bogdankostic
61d9429c25
Simplify loading of EmbeddingRetriever ( #2619 )
...
* Infer model format for EmbeddingRetriever automatically
* Update Documentation & Code Style
* Adapt conftest to automatic inference of model_format
* Update Documentation & Code Style
* Fix tests
* Update Documentation & Code Style
* Fix tests
* Adapt tutorials
* Update Documentation & Code Style
* Add test for similarity scores with sentence transformers
* Adapt doc string and warning message
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-06-02 15:05:29 +02:00
Julian Risch
b2a2c10fae
Update milvus installation instructions to v2 ( #2598 )
2022-05-25 17:22:04 +02:00
tstadel
dd8dc588b1
fix eval with context matching in table qa use cases ( #2597 )
2022-05-25 16:26:29 +02:00
tstadel
7caca41c5d
Support context matching in pipeline.eval() ( #2482 )
...
* calculate context pred metrics
* Update Documentation & Code Style
* extend doc_relevance_col values
* fix import order
* Update Documentation & Code Style
* fix mypy
* fix typings literal import
* add option for custom document_id_field
* Update Documentation & Code Style
* fix tests and dataframe col-order
* Update Documentation & Code Style
* rename content to context in eval dataframe
* add backward compatibility to EvaluationResult.load()
* Update Documentation & Code Style
* add docstrings
* Update Documentation & Code Style
* support sas
* Update Documentation & Code Style
* add answer_scope param
* Update Documentation & Code Style
* rework doc_relevance_col and keep document_id col in case of custom_document_id_field
* Update Documentation & Code Style
* improve docstrings
* Update Documentation & Code Style
* rename document_relevance_criterion into document_scope
* Update Documentation & Code Style
* add document_scope and answer_scope to print_eval_report
* support all new features in execute_eval_run()
* fix imports
* fix mypy
* Update Documentation & Code Style
* rename pred_label_sas_grid into pred_label_matrix
* update dataframe schema and sorting
* Update Documentation & Code Style
* pass through context_matching params and extend document_scope test
* Update Documentation & Code Style
* add answer_scope tests
* fix context_matching_threshold for document metrics
* shorten dataframe apply calls
* Update Documentation & Code Style
* fix queries getting lost if nothing was retrieved
* Update Documentation & Code Style
* Update Documentation & Code Style
* use document_id scopes
* Update Documentation & Code Style
* fix answer_scope literal
* Update Documentation & Code Style
* update the docs (lg changes)
* Update Documentation & Code Style
* update tutorial 5
* Update Documentation & Code Style
* fix tests
* Add minor lg updates
* final docstring changes
* fix single quotes in docstrings
* Update Documentation & Code Style
* dataframe scopes added for each column
* better docstrings for context_matching params
* Update Documentation & Code Style
* fix summarizer eval test
* Update Documentation & Code Style
* fix test
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: agnieszka-m <amarzec13@gmail.com>
2022-05-24 18:11:52 +02:00
bogdankostic
867695ad0c
Change signature of queries param in batch methods ( #2575 )
...
* Change signature of queries param in batch methods
* Update Documentation & Code Style
* Fix mypy
* Remove unused import
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-24 12:33:45 +02:00
ClaMnc
2b11981b08
set top_k to 5 in SAS to be consistent ( #2550 )
...
* set top_k to 5 in SAS to be consistent
* set top_k to 5 in SAS to be consistent
2022-05-16 10:29:03 +02:00
Sara Zan
00aa1f41d7
convert_files_to_docs typo ( #2546 )
2022-05-13 16:38:43 +02:00
bogdankostic
738e008020
Add run_batch method to all nodes and Pipeline to allow batch querying ( #2481 )
...
