Introduced Firestore vector search integration using `@firebase/firestore-vector-search`. Added support for restricting searches by specific noun types to optimize performance and relevance. Updated `README.md` to document the new functionality and usage examples.
Refactored memory augmentation methods to return `Promise<AugmentationResponse>` for async handling. Introduced a new `search` method for vector similarity searches within the memory system.
Applied consistent indentation and line-breaking rules to code and text sections in `README.md`, ensuring better formatting and alignment for readability. No functional changes made.
Deleted `examples/externalPlugins.js` and `pluginLoader.ts` as they are no longer used. Updated all `.ts` imports to `.js` across the codebase. Added `MemberOf` to `VerbType` and filtered disabled augmentations in `executeAugmentationPipeline`. Updated documentation to reflect new augmentation registration process. Removed deprecated `allowImportingTsExtensions` from `tsconfig.json`.
Improved the fallback sequence for storage initialization by adding a secondary attempt to use FileSystemStorage in browser environments before defaulting to in-memory storage. Enhanced error handling and logging for unavailable storage options.
Updated error messages for initialization failures to use "BrainyData" for clarity. Enhanced `getStorageStatus` to handle storage adapters without the `getStorageStatus` method, ensuring proper reporting of storage type, usage, and adapter details.
Introduced `pluginLoader.ts` to enable loading and configuring augmentation plugins from external packages. Added `examples/externalPlugins.js` to demonstrate usage. Enhanced storage status reporting in `opfsStorage` and `BrainyData` with detailed storage capacity and usage methods. Updated README with an external plugin usage guide.
Replaced type aliases with interface extensions to enhance type compatibility and readability. Reorganized exports in `index.ts` to streamline imports.
Introduced an optional `requestPersistentStorage` flag to enable persistent storage permission requests in the browser. Updated `OPFSStorage` to include methods for requesting and checking persistent storage status, and modified `createStorage` to handle the new flag.
Introduced direct exports for `GraphNoun`, `GraphVerb`, `EmbeddedGraphVerb`, and related graph types (`Person`, `Place`, `Thing`, etc.) to streamline imports and improve type accessibility.
Introduced direct exports for several augmentation interfaces (e.g., ISenseAugmentation, ICognitionAugmentation) to simplify imports and enhance type accessibility. Updated type imports and exports in relevant files.
Added a new README section detailing how to import and use augmentation interfaces without pulling the entire library. Updated `package.json` exports to enable direct imports for augmentation types. Included example demonstrating custom augmentation implementation and usage.
Added a new example file `import-graphTypes.js` to showcase how to selectively import the `graphTypes` module, highlighting usage of `GraphNoun`, `GraphVerb`, `NounType`, and `VerbType`.
Introduced a new README section explaining how to import graph types individually to enable tree shaking. Updated `package.json` exports to support direct graph type imports. Enhanced `GraphNoun` structure by adding optional `label` and `embeddedVerbs` properties while simplifying the `CreatorMetadata` interface.
Refactored `fileSystemStorage` to dynamically import `fs` and `path` modules, improving compatibility with various environments. Updated initialization logic to set paths post-import. Added error handling for failed imports and enhanced type annotations for better maintainability.
Enhanced README to clarify the transition from a vector database to a combined Graph and Vector database, detailing support for graph entities, relationships, and full capabilities of the new data model. Updated examples and documentation accordingly.
Enhanced embedding functionality by introducing `createTensorFlowEmbeddingFunction` and `createSimpleEmbeddingFunction` for flexible text vectorization. Updated TensorFlow.js dependencies to be automatically included with the package. Added detailed examples and documentation in `README.md`. Improved error handling and refactored default embedding function implementation. Updated `package.json` dependencies.
Deleted augmentation pipeline examples and `.releaserc.json`, streamlining the repository by eliminating redundant example implementations and release automation files.
Introduced an augmentation event pipeline supporting multiple execution modes (e.g., SEQUENTIAL, PARALLEL). Added new Memory Augmentation type for versatile data storage/retrieval (e.g., fileSystem, in-memory, Firestore). Updated `README.md` with pipeline usage, examples, and augmentations reorganization. Included new demo files for augmentation examples.
Changed `"private"` to `false` in package.json to allow publishing the package to npm. The `"access": "restricted"` setting ensures that access remains limited to @soulcraft organization members. Updated README to reflect the new configuration.
Changed package name and imports to use the @soulcraft scope. Updated `README.md` to reflect the use of a private npm package and added publishing/installing instructions. Configured `package.json` with `private: true` and restricted access for publishing. Updated demo link to the correct GitHub repository.
