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

add pip install option to README

Browse Source
This commit is contained in:
yichuan520030910320
2025-07-27 02:06:40 -07:00
parent a7cba078dd
commit 8596562de5
1 changed files with 19 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@@ -38,7 +38,19 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
✨ **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.
## Installation ## Installation
> `pip leann` coming soon!
LEANN provides two installation methods: **pip install** (quick and easy) and **build from source** (recommended for development).
### 🚀 Quick Install (Recommended for most users)
```bash
pip install leann
```
### 🔧 Build from Source (Recommended for development)
For development, we recommend building from source:
```bash ```bash
git clone git@github.com:yichuan-w/LEANN.git leann git clone git@github.com:yichuan-w/LEANN.git leann
cd leann cd leann
@@ -65,7 +77,7 @@ uv sync
``` ```
**Ollama Setup (Recommended for full privacy):** <!-- **Ollama Setup (Recommended for full privacy):**
> *You can skip this installation if you only want to use OpenAI API for generation.* > *You can skip this installation if you only want to use OpenAI API for generation.*
@@ -89,7 +101,7 @@ ollama serve &
# Pull a lightweight model (recommended for consumer hardware) # Pull a lightweight model (recommended for consumer hardware)
ollama pull llama3.2:1b ollama pull llama3.2:1b
``` ``` -->
## Quick Start in 30s ## Quick Start in 30s
@@ -465,4 +477,3 @@ This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.e
<p align="center"> <p align="center">
Made with ❤️ by the Leann team Made with ❤️ by the Leann team
</p> </p>