vecbox 0.2.1 → 0.2.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md ADDED
@@ -0,0 +1,40 @@
1
+ # Changelog
2
+
3
+ All notable changes to this project will be documented in this file.
4
+
5
+ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6
+ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7
+
8
+ ## [0.2.2] - 2026-02-14
9
+
10
+ ### Added
11
+ - Native N-API integration for Llama.cpp (10x faster performance)
12
+ - Auto-detection of best available provider
13
+ - Support for GGUF models with direct native loading
14
+ - Smart fallback system between providers
15
+ - File input support for direct text file embedding
16
+ - Batch processing capabilities
17
+
18
+ ### Changed
19
+ - Simplified installation - zero setup required
20
+ - Updated README with modern usage examples
21
+ - Improved error handling and logging
22
+ - Better TypeScript support with comprehensive types
23
+
24
+ ### Fixed
25
+ - Native module compilation issues
26
+ - Provider detection and fallback logic
27
+ - Memory management for native embeddings
28
+
29
+ ### Providers
30
+ - **OpenAI**: text-embedding-3-small, text-embedding-3-large
31
+ - **Google Gemini**: gemini-embedding-001
32
+ - **Mistral**: mistral-embed
33
+ - **Llama.cpp**: Native N-API with GGUF support
34
+
35
+ ## [0.2.1] - Previous
36
+
37
+ ### Added
38
+ - Multi-provider support
39
+ - Basic embedding functionality
40
+ - TypeScript definitions