* upgrade to pytorch 1.10 and transformers 4.11.3
* pin torch to 1.9.1
* Upgrade transformers and torch to 4.12.2 and 1.10.0
* Test transformers 4.10.2
* Pin transformers to 4.10.2
* transformers 4.10.3
* transformers 4.11.0
* transformers 4.11.1
* transformers 4.11.2
* check fix on current transformer's master branch
* Install transformers from commit id
* update transformers to 4.12.5
* Upgrade torch version for torch-scatter
* Upgrade torch version for torch-scatter in Windows CI
* Build new cache
* Undo last commit
* Use transformers v4.11.2
* bump transformers to 4.12.5
* bump transformers to 4.13.0
* re-allow range of torch versions
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
Co-authored-by: bogdankostic <bogdankostic@web.de>
* Rely api healthcheck on status code rather than json decoding
* Install UI dependencies on the Linux and Windows CI
Co-authored-by: Fabrice Depaulis <fabrice.depaulis@orange.com>
Co-authored-by: ZanSara <sarazanzo94@gmail.com>
* Fix bug ranker: wrong lambda function
The zip function used in line 110 intends to choose the logits array to be the key for the lambda function while it should be the first/second logit of the logit array which corresponds to the classification label (has_answer)
* Use label 1 as has_answer label
* generic ranker (add if-cond for logits vector shape)
* remove test code
* remove test code...
* add two_logits test case for ranker module.
* complete the documentation of ranker, support rankers with 1 or 2 logits as output
* Replace old tutorial 5 with new code based on test cases
* Add latest docstring and tutorial changes
* Use pipeline.eval() in tutorial
* Add latest docstring and tutorial changes
* Restructure notebook
* Add latest docstring and tutorial changes
* Add dataframe example
* Add latest docstring and tutorial changes
* Get eval data from doc store
* Add latest docstring and tutorial changes
* Load data from doc store
* Add latest docstring and tutorial changes
* Clear outputs
* Add latest docstring and tutorial changes
* Change example and add python script
* Add latest docstring and tutorial changes
* Fetch aggregated multilabels from doc store
* Add latest docstring and tutorial changes
* Incorporate review feedback on text comments
* Add latest docstring and tutorial changes
* Add Notebook output
* Remove queries param from pipeline.eval()
* Add latest docstring and tutorial changes
* Add output with all metrics
* Add printing of multiple metrics to script
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* diable problematic eval tests for windows ci
* move standard pipeline eval tests to separate test file
* switch to elasticsearch documentstore to reduce inproc mem
* Revert "switch to elasticsearch documentstore to reduce inproc mem"
This reverts commit 7a75871909c3317a252dff3a4df17e99eff69d05.
* get retiever from conftest
* use smaller embedding model for summarizer
* use smaller summarizer model
* remove queries param from pipeline.eval()
* isolate problematic tests
* rename separate test file
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Trying to fix a bug occurring when dataset is None (happens with many parallel request for some reason)
* Change favicon and title and fix bug with version number
* Improve the text description and partially fix the enter-to-run function
* Aliasing the join is not sufficient yet
* Update the filter query in some other functions of SQLDocumentStore - this functionality should be centralized
* Adding tests for get_all_documents, now failing
* Fix tests
* Fix typo spotted by mypy
* retriever metrics added
* Add latest docstring and tutorial changes
* answer and document level matching metrics implemented
* Add latest docstring and tutorial changes
* answer related metrics for retriever
* basic reader metrics implemented
* handle no_answers
* fix typing
* fix tests
* fix tests without sas
* first draft for simulated top k
* rename sas and f1 columns in dataframe
* refactoring of EvaluationResult
* Add latest docstring and tutorial changes
* more eval tests added
* fix sas expected value precision
* distinction between ir and qa recall
* EvaluationResult.worst_queries() implemented
* print_evaluation_report() added
* eval report for QA Pipeline improved
* dynamic metrics for worst queries calc
* Add latest docstring and tutorial changes
* method names adjusted
* simple test for print_eval_report() added
* improved documentation
* Add latest docstring and tutorial changes
* minor formatting
* Add latest docstring and tutorial changes
* fix no_answer cases
* adjust one docstring
* Add latest docstring and tutorial changes
* fix no_answer cases for sas
