leann 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,66 @@
1
+ Metadata-Version: 2.4
2
+ Name: leann
3
+ Version: 0.1.0
4
+ Summary: LEANN - The smallest vector index in the world. RAG Everything with LEANN!
5
+ Author: LEANN Team
6
+ License: MIT
7
+ Project-URL: Homepage, https://github.com/yourusername/leann
8
+ Project-URL: Documentation, https://leann.readthedocs.io
9
+ Project-URL: Repository, https://github.com/yourusername/leann
10
+ Project-URL: Issues, https://github.com/yourusername/leann/issues
11
+ Keywords: vector-database,rag,embeddings,search,ai
12
+ Classifier: Development Status :: 4 - Beta
13
+ Classifier: Intended Audience :: Developers
14
+ Classifier: License :: OSI Approved :: MIT License
15
+ Classifier: Programming Language :: Python :: 3
16
+ Classifier: Programming Language :: Python :: 3.9
17
+ Classifier: Programming Language :: Python :: 3.10
18
+ Classifier: Programming Language :: Python :: 3.11
19
+ Classifier: Programming Language :: Python :: 3.12
20
+ Requires-Python: >=3.9
21
+ Description-Content-Type: text/markdown
22
+ Requires-Dist: leann-core>=0.1.0
23
+ Requires-Dist: leann-backend-hnsw>=0.1.0
24
+ Provides-Extra: diskann
25
+ Requires-Dist: leann-backend-diskann>=0.1.0; extra == "diskann"
26
+
27
+ # LEANN - The smallest vector index in the world
28
+
29
+ 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**.
30
+
31
+ ## Installation
32
+
33
+ ```bash
34
+ # Default installation (HNSW backend, recommended)
35
+ pip install leann
36
+
37
+ # With DiskANN backend (Linux only, for large-scale deployments)
38
+ pip install leann[diskann]
39
+ ```
40
+
41
+ ## Quick Start
42
+
43
+ ```python
44
+ from leann import LeannBuilder, LeannSearcher, LeannChat
45
+
46
+ # Build an index
47
+ builder = LeannBuilder(backend_name="hnsw")
48
+ builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
49
+ builder.build_index("my_index.leann")
50
+
51
+ # Search
52
+ searcher = LeannSearcher("my_index.leann")
53
+ results = searcher.search("storage savings", top_k=3)
54
+
55
+ # Chat with your data
56
+ chat = LeannChat("my_index.leann", llm_config={"type": "ollama", "model": "llama3.2:1b"})
57
+ response = chat.ask("How much storage does LEANN save?")
58
+ ```
59
+
60
+ ## Documentation
61
+
62
+ For full documentation, visit [https://leann.readthedocs.io](https://leann.readthedocs.io)
63
+
64
+ ## License
65
+
66
+ MIT License
@@ -0,0 +1,4 @@
1
+ leann-0.1.0.dist-info/METADATA,sha256=_Q7lZq34eq3lShA_XF67Y-oyz32UNf6cPB3-KerXCTY,2271
2
+ leann-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
3
+ leann-0.1.0.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
4
+ leann-0.1.0.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (80.9.0)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1 @@
1
+