diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.cached.md index c2e4f7fb54..aadb9dca89 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-arguana.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-arguana.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.onnx.md index 2978b169d2..36b70a9940 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-arguana.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-arguana.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.cached.md index 49b9ecbc53..1c4a661807 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-arguana.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-arguana.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.onnx.md index 0fd17629c8..e2398d396f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-arguana.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-arguana.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.cached.md index eaa77f5efe..8c43e89913 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-bioasq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-bioasq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.onnx.md index 3aec45cc05..f5303381a3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-bioasq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-bioasq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.cached.md index 40d623cec5..012bd314c6 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-bioasq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-bioasq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.onnx.md index 45ce82ae41..c5dfa39e04 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-bioasq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-bioasq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.cached.md index 93631b396b..f780b07bb1 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-climate-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.onnx.md index 6f1c6fc21e..8aeef0dcea 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-climate-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.cached.md index 1fc3402b8b..74fe99e81f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-climate-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.onnx.md index 215c009072..0b280e4826 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-climate-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.cached.md index 6c707bf2a7..17db8d4c39 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.onnx.md index 2c22129693..94fc171b44 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.cached.md index da51e55dac..7a8cd75b88 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.onnx.md index 2f83356077..c686075748 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.cached.md index c4952d1ad4..23c379de42 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.onnx.md index 9768beb643..422178ea65 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.cached.md index 7425edb5bf..8c9403eebd 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.onnx.md index c09e638f4d..4ca382a07e 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.cached.md index b433ebd7f8..06c4f1cfd1 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.onnx.md index 17b634f8c8..a4291c6956 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.cached.md index 63e6bb3c70..8984643f3b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.onnx.md index 7e9e1df333..fd5a772f69 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.cached.md index ad2fafd987..2e0696e75c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.onnx.md index 2f407a171f..bbc942be1e 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.cached.md index ccfecc3580..aba567e7f4 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.onnx.md index d108ce0b12..1b2188d643 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.cached.md index 8125dae548..4c2c3414c0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.onnx.md index 5ad5409157..a7452af3e2 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.cached.md index dba91cce43..998a33ae99 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.onnx.md index 0c4467b015..1fa1dbe6dd 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.cached.md index cb3b675444..34444476ad 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.onnx.md index 2aaecc8d67..a00220c7c9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.cached.md index 17d063fb44..710804771c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.onnx.md index c89b89e4ce..2bfc1ea826 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.cached.md index caf215e037..3b5874a02e 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.onnx.md index bed428305d..43889b225b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.cached.md index 0de657a270..bafb4399f0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.onnx.md index ea63e9e298..34b165d65f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.cached.md index 2b1b0535f4..c3b9b76fbc 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.onnx.md index ac87163885..00db6f3170 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.cached.md index 14f6261466..fc576f7c56 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.onnx.md index d2995104a4..b8cb0d15fd 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.cached.md index 5982ebd6fc..47ad22269b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.onnx.md index 20c6ad78a9..0426e46c71 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.cached.md index bb15c436f5..a9b7e2eab1 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.onnx.md index e4ee54e8bc..d7c4787e1d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.cached.md index eda2180b64..43ce3663d2 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.onnx.md index 399f796629..994a27f8b6 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.cached.md index 098e5a10d0..e71d48e442 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.onnx.md index 46008603d8..6848849c54 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.cached.md index 72079d81b1..94761d2c7c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.onnx.md index 0b0071e332..3389e5acee 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.cached.md index e392d769aa..d4ea4013c0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.onnx.md index e279357102..3656d252e9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.cached.md index 44cb1cfc59..6f1ab97dea 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.onnx.md index 45280d1bbd..fc6d829c49 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.cached.md index a544772483..6cab32cd57 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.onnx.md index 0db22b07a5..e67abbe091 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.cached.md index 047e1751d5..b8aa529775 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.onnx.md index e1006cd3fb..c2bd95894a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.cached.md index df65ddf765..7e5895a1e3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.onnx.md index 69036de015..415a38ca29 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.cached.md index a882f65a78..9d9c003a33 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.onnx.md index c54d0ff0a2..cece11f6d0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.cached.md index 5b8496e249..9e41d18fb3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.onnx.md index 4e25c013ee..dc004abb39 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fever.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-fever.