From e872dd1d23ed92bf1c9726463a8572ee70c78c81 Mon Sep 17 00:00:00 2001 From: Andy Lee Date: Mon, 4 Aug 2025 17:51:21 -0700 Subject: [PATCH] docs: Weaken DiskANN emphasis in README - Change backend description to emphasize HNSW as default - DiskANN positioned as optional for billion-scale datasets - Simplify evaluation commands to be more generic --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 3b8e2cd..600efa4 100755 --- a/README.md +++ b/README.md @@ -516,7 +516,7 @@ Options: - **Dynamic batching:** Efficiently batch embedding computations for GPU utilization - **Two-level search:** Smart graph traversal that prioritizes promising nodes -**Backends:** DiskANN or HNSW - pick what works for your data size. +**Backends:** HNSW (default) for most use cases, with optional DiskANN support for billion-scale datasets. ## Benchmarks @@ -536,8 +536,7 @@ Options: ```bash uv pip install -e ".[dev]" # Install dev dependencies -python benchmarks/run_evaluation.py data/indices/dpr/dpr_diskann # DPR dataset -python benchmarks/run_evaluation.py data/indices/rpj_wiki/rpj_wiki.index # Wikipedia +python benchmarks/run_evaluation.py # Will auto-download evaluation data and run benchmarks ``` The evaluation script downloads data automatically on first run. The last three results were tested with partial personal data, and you can reproduce them with your own data!