big-ann-benchmarks

(★ 446)

Framework for evaluating ANNS algorithms on billion scale datasets.

파일 탐색기

최종 버전 다운로드 (.zip)

- - neurips21.yml
  - neurips23.yml
- - base.py
  - base_runner.py
  - bbann.py
  - buddy_t1.py
  - cuanns_ivfpq.py
  - cuanns_multigpu.py
  - definitions.py
  - diskann-t2.py
  - diskann-v0_3.py
  - elastiknn.py
  - faiss_inmem.py
  - faiss_t1.py
  - faiss_t3.py
  - gemini.py
  - httpann.py
  - httpann_example.py
  - kota-t2.py
  - kst_t1.py
  - puck_t1.py
  - team11.py
- - __init__.py
  - eval_range_search.py
  - metrics.py
  - plot_variants.py
  - utils.py
- - power_capture.py
- - __init__.py
  - compute_gt.py
  - download_gt.py
  - load_runbook.py
- - __init__.py
  - helper.py
- __init__.py
- dataset_io.py
- datasets.py
- distances.py
- main.py
- results.py
- runner.py
- - distance_histogram.png
  - IoU.png
  - pr_compression.png
  - result_stats.png
- caselaw_dataset.md
- dino10b_dataset.md
- FB_ssnpp_dataset.md
- filter_query_set_by_num_matches.py
- filter_query_set_by_num_predicates.py
- filter_query_set_by_selectivity.py
- filter_query_set_utils.py
- filter_utils.md
- jsonl_filter_utils.py
- make_filtered_groundtruth.py
- make_groundtruth.py
- make_sparse_groundtruth.py
- multi_vector_utils.py
- prepare_bigann.py
- prepare_fb_ssnpp.py
- prepare_yfcc100m.py
- sparse_dataset.md
- yfcc_filtered_dataset.md
- yfccimages_dataset.md
- show_operating_points.py
- Dockerfile
- Dockerfile.bbann
- Dockerfile.diskann
- Dockerfile.elastiknn
- Dockerfile.faiss
- Dockerfile.faissconda
- Dockerfile.httpann_example
- Dockerfile.kota
- Dockerfile.kst_ann_t1
- Dockerfile.pqbuddy
- Dockerfile.puck
- requirements_conda.txt
- - README.md
- - LEADERBOARDS.md
  - LEADERBOARDS_PRIVATE.md
  - LEADERBOARDS_PRIVATE_REJECT_ANOMALIES.md
  - LEADERBOARDS_PUBLIC.md
  - LEADERBOARDS_PUBLIC_REJECT_ANOMALIES.md
  - LEADERBOARDS_REJECT_ANOMALIES.md
  - RANKING.md
  - README.md
  - TASKS_ISSUES_RESOLUTIONS.md
- - __init__.py
  - baseline_faiss.py
  - baseline_faiss_filtered.py
  - parse_results.py
  - README.md
  - run_baselines.bash
  - test_bow_id_selector.py
- - gpu_baseline_faiss.py
  - README.md
- README.md
- - base.py
  - install_neurips23.sh
  - operating_points_private_queries_AzureD8lds_v5.csv
  - operating_points_public_queries_AzureD8lds_v5.txt
  - plot_public_queries_AzureD8lds_v5.png
  - res_private_queries_AzureD8lds_v5.csv
  - res_public_queries_AzureD8lds_v5.csv
  - run.py
- - README.md
- - Azure_D8lds_v5_table.md
  - leaderboard.md
- - base.py
  - install_neurips23.sh
  - operating_points_public_queries_AzureD8lds_v5.txt
  - plot_public_queries_AzureD8lds_v5.png
  - res_public_queries_AzureD8lds_v5.csv
  - run.py
- - clustered_data_gen.py
  - clustered_replace_runbook.yaml
  - clustered_runbook.yaml
  - delete_runbook.yaml
  - final_runbook.yaml
  - final_runbook_gen.py
  - gen_expiration_time_runbook.py
  - gen_replace_runbooks.py
  - generate_msturing10m_runbooks.py
  - msmarco-100M_expirationtime_runbook.yaml
  - msturing-10M_slidingwindow_runbook.yaml
  - random_replace_runbook.yaml
  - simple_replace_runbook.yaml
  - simple_runbook.yaml
  - wikipedia-1M_expiration_time_replace_delete_runbook.yaml
  - wikipedia-1M_expiration_time_replace_only_runbook.yaml
  - wikipedia-1M_expiration_time_runbook.yaml
  - wikipedia-35M_expiration_time_replace_delete_runbook.yaml
  - wikipedia-35M_expiration_time_replace_only_runbook.yaml
  - wikipedia-35M_expirationtime_runbook.yaml
- - base.py
  - install_neurips23.sh
  - operating_points_private_queries_AzureD8lds_v5.csv
  - operating_points_public_queries_AzureD8lds_v5.txt
  - plot_public_queries_AzureD8lds_v5.png
  - res_private_queries_AzureD8lds_v5.csv
  - res_public_queries_AzureD8lds_v5.csv
  - run.py
- - __init__.py
  - base.py
  - README.md
  - res_final_runbook_AzureD8lds_v5.csv
  - run.py
- __init__.py
- Azure_D8lds_v5_table.md
- common.py
- Dockerfile
- ec2_c6i.2xlarge_res.csv
- ec2_c6i.2xlarge_table.md
- leaderboard.md
- README.md
- - parse_filtered_results.ipynb
- recall_tests.py
- tests.sh
.dockerignore
.gitignore
algos-2021.yaml
create_dataset.py
data_export.py
install.py
LICENSE
logging.conf
plot.py
README.md
requirements.txt
requirements_py3.10.txt
requirements_py3.12.txt
requirements_py38.txt
run.py
run_algorithm.py
setup_links.sh

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/harsha-simhadri/big-ann-benchmarks

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd big-ann-benchmarks

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Docker

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.

docker build -f install/Dockerfile -t big-ann-benchmarks .

Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.

docker run -p 8080:80 big-ann-benchmarks

빌드된 이미지를 실제 컨테이너로 실행합니다.

✅ 터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r neurips21/t3/gemini/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python run.py

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.