* 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>
* 1. Prevent update_embeddings function in FAISSDocumentStore to set faiss_index as None when document store does not have any docs.
2. cleaning up tests by adding fixture for retriever.
* TfidfRetriever need document store with documents during initialization as it call fit() function in constructor so fixing it by checking self.paragraphs of None
* Fix naming of retriever's fixture (embedded to embedding and tfid to tfidf)
* 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>
* remove phi normalization
* add special case for hnsw
* rename vector_size to vector_dim
* fix loading. fix extra dim in tests
* switch to new ES syntax for vector similarity
* 3x sql speed up. cascade deletes. add train_index()
* add docstrings. remove vector_dim from load()
* delete docs from faiss and sql
* fix delete of docs in test
* relax type hint for faiss index
* rename metric to metric_type
Co-authored-by: lalitpagaria <19303690+lalitpagaria@users.noreply.github.com>
- Fixing issue when update_embeddings always create new FAISS index instead of clearing existing one. New index creation may not free existing used memory and cause memory leak.
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* Add tests for MultiLabel
* Add test for no_answer and is_correct_answer=False + fix bug in MultiLabel aggregation
* Fix bug in MultiLabel aggregation
