Skip to content

armgit / LEANN

Public Imported from GitHub
0

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

fix readme

yichuan52003091032043762d44c753
diff --git a/README.md b/README.md
index 96a990b..5c15664 100755
--- a/README.md
+++ b/README.md
@@ -69,14 +69,11 @@ uv sync
uv sync --extra diskann
```
-*We support multiple LLM providers:*
-- **Ollama** (recommended for privacy & performance)
-- **HuggingFace Transformers** (local inference)
-- **OpenAI API** (cloud-based, skip local installation if data isn't sensitive)
**Ollama Setup (Recommended for full privacy):**
+> *You can skip this installation if you only want to use OpenAI API for generation.*
*macOS:*
@@ -100,8 +97,6 @@ ollama serve &
ollama pull llama3.2:1b
```
-You can also replace `llama3.2:1b` to `deepseek-r1:1.5b` or `qwen3:4b` for better performance but higher memory usage.
-
## Dead Simple API
Just 3 lines of code. Our declarative API makes RAG as easy as writing a config file: