[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.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
docs: update -h and config advice
yichuan52003091032021f7d8e031a5
diff --git a/README.md b/README.mdindex 06403ae..8eb4daa 100755--- a/README.md+++ b/README.md@@ -190,7 +190,7 @@ All RAG examples share these common parameters. **Interactive mode** is availabl--force-rebuild # Force rebuild index even if it exists# Embedding Parameters---embedding-model MODEL # e.g., facebook/contriever, text-embedding-3-small, nomic-embed-text,mlx-community/Qwen3-Embedding-0.6B-8bit or nomic-embed-text+--embedding-model MODEL # e.g., facebook/contriever, text-embedding-3-small, mlx-community/Qwen3-Embedding-0.6B-8bit or nomic-embed-text--embedding-mode MODE # sentence-transformers, openai, mlx, or ollama# LLM Parameters (Text generation models)diff --git a/apps/base_rag_example.py b/apps/base_rag_example.pyindex 4bd62b9..df88290 100644--- a/apps/base_rag_example.py+++ b/apps/base_rag_example.py@@ -69,14 +69,14 @@ class BaseRAGExample(ABC):"--embedding-model",type=str,default=embedding_model_default,- help=f"Embedding model to use (default: {embedding_model_default})",+ help=f"Embedding model to use (default: {embedding_model_default}), we provide facebook/contriever, text-embedding-3-small,mlx-community/Qwen3-Embedding-0.6B-8bit or nomic-embed-text",)embedding_group.add_argument("--embedding-mode",type=str,default="sentence-transformers",choices=["sentence-transformers", "openai", "mlx", "ollama"],- help="Embedding backend mode (default: sentence-transformers)",+ help="Embedding backend mode (default: sentence-transformers), we provide sentence-transformers, openai, mlx, or ollama",)# LLM parameters@@ -86,13 +86,13 @@ class BaseRAGExample(ABC):type=str,default="openai",choices=["openai", "ollama", "hf", "simulated"],- help="LLM backend to use (default: openai)",+ help="LLM backend: openai, ollama, or hf (default: openai)",)llm_group.add_argument("--llm-model",type=str,default=None,- help="LLM model name (default: gpt-4o for openai, llama3.2:1b for ollama)",+ help="Model name (default: gpt-4o) e.g., gpt-4o-mini, llama3.2:1b, Qwen/Qwen2.5-1.5B-Instruct",)llm_group.add_argument("--llm-host",diff --git a/docs/configuration-guide.md b/docs/configuration-guide.mdindex 22dcaa8..49cb516 100644--- a/docs/configuration-guide.md+++ b/docs/configuration-guide.md@@ -52,7 +52,7 @@ Based on our experience developing LEANN, embedding models fall into three categ### Quick Start: Cloud and Local Embedding Options**OpenAI Embeddings (Fastest Setup)**-For immediate testing without local model downloads:+For immediate testing without local model downloads(also if you [do not have GPU](https://github.com/yichuan-w/LEANN/issues/43) and do not care that much about your document leak, you should use this, we compute the embedding and recompute using openai API):```bash# Set OpenAI embeddings (requires OPENAI_API_KEY)--embedding-mode openai --embedding-model text-embedding-3-small