TBNilles/LEANN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: polish

Browse Source
This commit is contained in:
Andy Lee
2025-07-19 21:02:25 -07:00
committed by GitHub
parent bed814e7e6
commit bda028cc1b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -16,7 +16,7 @@ LEANN is a revolutionary vector database that makes personal AI accessible to ev
RAG your **[emails](#-search-your-entire-life)**, **[browser history](#-time-machine-for-the-web)**, **[WeChat](#-wechat-detective)**, or 60M documents on your laptop, in nearly zero cost. No cloud, no API keys, completely private. RAG your **[emails](#-search-your-entire-life)**, **[browser history](#-time-machine-for-the-web)**, **[WeChat](#-wechat-detective)**, or 60M documents on your laptop, in nearly zero cost. No cloud, no API keys, completely private.
LEANN achieves this through *graph-based selective recomputation* with *high-degree preserving pruning* and *dynamic batching*, computing embeddings on-demand instead of storing them all. [Read more →](#️-architecture--how-it-works) LEANN achieves this through *graph-based selective recomputation* with *high-degree preserving pruning*, computing embeddings on-demand instead of storing them all. [Read more →](#️-architecture--how-it-works)
## Why LEANN? ## Why LEANN?
@@ -32,7 +32,7 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
🪶 **Lightweight:** Minimal resource requirements - runs smoothly on any laptop without specialized hardware. 🪶 **Lightweight:** Minimal resource requirements - runs smoothly on any laptop without specialized hardware.
📈 **Scalability:** Orgnize our messy personal data that would crash traditional vector DBs, with performance that gets better as your data grows more personalized. 📈 **Scalability:** Organize our messy personal data that would crash traditional vector DBs, with performance that gets better as your data grows more personalized.
✨ **No Accuracy Loss:** Maintain the same search quality as heavyweight solutions while using 97% less storage. ✨ **No Accuracy Loss:** Maintain the same search quality as heavyweight solutions while using 97% less storage.