* Add run_batch methods for batch querying
* Update Documentation & Code Style
* Fix mypy
* Update Documentation & Code Style
* Fix mypy
* Fix linter
* Fix tests
* Update Documentation & Code Style
* Fix tests
* Update Documentation & Code Style
* Fix mypy
* Fix rest api test
* Update Documentation & Code Style
* Add Doc strings
* Update Documentation & Code Style
* Add batch_size as attribute to nodes supporting batching
* Adapt error messages
* Adapt type of filters in retrievers
* Revert change about truncation_warning in summarizer
* Unify multiple_doc_lists tests
* Use smaller models in extractor tests
* Add return types to JoinAnswers and RouteDocuments
* Adapt return statements in reader's run_batch method
* Allow list of filters
* Adapt error messages
* Update Documentation & Code Style
* Fix tests
* Fix mypy
* Adapt print_questions
* Remove disabling warning about too many public methods
* Add flag for pylint to disable warning about too many public methods in pipelines/base.py and document_stores/base.py
* Add type check
* Update Documentation & Code Style
* Adapt tutorial 11
* Update Documentation & Code Style
* Add query_batch method for DCDocStore
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-11 11:11:00 +02:00
bogdankostic
5378a9ab48
Fix tutorials 4, 7 and 8 ( #2526 )
...
* Fix tutorials 4, 7 and 8
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-11 09:17:05 +02:00
MichelBartels
c7e39e5225
Replace TableTextRetriever with EmbeddingRetriever in Tutorial 15 ( #2479 )
...
* replace TableTextRetriever with EmbeddingRetriever in Tutorial 15
* Update Documentation & Code Style
* fix bug
* Update Documentation & Code Style
* update tutorial 15 outputs
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-20-212.eu-west-1.compute.internal>
2022-05-05 10:12:44 +02:00
MichelBartels
5d98810a17
Raise error if torch-scatter is not installed or wrong version is installed ( #2486 )
...
* automatically download correct torch-scatter version
* raise error if torch-scatter is not installed
* Update Documentation & Code Style
* catch all import errors and fix linter
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-05 10:12:10 +02:00
Sara Zan
01ea4bf21f
Change default encoding for PDFToTextConverter from Latin 1 to UTF-8 ( #2420 )
...
* Change default encoding for PDFToTextConverter
* Update Documentation & Code Style
* Improve docstring
* Update Documentation & Code Style
* Add list of ligatures to ignore and add the possibility to modify such list at need
* Add docstring
* Add tests
* Rename parameter
* Update Documentation & Code Style
* Move implementation into the base converter to make mypy happier
* Update Documentation & Code Style
* mypy and pylint
* mypy
* move encoding parameter to init of PDFToTextConverter
* Update Documentation & Code Style
* make utf8 default and fix mypy
* Update Documentation & Code Style
* Update Documentation & Code Style
* remove note on encoding in tutorial8
* Update Documentation & Code Style
* skip OCRConverter and test converter.run
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
2022-05-04 17:01:45 +02:00
Ahmed Nabil
9cdd719a6d
Update xpdfreader package installation ( #2491 )
...
This Update will fix this exception `Exception: pdftotext is not installed. It is part of xpdf or poppler-utils software suite. ` Now, converting PDFs wouldn't have any issues.
2022-05-03 18:09:41 +02:00
Tuana Celik
b6e369d1ca
changing the name of the retrievers from es_retriever to retriever ( #2487 )
...
* changing the name of the retrievers from es_retriever to retriever
* Update Documentation & Code Style
* name fix 2
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-03 18:08:23 +02:00
Tuana Celik
d49e92e21c
ElasticsearchRetriever to BM25Retriever ( #2423 )
...
* change class names to bm25
* Update Documentation & Code Style
* Update Documentation & Code Style
* Update Documentation & Code Style
* Add back all_terms_must_match
* fix syntax
* Update Documentation & Code Style
* Update Documentation & Code Style
* Creating a wrapper for old ES retriever with deprecated wrapper
* Update Documentation & Code Style
* New method for deprecating old ESRetriever
* New attempt for deprecating the ESRetriever
* Reverting to the simplest solution - warning logged
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sara Zan <sara.zanzottera@deepset.ai>
2022-04-26 16:09:39 +02:00
Sara Zan
ba9c976bfe
Update pdftotext link ( #2432 )
...