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.cached.md index b0b6772b5c..73c3e26ff9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fiqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-fiqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.onnx.md index 052ae2b55c..ec6c8f1b95 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fiqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-fiqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.cached.md index 3b47fa58cf..7eaebe238c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fiqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-fiqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.onnx.md index dde5a87098..1b90211ddc 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-fiqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-fiqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.cached.md index 2bbd7740b0..7c72365d75 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-hotpotqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.onnx.md index b04928c633..5d0355cbc5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-hotpotqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.cached.md index 96d710c8f3..74ced07807 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-hotpotqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.onnx.md index 77a976cf61..3bb1f95e02 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-hotpotqa.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.cached.md index f764583e72..80c3c73804 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-nfcorpus.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.onnx.md index 3a7a5df5d5..32f44f907a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-nfcorpus.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.cached.md index 6a83b60414..9699bc3200 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-nfcorpus.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.onnx.md index d65e0f0dd3..6b8aaf36e7 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-nfcorpus.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.cached.md index 2bf6e83b36..d213283209 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-nq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.onnx.md index 7d1a2a1bb8..5dcfa7107c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-nq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.cached.md index 752711c834..e7713b597a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-nq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.onnx.md index b1680c9112..c90dfc691c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-nq.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-nq.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.cached.md index fc233c3964..77e7fdd330 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-quora.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-quora.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.onnx.md index f9a9c1b1c9..0a489c82be 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-quora.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-quora.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.cached.md index b4c534de2c..f8975835aa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-quora.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-quora.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.onnx.md index b6f90d9bea..dadb31eda5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-quora.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-quora.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.cached.md index b18044d854..daefc1d92f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-robust04.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-robust04.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.onnx.md index 512bbad85b..419cb9fa11 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-robust04.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-robust04.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.cached.md index 6d8f2c8149..f0ed645acd 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-robust04.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-robust04.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.onnx.md index 1b9b0de01a..17a73a216b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-robust04.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-robust04.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.cached.md index 314f593b33..423abc1c79 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scidocs.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-scidocs.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.onnx.md index 056badc8eb..de2f27460d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scidocs.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-scidocs.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.cached.md index 1039872930..08ea94cf2b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scidocs.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-scidocs.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.onnx.md index 1269c55430..09fc06a6d9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scidocs.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-scidocs.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.cached.md index 782e6e5b80..0abf5ff58f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scifact.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-scifact.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.onnx.md index f116196882..bcd97a37ac 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scifact.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-scifact.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.cached.md index d1fdebb4b6..4e5130a711 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scifact.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-scifact.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.onnx.md index afefda1447..fe2d9cd035 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-scifact.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-scifact.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.cached.md index c9ce948832..ff5d7fa9ca 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-signal1m.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-signal1m.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.onnx.md index 173f369242..087f74441d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-signal1m.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-signal1m.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.cached.md index 3fa194fa80..81952bab7b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-signal1m.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-signal1m.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.onnx.md index 7fd8afda9d..6838b6cf14 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-signal1m.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-signal1m.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.cached.md index 2f83181216..efe6713722 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-trec-covid.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.onnx.md index 97f6d3f042..9a480802fc 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-trec-covid.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.cached.md index 20853d0def..b8aae72baa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-trec-covid.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.onnx.md index 36e8ddfa39..b6eb4e68b2 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-trec-covid.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.cached.md index cf1d4066ea..d9759a59ad 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-news.