haystack/docs/_src/benchmarks/retriever_speed.json

204 lines
5.8 KiB
JSON
Raw Normal View History

Create time and performance benchmarks for all readers and retrievers (#339) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * fix benchmarking for faiss hnsw queries. do sql calls in update_embeddings() as batches * update benchmarks for hnsw 128,20,80 * don't delete full index in delete_all_documents() * update texts for charts * update recall column for retriever * change scale and add units to desc * add units to legend * add axis titles. update desc * add html tags Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai> Co-authored-by: PiffPaffM <markuspaff.mp@gmail.com>
2020-10-12 13:34:42 +02:00
{
"chart_type": "LineChart",
"title": "Retriever Speed",
"subtitle": "Query Speed at different number of docs",
"description": "Here you can see how the query speed of different Retriever / DocumentStore combinations scale as the number of documents increases. The set up is the same as the above querying benchmark except that a varying number of negative documents are used to fill the document store.",
"columns": [
"n_docs",
"BM25 / Elasticsearch",
"DPR / Elasticsearch",
Create time and performance benchmarks for all readers and retrievers (#339) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * fix benchmarking for faiss hnsw queries. do sql calls in update_embeddings() as batches * update benchmarks for hnsw 128,20,80 * don't delete full index in delete_all_documents() * update texts for charts * update recall column for retriever * change scale and add units to desc * add units to legend * add axis titles. update desc * add html tags Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai> Co-authored-by: PiffPaffM <markuspaff.mp@gmail.com>
2020-10-12 13:34:42 +02:00
"DPR / FAISS (flat)",
"DPR / FAISS (HNSW)",
"DPR / Milvus (flat)",
"DPR / Milvus (HNSW)",
"Sentence Transformers / Elasticsearch"
Create time and performance benchmarks for all readers and retrievers (#339) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * fix benchmarking for faiss hnsw queries. do sql calls in update_embeddings() as batches * update benchmarks for hnsw 128,20,80 * don't delete full index in delete_all_documents() * update texts for charts * update recall column for retriever * change scale and add units to desc * add units to legend * add axis titles. update desc * add html tags Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai> Co-authored-by: PiffPaffM <markuspaff.mp@gmail.com>
2020-10-12 13:34:42 +02:00
],
"axis": [
{
"x": "Number of docs",
"y": "Queries/sec"
}
],
"data": [
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
{
"model": "DPR / Elasticsearch",
"n_docs": 1000,
"query_speed": 34.22768858415144
},
{
"model": "DPR / Elasticsearch",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 10000,
"query_speed": 22.197089725786853
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "BM25 / Elasticsearch",
"n_docs": 10000,
"query_speed": 127.11481826852273
},
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
{
"model": "Sentence Transformers / Elasticsearch",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 1000,
"query_speed": 47.51341215808855
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "Sentence Transformers / Elasticsearch",
"n_docs": 10000,
"query_speed": 29.74515869340777
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 1000,
"query_speed": 42.49634272581313
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 10000,
"query_speed": 27.684040507849826
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 1000,
"query_speed": 43.36685860983961
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 10000,
"query_speed": 41.819147130090286
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Milvus (flat)",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 1000,
"query_speed": 41.12204778755844
},
{
"model": "DPR / Milvus (flat)",
"n_docs": 10000,
"query_speed": 37.86882443918513
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Milvus (HNSW)",
"n_docs": 1000,
"query_speed": 41.14803671045185
},
{
"model": "DPR / Milvus (HNSW)",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 10000,
"query_speed": 40.072871546542935
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Elasticsearch",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 100000,
"query_speed": 5.192368815242574
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Elasticsearch",
"n_docs": 500000,
"query_speed": 1.0337466563959614
},
2021-06-02 13:58:55 +02:00
{
"model": "BM25 / Elasticsearch",
"n_docs": 100000,
"query_speed": 103.0884393334727
},
{
"model": "BM25 / Elasticsearch",
"n_docs": 500000,
"query_speed": 78.95037031647355
},
{
"model": "Sentence Transformers / Elasticsearch",
"n_docs": 100000,
"query_speed": 6.385621466857457
},
{
"model": "Sentence Transformers / Elasticsearch",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 500000,
"query_speed": 1.4175454254854258
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 100000,
"query_speed": 6.6270933964840415
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 500000,
"query_speed": 1.5394964631878052
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 100000,
"query_speed": 39.7839528511866
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 500000,
"query_speed": 39.84177061191119
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Milvus (flat)",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 100000,
"query_speed": 28.57264344960955
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
},
{
"model": "DPR / Milvus (flat)",
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
"n_docs": 500000,
"query_speed": 15.645867393099733
},
{
"model": "DPR / Milvus (HNSW)",
"n_docs": 100000,
"query_speed": 38.80526238789059
},
{
"model": "DPR / Milvus (HNSW)",
"n_docs": 500000,
"query_speed": 37.15717318924075
},
{
"model": "BM25 / Elasticsearch",
"n_docs": 1000,
"query_speed": 282.95914917837337
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 1000,
"query_speed": 29.061163356184426
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 10000,
"query_speed": 24.834414667596725
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 100000,
"query_speed": 15.306895223372484
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 1000,
"query_speed": 29.10621389658101
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 10000,
"query_speed": 26.92417300437131
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 100000,
"query_speed": 24.95733865947408
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 500000,
"query_speed": 11.33271222977541
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 500000,
"query_speed": 24.13921492357397
Add versioning docs (#495) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * versioning for docs * unsaved changes * cleaning * cleaning * Edit format of benchmarks data * update also jsons in v0.4.0 Co-authored-by: brandenchan <brandenchan@icloud.com> Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2020-10-19 11:46:51 +02:00
}
Create time and performance benchmarks for all readers and retrievers (#339) * add time and perf benchmark for es * Add retriever benchmarking * Add Reader benchmarking * add nq to squad conversion * add conversion stats * clean benchmarks * Add link to dataset * Update imports * add first support for neg psgs * Refactor test * set max_seq_len * cleanup benchmark * begin retriever speed benchmarking * Add support for retriever query index benchmarking * improve reader eval, retriever speed benchmarking * improve retriever speed benchmarking * Add retriever accuracy benchmark * Add neg doc shuffling * Add top_n * 3x speedup of SQL. add postgres docker run. make shuffle neg a param. add more logging * Add models to sweep * add option for faiss index type * remove unneeded line * change faiss to faiss_flat * begin automatic benchmark script * remove existing postgres docker for benchmarking * Add data processing scripts * Remove shuffle in script bc data already shuffled * switch hnsw setup from 256 to 128 * change es similarity to dot product by default * Error includes stack trace * Change ES default timeout * remove delete_docs() from timing for indexing * Add support for website export * update website on push to benchmarks * add complete benchmarks results * new json format * removed NaN as is not a valid json token * fix benchmarking for faiss hnsw queries. do sql calls in update_embeddings() as batches * update benchmarks for hnsw 128,20,80 * don't delete full index in delete_all_documents() * update texts for charts * update recall column for retriever * change scale and add units to desc * add units to legend * add axis titles. update desc * add html tags Co-authored-by: deepset <deepset@Crenolape.localdomain> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai> Co-authored-by: PiffPaffM <markuspaff.mp@gmail.com>
2020-10-12 13:34:42 +02:00
]
}