* Update pdftotext link
* Update Documentation & Code Style
* Update Tutorial8_Preprocessing.ipynb
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-19 14:30:18 +02:00
Sebastian
3d42b70fbb
Added macos version of xpdf in tutorial 8 ( #2424 )
...
* Added macos version of xpdf in tutorial 8
* mini-error
2022-04-14 15:31:40 +02:00
Branden Chan
75dcfd3fab
Delete files in docs/_src ( #2322 )
...
* Delete files in _src
* Filter unused images and re-add images that were in use in docs/img
* Remove all usages of user-images.githubusercontent.com
Co-authored-by: ZanSara <sarazanzo94@gmail.com>
2022-04-12 16:19:03 +02:00
tstadel
8342a6c1d6
Fix eval discrepancies ( #2381 )
...
* fix eval discrepancies
* Update Documentation & Code Style
* fix reader eval comparison
* Update Documentation & Code Style
* slightly improve messed up top_n_f1 func
* add no_answer hint to reader.eval metrics
* fix tut5
* Update Documentation & Code Style
* correct doc_relevance_col in tests
* Update Documentation & Code Style
* redefine recall metrics for no_answers
* fix bugs in EvalAnswers
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-12 09:24:22 +02:00
MichelBartels
fc1cb63bcc
Fix RouteDocuments documentation ( #2380 )
...
* fix RouteDocuments documentation
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-31 11:45:02 +02:00
MichelBartels
eb514a6167
Add evaluation and document conversion to tutorial 15 ( #2325 )
...
* update tutorial 15 with newer features
* Update Documentation & Code Style
* fix tutorial 15
* update telemetry with tutorial changes
* Update Documentation & Code Style
* remove error output
* add output
* update non-notebook tutorial 15
* Update Documentation & Code Style
* delete distracting output from tutorial 15 notebook
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-29 17:09:05 +02:00
bogdankostic
834f8c4902
Change return types of indexing pipeline nodes ( #2342 )
...
* Change return types of file converters
* Change return types of preprocessor
* Change return types of crawler
* Adapt utils to functions to new return types
* Adapt __init__.py to new method names
* Prevent circular imports
* Update Documentation & Code Style
* Let DocStores' run method accept Documents
* Adapt tests to new return types
* Update Documentation & Code Style
* Put "# type: ignore" to right place
* Remove id_hash_keys property from Document primitive
* Update Documentation & Code Style
* Adapt tests to new return types and missing id_hash_keys property
* Fix mypy
* Fix mypy
* Adapt PDFToTextOCRConverter
* Remove id_hash_keys from RestAPI tests
* Update Documentation & Code Style
* Rename tests
* Remove redundant setting of content_type="text"
* Add DeprecationWarning
* Add id_hash_keys to elasticsearch_index_to_document_store
* Change document type from dict to Docuemnt in PreProcessor test
* Fix file path in Tutorial 5
* Remove added output in Tutorial 5
* Update Documentation & Code Style
* Fix file_paths in Tutorial 9 + fix gz files in fetch_archive_from_http
* Adapt tutorials to new return types
* Adapt tutorial 14 to new return types
* Update Documentation & Code Style
* Change assertions to HaystackErrors
* Import HaystackError correctly
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-29 13:53:35 +02:00
mkkuemmel
04b56f0b1c
Replace dpr with embeddingretriever tut14 ( #2336 )
...
* add updated graph images for tutorial14
* ipynb: replaced DPR with EmbeddingRetriever, added TODO for further inspection of failing code
* Revert "ipynb: replaced DPR with EmbeddingRetriever, added TODO for further inspection of failing code"
This reverts commit f4b6f3e1dbbedfd1bbe5e0e33645899dbea5d924.
