| Name | leann JSON |
| Version |
0.3.4
JSON |
| download |
| home_page | None |
| Summary | LEANN - The smallest vector index in the world. RAG Everything with LEANN! |
| upload_time | 2025-09-18 21:51:34 |
| maintainer | None |
| docs_url | None |
| author | LEANN Team |
| requires_python | >=3.9 |
| license | MIT |
| keywords |
vector-database
rag
embeddings
search
ai
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 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
Raw data
{
"_id": null,
"home_page": null,
"name": "leann",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "vector-database, rag, embeddings, search, ai",
"author": "LEANN Team",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/d8/05/532ed3581eb5528bbfed74f120578c83002a44098203634f1b87f3dbeb47/leann-0.3.4.tar.gz",
"platform": null,
"description": "# LEANN - The smallest vector index in the world\n\nLEANN 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**.\n\n## Installation\n\n```bash\n# Default installation (includes both HNSW and DiskANN backends)\nuv pip install leann\n```\n\n## Quick Start\n\n```python\nfrom leann import LeannBuilder, LeannSearcher, LeannChat\nfrom pathlib import Path\nINDEX_PATH = str(Path(\"./\").resolve() / \"demo.leann\")\n\n# Build an index (choose backend: \"hnsw\" or \"diskann\")\nbuilder = LeannBuilder(backend_name=\"hnsw\") # or \"diskann\" for large-scale deployments\nbuilder.add_text(\"LEANN saves 97% storage compared to traditional vector databases.\")\nbuilder.add_text(\"Tung Tung Tung Sahur called\u2014they need their banana\u2011crocodile hybrid back\")\nbuilder.build_index(INDEX_PATH)\n\n# Search\nsearcher = LeannSearcher(INDEX_PATH)\nresults = searcher.search(\"fantastical AI-generated creatures\", top_k=1)\n\n# Chat with your data\nchat = LeannChat(INDEX_PATH, llm_config={\"type\": \"hf\", \"model\": \"Qwen/Qwen3-0.6B\"})\nresponse = chat.ask(\"How much storage does LEANN save?\", top_k=1)\n```\n\n## License\n\nMIT License\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "LEANN - The smallest vector index in the world. RAG Everything with LEANN!",
"version": "0.3.4",
"project_urls": {
"Issues": "https://github.com/yichuan-w/LEANN/issues",
"Repository": "https://github.com/yichuan-w/LEANN"
},
"split_keywords": [
"vector-database",
" rag",
" embeddings",
" search",
" ai"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "04275c0a45d6e7a1b5c06479501ad5d05e99900c1597762475c06ceadf3f1108",
"md5": "237a5e3f114d23fca61a36b1c5be7b04",
"sha256": "78d4f86b629f6805aeb3b491c5a1213db74ff0328f46064635d56cabefc51695"
},
"downloads": -1,
"filename": "leann-0.3.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "237a5e3f114d23fca61a36b1c5be7b04",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 1917,
"upload_time": "2025-09-18T21:49:49",
"upload_time_iso_8601": "2025-09-18T21:49:49.886217Z",
"url": "https://files.pythonhosted.org/packages/04/27/5c0a45d6e7a1b5c06479501ad5d05e99900c1597762475c06ceadf3f1108/leann-0.3.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d805532ed3581eb5528bbfed74f120578c83002a44098203634f1b87f3dbeb47",
"md5": "76501ce65096783a71a2a85ab30e31f5",
"sha256": "da281f5fc8d9024f950c6bea4766189718766e48edf33c96f1c38a4845eea344"
},
"downloads": -1,
"filename": "leann-0.3.4.tar.gz",
"has_sig": false,
"md5_digest": "76501ce65096783a71a2a85ab30e31f5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 2115,
"upload_time": "2025-09-18T21:51:34",
"upload_time_iso_8601": "2025-09-18T21:51:34.626475Z",
"url": "https://files.pythonhosted.org/packages/d8/05/532ed3581eb5528bbfed74f120578c83002a44098203634f1b87f3dbeb47/leann-0.3.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-18 21:51:34",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yichuan-w",
"github_project": "LEANN",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "leann"
}
