haystack/docs/_src/benchmarks/retriever_speed.json

184 lines
5.3 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": "Sentence Transformers / Elasticsearch",
"n_docs": 500000,
"query_speed": 1.4416146543448518
},
{
"model": "DPR / Elasticsearch",
"n_docs": 500000,
"query_speed": 1.4681488854743858
},
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": 48.176051675516526
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": 30.0778559137467
},
{
"model": "DPR / Elasticsearch",
"n_docs": 100000,
"query_speed": 6.239008635095737
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": 1000,
"query_speed": 258.12517634164914
},
{
"model": "BM25 / Elasticsearch",
"n_docs": 500000,
"query_speed": 67.45949681882962
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": 100000,
"query_speed": 132.02605052193084
},
{
"model": "BM25 / Elasticsearch",
"n_docs": 10000,
"query_speed": 196.51035140878585
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": 36.06325436233689
},
{
"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": 25.07636705997116
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": 100000,
"query_speed": 6.358106794217024
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": 1.5303310709494675
},
2021-06-02 13:58:55 +02:00
{
"model": "DPR / FAISS (flat)",
"n_docs": 10000,
"query_speed": 31.06388073640026
2021-06-02 13:58:55 +02:00
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 1000,
"query_speed": 35.49036694594937
},
{
"model": "DPR / FAISS (flat)",
"n_docs": 100000,
"query_speed": 6.700916380795566
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 100000,
"query_speed": 40.6580803190388
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": 10000,
"query_speed": 50.01305495228924
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": 41.538171283159
},
{
"model": "DPR / FAISS (HNSW)",
"n_docs": 500000,
"query_speed": 45.097511850660666
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 / OpenSearch (flat)",
"n_docs": 10000,
"query_speed": 173.8232982275283
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 / OpenSearch (flat)",
"n_docs": 10000,
"query_speed": 30.86623936563611
},
{
"model": "BM25 / OpenSearch (flat)",
"n_docs": 100000,
"query_speed": 120.12526583899732
},
{
"model": "BM25 / OpenSearch (flat)",
"n_docs": 1000,
"query_speed": 174.3733594241761
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 100000,
"query_speed": 17.604366772353018
},
{
"model": "BM25 / OpenSearch (flat)",
"n_docs": 500000,
"query_speed": 67.59304756122785
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 500000,
"query_speed": 12.09249157007648
},
{
"model": "DPR / OpenSearch (flat)",
"n_docs": 1000,
"query_speed": 35.35562598951788
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 10000,
"query_speed": 30.986629506879076
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 1000,
"query_speed": 35.67303735213834
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 100000,
"query_speed": 17.226750993345046
},
{
"model": "DPR / OpenSearch (HNSW)",
"n_docs": 500000,
"query_speed": 11.809321812785312
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
]
}