* ipynb: replaced DPR with EmbeddingRetriever, added TODO for further inspection of failing code
* ipynb: quick fix to avoid failure in print_answers
* py: quick fix to avoid failure in print_answers
* Update Documentation & Code Style
* ipynb: remove DPR, remove images
* Revert "ipynb: remove DPR, remove images"
This reverts commit dfa1e7585da6743fcf97488405c356bf935a976d.
* ipynb: remove DPR, remove images
* py: replace DPR with EmbeddingRetriever
* Update Documentation & Code Style
* correcting a typo
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: TuanaCelik <tuana.celik@deepset.ai>
2022-03-28 16:54:49 +02:00
Raphaël Merx
4ebb71d42d
Fix link to squad_to_dpr.py in DPR train tutorial ( #2334 )
...
* Fix link to squad_to_dpr.py in DPR train tutorial
* update tutorial 9
2022-03-25 12:05:12 +01:00
Julian Risch
cec0137693
Change document attribute from text to content ( #2352 )
...
* Change document attribute from text to content
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-23 16:55:01 +03:00
Julian Risch
7ffeccece6
Fix tutorial dataset paths ( #2340 )
...
* fix tutorial 4 dataset path
* fix tutorial 8 dataset path
* fix tutorial 10 event
* Update Documentation & Code Style
* fix send event for tutorial 15
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-22 09:19:50 +01:00
Julian Risch
ac5617e757
Add basic telemetry features ( #2314 )
...
* add basic telemetry features
* change pipeline_config to _component_config
* Update Documentation & Code Style
* add super().__init__() calls to error classes
* make posthog mock work with python 3.7
* Update Documentation & Code Style
* update link to docs web page
* log exceptions, send event for raised HaystackErrors, refactor Path(CONFIG_PATH)
* add comment on send_event in BaseComponent.init() and fix mypy
* mock NonPrivateParameters and fix pylint undefined-variable
* Update Documentation & Code Style
* check model path contains multiple /
* add test for writing to file
* add test for en-/disable telemetry
* Update Documentation & Code Style
* merge file deletion methods and ignore pylint global statement
* Update Documentation & Code Style
* set env variable in demo to activate telemetry
* fix mock of HAYSTACK_TELEMETRY_ENABLED
* fix mypy and linter
* add CI as env variable to execution contexts
* remove threading, add test for custom error event
* Update Documentation & Code Style
* simplify config/log file deletion
* add test for final event being sent
* force writing config file in test
* make test compatible with python 3.7
* switch to posthog production server
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-21 11:58:51 +01:00
mkkuemmel
06497da748
ipynb: inserted links to graph images ( #2309 )
...
* ipynb: inserted links to graph images
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-15 11:20:31 +01:00
mkkuemmel
a1040a17b2
Replace dpr with embeddingretriever tut11 ( #2287 )
...
* images for tutorial 11 in .github folder for easy access
* ipynb: changed DPR to EmbeddingRetriever, incl. new graphs of pipelines
* Update Documentation & Code Style
* moved images into correct folder
* removed images path
* Update Documentation & Code Style
* fixed debugging run of p_classifier
* Update Documentation & Code Style
* Revert debug param change
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: brandenchan <brandenchan@icloud.com>
2022-03-15 08:30:00 +01:00
Vladimir Blagojevic
6c0094b5ad
Update LFQA with the latest LFQA seq2seq and retriever models ( #2210 )
...
* Register BartEli5Converter for vblagoje/bart_lfqa model
* Update LFQA unit tests
* Update LFQA tutorials
2022-03-08 15:11:41 +01:00
tstadel
dde9d59271
fix pip backtracking issue ( #2281 )
...
* fix pip backtracking issue
* restrict azure-core version
* Remove the trailing comma
* Add skip_magic_trailing_comma in pyproject.toml for pydoc compatibility
* Pin pydoc-markdown _again_
Co-authored-by: Sara Zan <sarazanzo94@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-07 19:25:33 +01:00
mkkuemmel
5951fc463e
Replace dpr with embeddingretriever tut5 ( #2274 )
...
