TBNilles/LEANN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
yichuan520030910320
2025-06-30 09:05:05 +00:00
commit 46f6cc100b
1231 changed files with 278432 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
packages/leann-backend-diskann/third_party/DiskANN/.github/workflows/disk-pq.yml vendored Normal file
View File

@@ -0,0 +1,117 @@
name: Disk With PQ
on: [workflow_call]
jobs:
acceptance-tests-disk-pq:
name: Disk, PQ
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, windows-2019, windows-latest]
runs-on: ${{matrix.os}}
defaults:
run:
shell: bash
steps:
- name: Checkout repository
if: ${{ runner.os == 'Linux' }}
uses: actions/checkout@v3
with:
fetch-depth: 1
- name: Checkout repository
if: ${{ runner.os == 'Windows' }}
uses: actions/checkout@v3
with:
fetch-depth: 1
submodules: true
- name: DiskANN Build CLI Applications
uses: ./.github/actions/build
- name: Generate Data
uses: ./.github/actions/generate-random
- name: build and search disk index (one shot graph build, L2, no diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn l2 --data_path data/rand_float_10D_10K_norm1.0.bin --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_oneshot -R 16 -L 32 -B 0.00003 -M 1
dist/bin/search_disk_index --data_type float --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_oneshot --result_path /tmp/res --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/l2_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, cosine, no diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn cosine --data_path data/rand_float_10D_10K_unnorm.bin --index_path_prefix data/disk_index_cosine_rand_float_10D_10K_unnorm_diskfull_oneshot -R 16 -L 32 -B 0.00003 -M 1
dist/bin/search_disk_index --data_type float --dist_fn cosine --fail_if_recall_below 70 --index_path_prefix data/disk_index_cosine_rand_float_10D_10K_unnorm_diskfull_oneshot --result_path /tmp/res --query_file data/rand_float_10D_1K_unnorm.bin --gt_file data/cosine_rand_float_10D_10K_unnorm_10D_1K_unnorm_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, no diskPQ) (int8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type int8 --dist_fn l2 --data_path data/rand_int8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_oneshot -R 16 -L 32 -B 0.00003 -M 1
dist/bin/search_disk_index --data_type int8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_oneshot --result_path /tmp/res --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/l2_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, no diskPQ) (uint8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type uint8 --dist_fn l2 --data_path data/rand_uint8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_oneshot -R 16 -L 32 -B 0.00003 -M 1
dist/bin/search_disk_index --data_type uint8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_oneshot --result_path /tmp/res --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/l2_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, no diskPQ, build with PQ distance comparisons) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn l2 --data_path data/rand_float_10D_10K_norm1.0.bin --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_oneshot_buildpq5 -R 16 -L 32 -B 0.00003 -M 1 --build_PQ_bytes 5
dist/bin/search_disk_index --data_type float --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_oneshot_buildpq5 --result_path /tmp/res --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/l2_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, no diskPQ, build with PQ distance comparisons) (int8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type int8 --dist_fn l2 --data_path data/rand_int8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_oneshot_buildpq5 -R 16 -L 32 -B 0.00003 -M 1 --build_PQ_bytes 5
dist/bin/search_disk_index --data_type int8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_oneshot_buildpq5 --result_path /tmp/res --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/l2_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16\
- name: build and search disk index (one shot graph build, L2, no diskPQ, build with PQ distance comparisons) (uint8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type uint8 --dist_fn l2 --data_path data/rand_uint8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_oneshot_buildpq5 -R 16 -L 32 -B 0.00003 -M 1 --build_PQ_bytes 5
dist/bin/search_disk_index --data_type uint8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_oneshot_buildpq5 --result_path /tmp/res --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/l2_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (sharded graph build, L2, no diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn l2 --data_path data/rand_float_10D_10K_norm1.0.bin --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_sharded -R 16 -L 32 -B 0.00003 -M 0.00006
dist/bin/search_disk_index --data_type float --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskfull_sharded --result_path /tmp/res --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/l2_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (sharded graph build, cosine, no diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn cosine --data_path data/rand_float_10D_10K_unnorm.bin --index_path_prefix data/disk_index_cosine_rand_float_10D_10K_unnorm_diskfull_sharded -R 16 -L 32 -B 0.00003 -M 0.00006
dist/bin/search_disk_index --data_type float --dist_fn cosine --fail_if_recall_below 70 --index_path_prefix data/disk_index_cosine_rand_float_10D_10K_unnorm_diskfull_sharded --result_path /tmp/res --query_file data/rand_float_10D_1K_unnorm.bin --gt_file data/cosine_rand_float_10D_10K_unnorm_10D_1K_unnorm_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (sharded graph build, L2, no diskPQ) (int8)
run: |
dist/bin/build_disk_index --data_type int8 --dist_fn l2 --data_path data/rand_int8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_sharded -R 16 -L 32 -B 0.00003 -M 0.00006
dist/bin/search_disk_index --data_type int8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskfull_sharded --result_path /tmp/res --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/l2_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (sharded graph build, L2, no diskPQ) (uint8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type uint8 --dist_fn l2 --data_path data/rand_uint8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_sharded -R 16 -L 32 -B 0.00003 -M 0.00006
dist/bin/search_disk_index --data_type uint8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskfull_sharded --result_path /tmp/res --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/l2_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn l2 --data_path data/rand_float_10D_10K_norm1.0.bin --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskpq_oneshot -R 16 -L 32 -B 0.00003 -M 1 --PQ_disk_bytes 5
dist/bin/search_disk_index --data_type float --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_float_10D_10K_norm1.0_diskpq_oneshot --result_path /tmp/res --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/l2_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, diskPQ) (int8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type int8 --dist_fn l2 --data_path data/rand_int8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskpq_oneshot -R 16 -L 32 -B 0.00003 -M 1 --PQ_disk_bytes 5
dist/bin/search_disk_index --data_type int8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_int8_10D_10K_norm50.0_diskpq_oneshot --result_path /tmp/res --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/l2_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (one shot graph build, L2, diskPQ) (uint8)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type uint8 --dist_fn l2 --data_path data/rand_uint8_10D_10K_norm50.0.bin --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskpq_oneshot -R 16 -L 32 -B 0.00003 -M 1 --PQ_disk_bytes 5
dist/bin/search_disk_index --data_type uint8 --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_l2_rand_uint8_10D_10K_norm50.0_diskpq_oneshot --result_path /tmp/res --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/l2_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: build and search disk index (sharded graph build, MIPS, diskPQ) (float)
if: success() || failure()
run: |
dist/bin/build_disk_index --data_type float --dist_fn mips --data_path data/rand_float_10D_10K_norm1.0.bin --index_path_prefix data/disk_index_mips_rand_float_10D_10K_norm1.0_diskpq_sharded -R 16 -L 32 -B 0.00003 -M 0.00006 --PQ_disk_bytes 5
dist/bin/search_disk_index --data_type float --dist_fn l2 --fail_if_recall_below 70 --index_path_prefix data/disk_index_mips_rand_float_10D_10K_norm1.0_diskpq_sharded --result_path /tmp/res --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/mips_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --recall_at 5 -L 5 12 -W 2 --num_nodes_to_cache 10 -T 16
- name: upload data and bin
uses: actions/upload-artifact@v4
with:
name: disk-pq-${{matrix.os}}
path: |
./dist/**
./data/**