* batchmode for sas implemented
* fix for retriever metrics if there are only no_answers
* fix multilabel tests
* improve documentation for pipeline.eval()
* streamline multilabel aggregates and docs
* Add latest docstring and tutorial changes
* fix multilabel tests
* unify document_id
* add dataframe schema description to EvaluationResult
* Add latest docstring and tutorial changes
* rename worst_queries to wrong_examples
* Add latest docstring and tutorial changes
* make query digesting standard pipelines work with pipeline.eval()
* Add latest docstring and tutorial changes
* tests for multi retriever pipelines added
* remove unnecessary import
* print_eval_report(): support all pipelines without junctions
* Add latest docstring and tutorial changes
* fix typos
* Add latest docstring and tutorial changes
* fix minor simulated_top_k bug and use memory documentstore throughout tests
* sas model param description improved
* Add latest docstring and tutorial changes
* rename recall metrics
* Add latest docstring and tutorial changes
* fix mean average precision link
* Add latest docstring and tutorial changes
* adjust sas description docstring
* Add latest docstring and tutorial changes
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* bugfix metadata extraxtion in the formrecognizer and seperation of surrounding in preceding and following content length
* Fix docstring
* fix metadata extraction for content_type text
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* Add more env vars to the streamlit ui
* Add some more questions to the random ones
* Relax a statuscode check and rename env vars
* Make query error message more descriptive
* Add log message
* Align docker-compose with and without GPU
* Typo in pipeline filename
* Remove prefix from var in docker_compose
* Align docker-compose.yml and add small sleep to the initialized poller to prevent spamming
* Fix the name of the dockerfile used to build the GPU image
* Fix some miscopied code
* Remove feedback from the no-answer, seems the backend can't take it
* Try to raise concurrent requests per worker
* Remove the actual number of workers
* Add FormRecognizerConverter
* Change signature of convert method + change return type of all converters
* Adapt preprocessing util to new return type of converters
* Parametrize number of lines used for surrounding context of table
* Change name from FormRecognizerConverter to AzureConverter
* Set version of azure-ai-formrecognizer package
* Change tutorial 8 based on new return type of converters
* Add tests
* Add latest docstring and tutorial changes
* Fix typo
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* Fix the feedback function of the demo with a workaround
* Some docstring
* Update tests and rename methods in feedback.py
* Fix tests
* Remove operation_ids
* Add a couple of status code checks
* Adapt docker-compose-gpu.yml to use DPR by default
* Update the comments
* Change the ES image
* Increase the context window and allow no-answers in the DPR pipeline too
* Re-enable file upload in GPU version
* Add env var without value and a commet to explain it
* Improve the Random Question functionality and add three example questions
* Fix the example questions
* Change default docs for the retriever
* Add example short description and make the no-answer boxes blue
* Modify some text and add a fix for the slider's bug
* New no-answer message
* Fix link to colab notebook in tutorial 16
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Introduced an arg add synonyms to Elasticsearch
* Added the test code, removed the whitespace formatting changes, and overwrote the relevant parts from the already existing mapping instead of creating new mapping.
* Added the test code
* Remove whitespace change
* Added the doc_string with examples and link
* Removed unneccessary spaces
* Add latest docstring and tutorial changes
* fix text_field -> content_field
Co-authored-by: sowmiya-emplay <sowmiya.j@emplay.net>
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* adding yaml functionality to BaseStandardPipeline
fixes#1681
* Add latest docstring and tutorial changes
* Update API Reference Pages for v1.0 (#1729)
* Create new API pages and update existing ones
* Create query classifier page
* Remove Objects suffix
* Change answer aggregation key to doc_id, query instead of label_id, query (#1726)
* Add debugging example to tutorial (#1731)
* Add debugging example to tutorial
* Add latest docstring and tutorial changes
* Remove Objects suffix
* Add latest docstring and tutorial changes
* Revert "Remove Objects suffix"
This reverts commit 6681cb06510b080775994effe6a50bae42254be4.