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-trec-news.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.onnx.md index 78ba8d4bcf..3a8b994f88 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-news.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-trec-news.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.cached.md index 575337a962..0c90cd6e48 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-news.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-trec-news.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.onnx.md index fb19a7da7b..65ef40ee8d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-trec-news.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-trec-news.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.cached.md index 292fd48bba..e2889fa619 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.onnx.md index ae6eba7020..a4b9c051d8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat-int8.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building quantized flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.cached.md index 25e9cb9c0c..a7a6d1784c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.cached.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.onnx.md index 589ffa1240..024a5b9370 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat.onnx.md @@ -32,7 +32,7 @@ After download and unpacking the corpora, the `run_regression.py` command above Sample indexing command, building flat indexes: ``` -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020.bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -50,7 +50,7 @@ Topics and qrels are stored [here](https://github.com/castorini/anserini-tools/t After indexing has completed, you should be able to perform retrieval as follows: ``` -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.tsv.gz \ -topicReader TsvString \ diff --git a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.cached.md index e4ebbebe05..e2aa4ab380 100644 --- a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl19-passage.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.onnx.md index ec809a3ec9..f0ca3d5cf9 100644 --- a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat-int8.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.cached.md index 6c42e9a6ab..0054e0cc53 100644 --- a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl19-passage.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.onnx.md index 3a8d7b2453..5fdbabf453 100644 --- a/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-dl19-passage.bge-base-en-v1.5.flat.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat-int8.cached.md b/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat-int8.cached.md index e8d1e33a56..d3a220318d 100644 --- a/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat-int8.cached.md +++ b/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat-int8.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -68,7 +68,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat.cached.md b/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat.cached.md index f110f1c93e..379bbc98fd 100644 --- a/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat.cached.md +++ b/docs/regressions/regressions-dl19-passage.cohere-embed-english-v3.0.flat.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -68,7 +68,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.cached.md b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.cached.md index e490cbfc5e..ffeb61aaf0 100644 --- a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.cached.md +++ b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.onnx.md b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.onnx.md index d593ffefdf..f5c8d77ff1 100644 --- a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.onnx.md +++ b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat-int8.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.cached.md b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.cached.md index 0f9c561a59..2431761424 100644 --- a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.cached.md +++ b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.onnx.md b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.onnx.md index 5c2d912f80..5db97fb66d 100644 --- a/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.onnx.md +++ b/docs/regressions/regressions-dl19-passage.cos-dpr-distil.flat.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl19-passage.openai-ada2.flat-int8.cached.md b/docs/regressions/regressions-dl19-passage.openai-ada2.flat-int8.cached.md index f7af596259..cc9c3a0a4e 100644 --- a/docs/regressions/regressions-dl19-passage.openai-ada2.flat-int8.cached.md +++ b/docs/regressions/regressions-dl19-passage.openai-ada2.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl19-passage.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl19-passage.openai-ada2.flat.cached.md b/docs/regressions/regressions-dl19-passage.openai-ada2.flat.cached.md index 1e9d458d7e..dc33f4e39a 100644 --- a/docs/regressions/regressions-dl19-passage.openai-ada2.flat.cached.md +++ b/docs/regressions/regressions-dl19-passage.openai-ada2.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2019.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl19-passage.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.cached.md index 3632387c88..3a80d6b35e 100644 --- a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl20.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.onnx.md index fc54a93138..e020ed3264 100644 --- a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat-int8.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.cached.md index 6c50c6f441..8d187a4600 100644 --- a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl20.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.onnx.md index 61f2381ee0..260570c9a4 100644 --- a/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-dl20-passage.bge-base-en-v1.5.flat.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat-int8.cached.md b/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat-int8.cached.md index 725547f160..fc65ef7373 100644 --- a/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat-int8.cached.md +++ b/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat-int8.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -68,7 +68,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.dl20.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat.cached.md b/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat.cached.md index 57de997741..7742347275 100644 --- a/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat.cached.md +++ b/docs/regressions/regressions-dl20-passage.cohere-embed-english-v3.0.flat.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -68,7 +68,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.dl20.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.cached.md b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.cached.md index 66d954ff0a..57158710b9 100644 --- a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.cached.md +++ b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.onnx.md b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.onnx.md index f155791784..28e97cffef 100644 --- a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.onnx.md +++ b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat-int8.