* ipynb: EmbeddingRetriever made more prominent than DPR
* ipynb: EmbeddingRetriever more prominent than DPR
* Update Documentation & Code Style
* indentation fix
* Update Documentation & Code Style
* py: EmbeddingRetriever more prominent than DPR
* indentation fix
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-04 11:29:48 +01:00
bogdankostic
c5542bd3fb
Add RouteDocuments and JoinAnswers nodes ( #2256 )
...
* Add SplitDocumentList and JoinAnswer nodes
* Update Documentation & Code Style
* Add tests + adapt tutorial
* Update Documentation & Code Style
* Remove branch from installation path in Tutorial
* Update Documentation & Code Style
* Fix typing
* Update Documentation & Code Style
* Change name of SplitDocumentList to RouteDocuments
* Update Documentation & Code Style
* Adapt tutorials to new name
* Add test for JoinAnswers
* Update Documentation & Code Style
* Adapt name of test for JoinAnswers node
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-01 17:42:11 +01:00
Branden Chan
b563b6622c
Api pages ( #2248 )
...
* Update Readme WIP
* Update Documentation & Code Style
* Update Documentation & Code Style
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-25 13:53:46 +01:00
Branden Chan
bb107e5027
Polish Evaluation Tutorial ( #2212 )
...
* Polish evaluation tutorial
* Clear notebook output
* Cleanup tutorials
* Fix discrepancy in isolated retriever eval results
* Incorporate reviewer feedback
* Clean notebook output
2022-02-24 17:45:40 +01:00
Sara Zan
b475a1d4f7
Comment out Milvus cell on Tutorial6 ( #2243 )
...
* Comment out Milvus cell on Tutorial6
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-24 15:20:54 +01:00
mkkuemmel
853de933a1
changed document_store to ElasticsearchDocumentStore ( #2192 )
...
because FAISSDocumentStore errored with ElasticSearchRetriever
2022-02-16 12:35:17 +01:00
Sara Zan
fdc36292f1
Align REST API and Haystack versions ( #2164 )
...
* Align REST API and Haystack versions
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-11 14:17:26 +01:00
Sara Zan
795c7c8a47
Fix dependency management in Tutorial 6 ( #2148 )
...
* Fix dependency issue in Tutorial 6
* Remove faiss from first install block
* move faiss group back to main installation step
* Comment out Milvus cell
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-10 15:07:02 +01:00
Sara Zan
957e78ed9e
Upgrade pydoc-markdown & refactor GitHub Actions ( #2117 )
...
* Upgrade pydoc-markdown and fix the YAMLs to work with it
* Pin pydoc-markdown to major version
* Generalize pydoc-markdown workflow
* Make a single Action to perform all tasks that require committing into the local branch
* Merge the code updates and the docs in the Linux CI to prevent the bot from always show the pipeline as green
* Installing Jupyter deps for Black
* Build cache before running generation tasks
* Add check not to run the code generation on master
* Simplify push action
* Add more test deps in setup.cfg and remove from GH Action workflow
* Remove forced upgrades on pip install
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-04 15:45:09 +01:00
Sara Zan
a59bca3661
Apply black formatting ( #2115 )
...
* Testing black on ui/
* Applying black on docstores
* Add latest docstring and tutorial changes
* Create a single GH action for Black and docs to reduce commit noise to the minimum, slightly refactor the OpenAPI action too
* Remove comments
* Relax constraints on pydoc-markdown
* Split temporary black from the docs. Pydoc-markdown was obsolete and needs a separate PR to upgrade
* Fix a couple of bugs
* Add a type: ignore that was missing somehow
* Give path to black
* Apply Black
* Apply Black
* Relocate a couple of type: ignore
* Update documentation
* Make Linux CI run after applying Black
* Triggering Black
* Apply Black
* Remove dependency, does not work well
* Remove manually double trailing commas
* Update documentation
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-03 13:43:18 +01:00
Julian Risch
3245cdef1d
Add faiss dependency to tutorial 12 ( #2109 )
2022-02-02 14:19:08 +01:00
Sara Zan
d470b9d0bd
Improve dependency management ( #1994 )
...
