Skip to content

Commit

Permalink
Initial implementation of flat vector search (#2510)
Browse files Browse the repository at this point in the history
1st installment (of many to come): current implementation checked with BEIR BGE (cached queries).
no quantized yet; no ONNX yet - both to come.
  • Loading branch information
lintool authored May 30, 2024
1 parent dcca41a commit 2152338
Show file tree
Hide file tree
Showing 277 changed files with 3,661 additions and 264 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-arguana-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-arguana-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-arguana-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-arguana-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-bioasq-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 500 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-bioasq-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 500 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-bioasq-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 500 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-bioasq-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 500 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-climate-fever-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-climate-fever-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-climate-fever-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-climate-fever-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-android-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-android-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-android-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-android-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-english-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-english-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-english-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-english-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gaming-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gaming-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gaming-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gaming-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gis-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gis-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gis-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-gis-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-physics-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-physics-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-physics-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-physics-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-programmers-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-programmers-bge-base-en-v1.5-int8/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge -quantize.int8 \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-programmers-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Sample indexing command, building HNSW indexes:
bin/run.sh io.anserini.index.IndexHnswDenseVectors \
-collection JsonDenseVectorCollection \
-input /path/to/beir-v1.0.0-bge-base-en-v1.5 \
-generator HnswDenseVectorDocumentGenerator \
-generator DenseVectorDocumentGenerator \
-index indexes/lucene-hnsw.beir-v1.0.0-cqadupstack-programmers-bge-base-en-v1.5/ \
-threads 16 -M 16 -efC 100 -memoryBuffer 65536 -noMerge \
>& logs/log.beir-v1.0.0-bge-base-en-v1.5 &
Expand Down
Loading

0 comments on commit 2152338

Please sign in to comment.