* Revert unintentional commit
* Add third debugging option
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Fix another self.device/s typo (#1734)
* Fix yet another self.device(s) typo
* Add typing to 'initialize_device_settings' to try prevent future issues
* Fix bug in Tutorial5
* Fix the same bug in the notebook
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* added test for saving and loading prebuilt pipelines
* fixed typo, changed variable name and added comments
* Add latest docstring and tutorial changes
* Fix a few details of some tutorials (#1733)
* Make Tutorial10 use print instead of logs and fix a typo in Tutoria15
* Add a type check in 'print_answers'
* Add same checks to print_documents and print_questions
* Make RAGenerator return Answers instead of dictionaries
* Fix RAGenerator tests
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Fix `print_answers` (#1743)
* Fix a specific path of print_answers that was assuming answers are dictionaries
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Split pipeline tests into three suites (#1755)
* Split pipeline tests into three suites
* Will this trigger the CI?
* Rename duplicate test into test_most_similar_documents_pipeline
* Fixing a bug that was probably never noticed
* Capitalize starting letter in params (#1750)
* Capitalize starting letter in params
Capitalized the starting letter in code examples for params in keeping with the latest names for nodes where first letter is capitalized.
Refer: https://github.com/deepset-ai/haystack/issues/1748
* Update standard_pipelines.py
Capitalized some starting letters in the docstrings in keeping with the updated node names for standard pipelines
* Multi query eval (#1746)
* add eval() to pipeline
* Add latest docstring and tutorial changes
* support multiple queries in eval()
* Add latest docstring and tutorial changes
* keep single query test
* fix EvaluationResult node_results default
* adjust docstrings
* Add latest docstring and tutorial changes
* minor improvements from comments
* Add latest docstring and tutorial changes
* move EvaluationResult and calculate_metrics to schema
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Split summarizer tests in order to make windows CI work again (#1757)
* separate testfile for summarizer with translation
* Add latest docstring and tutorial changes
* import SPLIT_DOCS from test_summarizer
* add workflow_dispatch to windows_ci
* add worflow_dispatch to linux_ci
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix import of EvaluationResult in test case
* exclude test_summarizer_translation.py for windows_ci (#1759)
* Pipelines now tolerate custom _debug content (#1756)
* Pipelines now tolerate custom _debug content
* Support Tables in all DocumentStores (#1744)
* Add support for tables in SQLDocumentStore, FAISSDocumentStore and MilvuDocumentStore
* Add support for WeaviateDocumentStore
* Make sure that embedded meta fields are strings + add embedding_dim to WeaviateDocStore in test config
* Add latest docstring and tutorial changes
* Represent tables in WeaviateDocumentStore as nested lists
* Fix mypy
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Allow TableReader models without aggregation classifier (#1772)
* Fix usage of filters in `/query` endpoint in REST API (#1774)
* WIP filter refactoring
* fix filter formatting
* remove inplace modification of filters
* Public demo (#1747)
* Queries now run only when pressing RUN. File upload hidden. Question is not sent if the textbox is empty.
* Add latest docstring and tutorial changes
* Tidy up: remove needless state, add comments, fix minor bugs
* Had to add results to the status to avoid some bugs in eval mode
* Added 'credits'
* Add footers, update requirements, some random questions for the evaluation
* Add requested changes
* Temporary rollback the UI to the old GoT dataset
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Facilitate concurrent query / indexing in Elasticsearch with dense retrievers (new `skip_missing_embeddings` param) (#1762)
* Filtering records not having embeddings
* Added support for skip_missing_embeddings Flag. Default behavior is throw error when embeddings are missing. If skip_missing_embeddings=True then documents without embeddings are ignored for vector similarity
* Fix for below error:
haystack/document_stores/elasticsearch.py:852: error: Need type annotation for "script_score_query"
* docstring for skip_missing_embeddings parameter
* Raise exception where no documents with embeddings is found for Embedding retriever.
