### Changes:
- **Core MCP Components**:
- Introduced `BrainyMCPAdapter`, `BrainyMCPService`, and `MCPAugmentationToolset` for handling data access, tool execution, system information, and authentication via MCP.
- Added asynchronous handlers to process requests for Brainy data, augmentations, and relationships.
- Built pipelines to expose Brainy augmentation capabilities as tools.
- **Server Implementations**:
- Added WebSocket and REST interfaces in `initializeMCPService` for external MCP requests.
- Included rate limiting, authentication, and CORS support for REST API.
- **Type Definitions**:
- Defined MCP-related types such as `MCPRequestType`, `MCPResponse`, and `MCPToolExecutionRequest` in `src/types/mcpTypes.ts`.
- Incorporated augmentation-type-specific methods from `augmentationPipeline`.
- **Exports**:
- Exposed MCP modules (`BrainyMCPAdapter`, `BrainyMCPService`, `MCPAugmentationToolset`) via `src/mcp/index.ts`.
### Purpose:
Introduced a Model Control Protocol (MCP) framework to enable seamless integration of Brainy data and augmentation tools with external models. The implementation provides structured, scalable access to data and tools through both WebSocket and REST APIs.
### Changes:
- Added `HNSWIndexOptimized` class in `src/hnsw/hnswIndexOptimized.ts`:
- Supports large datasets with product quantization for dimensionality reduction.
- Enables disk-based index storage via a configurable storage adapter.
- Introduces `HNSWOptimizedConfig` interface for advanced configuration:
- Includes memory thresholds, product quantization (subvectors, centroids), and disk-based indexing options.
- Implements methods for adding, searching, and managing indexed vectors with enhanced scalability.
- Introduced `ProductQuantizer` utility:
- Handles vector quantization with training and reconstruction capabilities.
- Reduces vector dimensions, improving memory and performance efficiency.
- Added accessor methods in `src/hnsw/hnswIndex.ts` for configuration and index metadata (e.g., dimension, max level, entry point).
### Purpose:
Enhanced the HNSW implementation to support optimized indexing and search for large datasets, addressing scalability challenges via product quantization and optional disk-based storage. This update elevates the library's performance and applicability for memory-constrained environments.
### Changes:
- Created `examples/browser_compatible_exports.ts`:
- Introduced browser-friendly exports with polyfill for `Buffer` in browser environments.
- Implemented shims for Node.js modules (`fs`, `util`, and `path`) to avoid compatibility issues.
- Exported browser-compatible types and utilities: `BrainyData`, `NounType`, `VerbType`, graph types, core types, distance functions, embedding utilities, and storage adapters.
- Explicitly excluded Node.js/CLI-specific parts to focus on browser compatibility.
- Added `src/types/brainyDataInterface.ts`:
- Defined `BrainyDataInterface` to break the circular dependency between `brainyData.ts` and `serverSearchAugmentations.ts`.
- Provided methods for managing nodes, relationships, initialization, search, and adding vector data with metadata.
### Purpose:
- Enhanced the codebase to support browser environments by introducing browser-specific exports and avoiding Node.js dependencies.
- Established clearer separation of concerns and modularity by introducing the `BrainyDataInterface` for dependency management, improving maintainability and flexibility.
Implemented WebSocketConduitAugmentation and WebRTCConduitAugmentation for syncing Brainy instances. Added comprehensive usage examples to showcase data synchronization via WebSocket and WebRTC.
Upgraded minimum Node.js version from 18.0.0 to 23.11.0 across `README.md`, `package.json`, and `version.ts`. Optimized distance utilities and pipelines to leverage Node.js 23.11+ native performance improvements (e.g., `array.reduce`, WebStreams API). Incremented version to 0.7.4 for consistency.
Added the `SequentialPipeline` class for structured augmentation execution. Integrated threading capabilities via the `THREADED` execution mode in `augmentationPipeline`. Enhanced WebSocket support for real-time data processing through pipelines.
Deleted all Firestore augmentation, storage, sync implementations, and related type definitions. Removed the FirestoreSync example file as part of the cleanup for disabled Firestore functionality.
Commented out all Firestore-related code across the project, including sync, storage, and vector search features. Removed Firebase dependencies (`firebase`, `firebase-admin`) from `package.json`. Updated `README.md` to reflect the temporary unavailability of Firestore features.
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`.
Replaced type aliases with interface extensions to enhance type compatibility and readability. Reorganized exports in `index.ts` to streamline imports.
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.
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.
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.
