Set FastEmbed as default embedding provider in TextEmbedder. Updated dependencies in pyproject.toml. Refreshed Context Module notebook and documentation to reflect changes. Added verification tests.
- Updated AgentContext, AgentMemory, and ContextGraph to support save/load persistence
- Integrated FastEmbed into VectorStore for high-performance local embeddings
- Replaced DemoVectorStore with production VectorStore in docs and examples
- Rebuilt 19_Context_Module.ipynb as a deep dive into context engineering
- Updated documentation and README to reflect new capabilities
- Fix AttributeError in SlidingWindowChunker notebook example by using correct chunk attributes (start_index/end_index).
- Update SlidingWindowChunker initialization in notebook (window_size->chunk_size, step_size->stride).
- Fix UnicodeEncodeError in progress_tracker.py by adding fallback encoding for Windows console output.
- Minor updates to chunk validator and table chunker.
- Fix indentation error in GraphBuilder loop
- Update EntityResolver.resolve to resolve_entities
- Update GraphValidator result access to use dataclass attributes
- Fix deduplication logic to preserve unmerged entities
- Fixed pattern-based relation extraction by using entity patterns for subjects to ensure validity.
- Improved dependency-based relation extraction to handle nested prepositional phrases and passive voice.
- Increased cooccurrence confidence threshold to meet defaults.
- Fixed AttributeError in 07_Building_Knowledge_Graphs.ipynb by replacing dict.get() with direct attribute access for Entity/Relation dataclasses.
- 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
KaifAhmad1