dl20-passage.openai-ada2.parquet.hnsw.cached.yaml

---
corpus: msmarco-passage-openai-ada2.parquet
corpus_path: collections/msmarco/msmarco-passage-openai-ada2.parquet/

download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-openai-ada2.parquet.tar
download_checksum: fa3637e9c4150b157270e19ef3a4f779

index_path: indexes/lucene-hnsw.msmarco-v1-passage.openai-ada2/
index_type: hnsw
collection_class: ParquetDenseVectorCollection
generator_class: ParquetDenseVectorDocumentGenerator
index_threads: 16
index_options: -M 16 -efC 100

metrics:
  - metric: AP@1000
    command: bin/trec_eval
    params: -m map -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: nDCG@10
    command: bin/trec_eval
    params: -m ndcg_cut.10 -c
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: bin/trec_eval
    params: -m recall.100 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: bin/trec_eval
    params: -m recall.1000 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: JsonIntVector
topics:
  - name: "[DL20 (Passage)](https://trec.nist.gov/data/deep2020.html)"
    id: dl20
    path: topics.dl20.openai-ada2.jsonl.gz
    qrel: qrels.dl20-passage.txt

models:
  - name: openai-ada2-hnsw-cached
    display: OpenAI-ada2
    type: hnsw
    params: -hits 1000 -efSearch 1000 -threads 16
    results:
      AP@1000:
        - 0.4771
      nDCG@10:
        - 0.6759
      R@100:
        - 0.7237
      R@1000:
        - 0.8705
    tolerance:
      AP@1000:
        - 0.001
      nDCG@10:
        - 0.001
      R@100:
        - 0.003
      R@1000:
        - 0.009