- Part 2: Smart filtering with metadata
- Part 3: Result fusion (RRF, weighted)
- Part 4: Multi-tenant data isolation
- Beginner-friendly with clear examples
- Quick reference guide included
All vector_store documentation complete and production-ready.
BREAKING CHANGE: Removed build() convenience function from semantic_extract module
- Removed build() function from semantic_extract/__init__.py
- Updated __all__ exports to remove 'build'
- Resolved merge conflicts in named_entity_recognizer.py, relation_extractor.py, triple_extractor.py
- Updated semantic_extract_usage.md with class-based examples
- Updated docs/reference/semantic_extract.md with detailed parameter documentation
- Fixed 01_GraphRAG_Complete.ipynb to use individual extractor classes
- Enhanced 05_Entity_Extraction.ipynb with comprehensive examples (9 sections)
- Enhanced 06_Relation_Extraction.ipynb with complete pipeline examples (9 sections)
Users should now use individual classes (NERExtractor, RelationExtractor, TripleExtractor, etc.)
instead of the build() function for better control and flexibility.
Migration guide available in documentation.
- Remove ConflictDetector and Deduplicator from semantica.kg module
- Update all imports to use dedicated semantica.conflicts and semantica.deduplication modules
- Update all cookbook notebooks to use class-based API instead of convenience functions
- Fix calculate_centrality calls to use specific methods (calculate_degree_centrality, calculate_betweenness_centrality)
- Update detect_communities and analyze_connectivity calls to pass graph parameter
- Update documentation (kg_usage.md, docs/reference/kg.md) to reflect changes
- Remove conflict and deduplicate task types from method registry
- Removed deprecated 'build' convenience function from semantica/ingest/__init__.py to resolve conflicts and promote class-based usage.
- Updated 'docs/reference/ingest.md' to include missing main classes: FeedIngestor, EmailIngestor, DBIngestor, and MCPIngestor.
- Added 'Stream Monitoring' usage example to 'semantica/ingest/ingest_usage.md'.
- Completely rewrote 'cookbook/introduction/02_Data_Ingestion.ipynb' to provide a comprehensive, runnable guide covering all ingestion submodules and helper classes.
- Enhanced Graph Store notebook with comprehensive examples and clean formatting
- Fixed GraphStore API usage across all documentation files
- Updated examples to use keyword arguments (labels, properties, start_node_id, end_node_id, rel_type)
- Removed emojis and links from notebook for cleaner markdown
- Made summary section more concise
- Ensured consistency across cookbook notebooks, docs, and module code
- Enhanced introduction/15_Export.ipynb with complete module architecture documentation
- Enhanced advanced/05_Multi_Format_Export.ipynb with all export formats and classes
- Removed HTMLExporter references from intelligence notebooks (class doesn't exist)
- Fixed OWLExporter usage in healthcare notebook (removed invalid export_knowledge_graph call)
- Updated all notebooks to use only class imports, no convenience functions
- Added comprehensive documentation for all exporter classes and methods
- Improved markdown structure and learning objectives in both notebooks
- Fix anchor links in cookbook.md (#core-tutorials, #industry-use-cases)
- Convert all notebook links to GitHub URLs for proper resolution
- Fix intelligence notebook filenames
- Update all use case notebook links to use absolute GitHub paths
- Resolve all WARNING level issues in MkDocs strict build
- Update all notebooks to use generate_embeddings() instead of generate()
- Update docs/reference/embeddings.md to remove references to removed components
- All notebooks now use data_type='text' parameter for embedding generation
- Updated 11 notebooks across introduction, use_cases, and advanced directories
- Restructured 18_Deduplication.ipynb with comprehensive module overview
- Added detailed explanations of module capabilities and architecture
- Improved markdown formatting and removed emojis
- Reorganized content to focus on module capabilities rather than individual classes
- Added clear examples for all major features
- Updated documentation for consistency across all files
Resolved merge conflicts by:
- Removing statistics functionality from ConflictResolver and ConflictAnalyzer
- Removing detect_and_resolve convenience function
- Updating all documentation and examples
- Adding by_source analysis capability
- Updating method signatures to match new API
KaifAhmad1