SIGN IN SIGN UP
yichuan-w / LEANN UNCLAIMED

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

0 0 1 Python

TAGS

20 tags
v0.3.7

fix(ci): check pkg-config.exe exists instead of choco exit code choco install exits 0 even when it installs 0/0 packages (e.g. on 504 Gateway Timeout from chocolatey.org), so the fallback never triggered. Check the binary actually exists on disk instead. Made-with: Cursor

v0.3.6

fix(ci): use Python 3.13 in Arch Linux smoke test Arch Linux has upgraded to Python 3.14, but tokenizers/PyO3 only supports up to Python 3.13. Use uv to install and manage Python 3.13 explicitly instead of relying on system Python.

v0.3.4

[Fix] Enable AST chunking when installed (package chunking utils) (#101) * fix(core): package chunking utils for AST chunking; re-export in apps; CLI imports packaged utils * style * chore: fix ruff warnings (RUF059, F401) * style

v0.3.0

feat: Add Google Gemini API support for chat and embeddings (#57) - Add GeminiChat class with gemini-2.5-flash model support - Add compute_embeddings_gemini function with text-embedding-004 model - Update get_llm factory to support "gemini" type - Update API documentation to include gemini embedding mode - Support temperature, max_tokens, top_p parameters for Gemini chat - Support batch embedding processing with progress bars - Add proper error handling and API key validation

v0.2.0

feat: implement smart memory configuration for DiskANN (#16) - Add intelligent memory calculation based on data size and system specs - search_memory_maximum: 1/10 of embedding size (controls PQ compression) - build_memory_maximum: 50% of available RAM (controls sharding) - Provides optimal balance between performance and memory usage - Automatic fallback to default values if parameters are explicitly provided