Metadata-Version: 2.4
Name: leann
Version: 0.2.6
Summary: LEANN - The smallest vector index in the world. RAG Everything with LEANN!
Author: LEANN Team
License: MIT
Project-URL: Repository, https://github.com/yichuan-w/LEANN
Project-URL: Issues, https://github.com/yichuan-w/LEANN/issues
Keywords: vector-database,rag,embeddings,search,ai
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: leann-core>=0.1.0
Requires-Dist: leann-backend-hnsw>=0.1.0
Requires-Dist: leann-backend-diskann>=0.1.0

# LEANN - The smallest vector index in the world

LEANN is a revolutionary vector database that democratizes personal AI. Transform your laptop into a powerful RAG system that can index and search through millions of documents while using **97% less storage** than traditional solutions **without accuracy loss**.

## Installation

```bash
# Default installation (includes both HNSW and DiskANN backends)
uv pip install leann
```

## Quick Start

```python
from leann import LeannBuilder, LeannSearcher, LeannChat
from pathlib import Path
INDEX_PATH = str(Path("./").resolve() / "demo.leann")

# Build an index (choose backend: "hnsw" or "diskann")
builder = LeannBuilder(backend_name="hnsw")  # or "diskann" for large-scale deployments
builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
builder.add_text("Tung Tung Tung Sahur called—they need their banana‑crocodile hybrid back")
builder.build_index(INDEX_PATH)

# Search
searcher = LeannSearcher(INDEX_PATH)
results = searcher.search("fantastical AI-generated creatures", top_k=1)

# Chat with your data
chat = LeannChat(INDEX_PATH, llm_config={"type": "hf", "model": "Qwen/Qwen3-0.6B"})
response = chat.ask("How much storage does LEANN save?", top_k=1)
```

## License

MIT License