* Default skip_missing_embeddings to True
* Explicitly check if embeddings are present if no results are returned by EmbeddingRetriever for Elasticsearch
* Added test case for based on Julian's input
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Simplify code by using get_embed_count
* Adjust docstring & error msg slightly
* Revert error msg
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* Huggingface private model support via API tokens (FARMReader) (#1775)
* passed kwargs to model loading
* Pass Auth token explicitly
* add use_auth_token to get_language_model_class
* added use_auth_token parameter at FARMReader
* Add latest docstring and tutorial changes
* added docs for parameter `use_auth_token`
* Add latest docstring and tutorial changes
* adding docs link
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* private hugging face models for retrievers (#1785)
* private dpr
* Add latest docstring and tutorial changes
* added parameters to child functions
* Add latest docstring and tutorial changes
* added tableextractor
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* ignore empty filters parameter (#1783)
* ignore empty filters parameter
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* initialize doc store with doc and label index in tutorial 5 (#1730)
* initialize doc store with doc and label index
* change ipynb according to py for tutorial 5
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Small fixes to the public demo (#1781)
* Make strealit tolerant to haystack not knowing its version, and adding special error for docstore issues
* Add workaround for a Streamlit bug
* Make default filters value an empty dict
* Return more context for each answer in the rest api
* Make the hs_version call not-blocking by adding a very quick timeout
* Add disclaimer on low confidence answer
* Use the no-answer feature of the reader to highlight questions with no good answer
* Upgrade torch to v1.10.0 (#1789)
* Upgrade torch to v1.10.0
* Adapt torch version for torch-scatter in TableQA tutorial
* Add latest docstring and tutorial changes
* Make torch version more flexible
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* adding yaml functionality to BaseStandardPipeline
fixes#1681
* Add latest docstring and tutorial changes
* added test for saving and loading prebuilt pipelines
* fixed typo, changed variable name and added comments
* Add latest docstring and tutorial changes
* fix code rendering for example
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Branden Chan <33759007+brandenchan@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
Co-authored-by: Sara Zan <sara.zanzottera@deepset.ai>
Co-authored-by: nishanthcgit <5066268+nishanthcgit@users.noreply.github.com>
Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
Co-authored-by: bogdankostic <bogdankostic@web.de>
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
Co-authored-by: C V Goudar <cvgoudar@users.noreply.github.com>
Co-authored-by: Kristof Herrmann <37148029+ArzelaAscoIi@users.noreply.github.com>
* Upgrade torch to v1.10.0
* Adapt torch version for torch-scatter in TableQA tutorial
* Add latest docstring and tutorial changes
* Make torch version more flexible
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Make strealit tolerant to haystack not knowing its version, and adding special error for docstore issues
* Add workaround for a Streamlit bug
* Make default filters value an empty dict
* Return more context for each answer in the rest api
* Make the hs_version call not-blocking by adding a very quick timeout
* Add disclaimer on low confidence answer
* Use the no-answer feature of the reader to highlight questions with no good answer
* initialize doc store with doc and label index
* change ipynb according to py for tutorial 5
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Filtering records not having embeddings
* Added support for skip_missing_embeddings Flag. Default behavior is throw error when embeddings are missing. If skip_missing_embeddings=True then documents without embeddings are ignored for vector similarity
* Fix for below error:
haystack/document_stores/elasticsearch.py:852: error: Need type annotation for "script_score_query"
* docstring for skip_missing_embeddings parameter
* Raise exception where no documents with embeddings is found for Embedding retriever.
* Default skip_missing_embeddings to True
* Explicitly check if embeddings are present if no results are returned by EmbeddingRetriever for Elasticsearch
* Added test case for based on Julian's input
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Added test case for based on Julian's input. Fix pytest error on the testcase
* Simplify code by using get_embed_count
* Adjust docstring & error msg slightly
* Revert error msg
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
* Queries now run only when pressing RUN. File upload hidden. Question is not sent if the textbox is empty.
* Add latest docstring and tutorial changes
* Tidy up: remove needless state, add comments, fix minor bugs
* Had to add results to the status to avoid some bugs in eval mode
* Added 'credits'
* Add footers, update requirements, some random questions for the evaluation
* Add requested changes
* Temporary rollback the UI to the old GoT dataset
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