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.cached.md b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.cached.md index 229270703f..5ab0376277 100644 --- a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.cached.md +++ b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.onnx.md b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.onnx.md index b5bcaeb12f..1b44eac7b2 100644 --- a/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.onnx.md +++ b/docs/regressions/regressions-dl20-passage.cos-dpr-distil.flat.onnx.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-dl20-passage.openai-ada2.flat-int8.cached.md b/docs/regressions/regressions-dl20-passage.openai-ada2.flat-int8.cached.md index 604ff127b8..4a344d72d3 100644 --- a/docs/regressions/regressions-dl20-passage.openai-ada2.flat-int8.cached.md +++ b/docs/regressions/regressions-dl20-passage.openai-ada2.flat-int8.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl20.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-dl20-passage.openai-ada2.flat.cached.md b/docs/regressions/regressions-dl20-passage.openai-ada2.flat.cached.md index eb6dc2d268..f4ed318607 100644 --- a/docs/regressions/regressions-dl20-passage.openai-ada2.flat.cached.md +++ b/docs/regressions/regressions-dl20-passage.openai-ada2.flat.cached.md @@ -52,7 +52,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -73,7 +73,7 @@ The original data can be found [here](https://trec.nist.gov/data/deep2020.html). After indexing has completed, you should be able to perform retrieval as follows: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl20.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.cached.md b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.cached.md index b192407bee..6709c23583 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.onnx.md b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.onnx.md index c952f0d51a..fc5706e1eb 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.onnx.md +++ b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat-int8.onnx.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.cached.md b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.cached.md index 13219a1477..b85ba9b02b 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.onnx.md b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.onnx.md index 940cb41ed1..de752f7794 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.onnx.md +++ b/docs/regressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.flat.onnx.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-bge-base-en-v1.5 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat-int8.cached.md b/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat-int8.cached.md index e4ff49d07b..91197c05bc 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat-int8.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat-int8.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -67,7 +67,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached.md b/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached.md index c71dd2e9e9..2272a2a318 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cohere-embed-english-v3.0.flat.cached.md @@ -47,7 +47,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \ -generator DenseVectorDocumentGenerator \ @@ -67,7 +67,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cohere-embed-english-v3.0/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.cached.md b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.cached.md index 9f026eca2f..f995d1c560 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.onnx.md b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.onnx.md index 86b6cf7c7b..6f48cca77d 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.onnx.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat-int8.onnx.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.cached.md b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.cached.md index 5af3fbd187..6ccb145e44 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.onnx.md b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.onnx.md index 923b9d3a11..505e62854b 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.onnx.md +++ b/docs/regressions/regressions-msmarco-v1-passage.cos-dpr-distil.flat.onnx.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ -topicReader TsvInt \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat-int8.cached.md b/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat-int8.cached.md index fc935316b9..a4687243ef 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat-int8.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat-int8.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building quantized flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat-int8.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat.cached.md b/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat.cached.md index 6bcba8f1db..32c2b25ef0 100644 --- a/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat.cached.md +++ b/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.flat.cached.md @@ -49,7 +49,7 @@ python src/main/python/run_regression.py --index --verify --search --regression Sample indexing command, building flat indexes: ```bash -bin/run.sh io.anserini.index.IndexCollection \ +bin/run.sh io.anserini.index.IndexFlatDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ -generator DenseVectorDocumentGenerator \ @@ -69,7 +69,7 @@ The regression experiments here evaluate on the 6980 dev set questions; see [thi After indexing has completed, you should be able to perform retrieval as follows using HNSW indexes: ```bash -bin/run.sh io.anserini.search.SearchCollection \ +bin/run.sh io.anserini.search.SearchFlatDenseVectors \ -index indexes/lucene-flat.msmarco-v1-passage.openai-ada2/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.openai-ada2.jsonl.gz \ -topicReader JsonIntVector \ diff --git a/src/test/java/io/anserini/doc/DataModel.java b/src/test/java/io/anserini/doc/DataModel.java index 7a2b44dc06..f62ad79399 100755 --- a/src/test/java/io/anserini/doc/DataModel.java +++ b/src/test/java/io/anserini/doc/DataModel.java @@ -27,10 +27,12 @@ public class DataModel { private static final String INDEX_COMMAND = "bin/run.sh io.anserini.index.IndexCollection"; private static final String INDEX_HNSW_COMMAND = "bin/run.sh io.anserini.index.IndexHnswDenseVectors"; + private static final String INDEX_FLAT_COMMAND = "bin/run.sh io.anserini.index.IndexFlatDenseVectors"; private static final String INDEX_INVERTED_DENSE_COMMAND = "bin/run.sh io.anserini.index.IndexInvertedDenseVectors"; private static final String SEARCH_COMMAND = "bin/run.sh io.anserini.search.SearchCollection"; private static final String SEARCH_HNSW_COMMAND = "bin/run.sh io.anserini.search.SearchHnswDenseVectors"; + private static final String SEARCH_FLAT_COMMAND = "bin/run.sh io.anserini.search.SearchFlatDenseVectors"; private static final String SEARCH_INVERTED_DENSE_COMMAND = "bin/run.sh io.anserini.search.SearchInvertedDenseVectors"; private String corpus; @@ -280,6 +282,8 @@ public String generateIndexingCommand(String collection) { String indexCommand = INDEX_COMMAND; if ("hnsw".equals(getIndex_type())) { indexCommand = INDEX_HNSW_COMMAND; + } else if ("flat".equals(getIndex_type())) { + indexCommand = INDEX_FLAT_COMMAND; } else if ("inverted-dense".equals(getIndex_type())) { indexCommand = INDEX_INVERTED_DENSE_COMMAND; } @@ -319,6 +323,8 @@ public String generateRankingCommand(String collection) { String searchCommand = SEARCH_COMMAND; if ("hnsw".equals(model.getType())) { searchCommand = SEARCH_HNSW_COMMAND; + } else if ("flat".equals(model.getType())) { + searchCommand = SEARCH_FLAT_COMMAND; } else if ("inverted-dense".equals(model.getType())) { searchCommand = SEARCH_INVERTED_DENSE_COMMAND; }