* Fist attempt at using setup.cfg for dependency management
* Trying the new package on the CI and in Docker too
* Add composite extras_require
* Add the safe_import function for document store imports and add some try-catch statements on rest_api and ui imports
* Fix bug on class import and rephrase error message
* Introduce typing for optional modules and add type: ignore in sparse.py
* Include importlib_metadata backport for py3.7
* Add colab group to extra_requires
* Fix pillow version
* Fix grpcio
* Separate out the crawler as another extra
* Make paths relative in rest_api and ui
* Update the test matrix in the CI
* Add try catch statements around the optional imports too to account for direct imports
* Never mix direct deps with self-references and add ES deps to the base install
* Refactor several paths in tests to make them insensitive to the execution path
* Include tstadel review and re-introduce Milvus1 in the tests suite, to fix
* Wrap pdf conversion utils into safe_import
* Update some tutorials and rever Milvus1 as default for now, see #2067
* Fix mypy config
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-26 18:12:55 +01:00
MichelBartels
4cc37548e3
Fix finetuning notebook augmentation ( #2071 )
...
* fix data augmentation path in finetuning notebook
* Add latest docstring and tutorial changes
* make distillation possible with other models than BERT
* use smaller dataset for distillation in finetuning tutorial
* Add latest docstring and tutorial changes
* make data augmentation in finetuning faster
* update language models forward doc strings
* fix return type of language models
* remove debug output
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-26 17:49:14 +01:00
Julian Risch
0f34983f74
fix answer is not subscriptable error ( #2069 )
...
* fix answer is not subscriptable error
* fix answer is not subscriptable in script
2022-01-26 11:45:45 +01:00
MichelBartels
e8cd5ea943
Add distillation to finetuning tutorial ( #2025 )
...
* Add finetuning tutorial
* Add latest docstring and tutorial changes
* fix typo
* Add latest docstring and tutorial changes
* improve distillation explanation in finetuning tutorial
* Add latest docstring and tutorial changes
* allow augment_squad.py to be easier to call from within python
* Update Tutorial2_Finetune_a_model_on_your_data.py
* fix squad augmentation test
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-20 12:18:32 +01:00
Julian Risch
2c063e960e
Extend Tutorial 5 with Upper Bound Reader Eval Metrics ( #1995 )
...
* print report for closed-domain eval
* Add latest docstring and tutorial changes
* rename parameter and rewrite docs
* Add latest docstring and tutorial changes
* print eval report in separate cell
* Add latest docstring and tutorial changes
* explain when to eval individual components
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-14 16:29:18 +01:00
Julian Risch
5695d721aa
update link to annotation tool docu ( #2005 )
...
* update link to annotation tool docu
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-14 16:10:59 +01:00
Dmitry Goryunov
79fdda8a7c
Remove hard-coded variables from the Tutorial 15 ( #1984 )
...
* Remove hard-coded variables from the Tutorial 15
* Fix missing comma
* Add latest docstring and tutorial changes
* Fix formatting in Tutorial15_TableQA.ipynb
* Add latest docstring and tutorial changes
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-11 17:55:20 +01:00
Mathew Kuriakose
a44b6c18c0
Unify vector_dim and embedding_dim parameter in Document Store ( #1922 )
...
* Refactored code to unify vector_dim and embedding_dim parameter in DocumentStores
* Unit test cases updated to use `embedding_dim` instead of `vector_dim`
* Unit test case update to use embedding_dim instead of vector_dim
* Add latest docstring and tutorial changes
* Put usage of `vector_dim` param in same if-block as corresponding warning
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bogdankostic <bogdankostic@web.de>
2022-01-10 18:10:32 +01:00
