3803 Commits

Author SHA1 Message Date
MichelBartels
a952ba240f
Include meta data when computing embeddings in EmbeddingRetriever (#2559)
* include meta data when calculating embeddings in EmbeddingRetriever

* Update Documentation & Code Style

* fix None meta field

* remove default values

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-17 12:37:04 +02:00
Sara Zan
ff4303c51b
[CI refactoring] Categorize tests into folders (#2554)
* Categorize tests into folders

* Fix linux_ci.yml and an import

* Wrong path
2022-05-17 09:55:53 +01:00
Sara Zan
81223f8cd1
[CI refactoring] Avoid ray==1.12.0 on Windows (#2562)
* Avoid ray 1.12.0 on windows (bug)

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-17 09:55:16 +01:00
MichelBartels
686e9d24ef
Documenting output score of JoinDocuments when using concatenation (#2561)
* add documentation regarding the score of JoinDocuments when using concatenation

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-16 18:30:07 +02:00
Ivan Lopez
a2a99f79b1
Fix docker image tag with semantic version for releases (#2548)
* Fix docker tag with semantic version for releases

* Prepend latest docker tag with tagprefix in cache-from
2022-05-16 13:26:33 +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
Agnieszka Marzec
2d03a26045
Minor lg changes (#2533)
* Minor lg change

* Update Documentation & Code Style

* Fix missing articles

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-13 16:12:22 +02:00
Agnieszka Marzec
1ae5a1449b
Update run() and run_batch() params descriptions in API (#2542)
* Update run() and run_batch() params descriptions

* Update Documentation & Code Style

* Update api params descriptions

* Update Documentation & Code Style

* Fix typo

Co-authored-by: bogdankostic <bogdankostic@web.de>

* Add Bogdan's suggestions

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bogdankostic <bogdankostic@web.de>
2022-05-13 15:11:01 +02:00
bogdankostic
300ee1ac83
Upgrade torch version to 1.11 (#2538)
* Bump torch version

* Upgrade torch version in torch-scatter
2022-05-13 14:45:53 +02:00
MichelBartels
4f22942cb0
Handle transformers pipeline flattening lists of length 1 (#2531)
* Handle transformers pipeline flattening lists of length 1

* Consider case where only one document is passed

* Change position of fix

* Make use of top_k_per_candidate in predict method

* Fix predict method

Co-authored-by: bogdankostic <bogdankostic@web.de>
2022-05-12 16:11:38 +02:00
tstadel
771ed0bb1d
Remove wrong retriever top_1 metrics from print_eval_report (#2510)
* remove wrong retriever top_1 metrics

* Update Documentation & Code Style

* don't show wrong examples frame when n_wrong_examples is 0

* Update Documentation & Code Style

* Update Documentation & Code Style

* only use farm reader during eval tests

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-12 12:34:11 +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
bogdankostic
4581b91e83
Make DeepsetCloudDocumentStore work with non-existing index (#2513)
* Make DeepsetCloudDocumentStore work with non-existing index

* Update Documentation & Code Style

* Add tests

* Update Documentation & Code Style

* Fix tests, adapt warning messages + lowercase deepset

* Update Documentation & Code Style

* Fix typo in test

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-10 15:21:35 +02:00
Massimiliano Pippi
7595bb49ab
rearrange contributing guidelines (#2515)
* rearrange contributing guidelines

* revert unneeded change to README
2022-05-10 14:59:46 +02:00
Branden Chan
43bfea6f3d
Add sort arg to JoinAnswers (#2436)
* Add sort arg to JoinAnswers

* Update Documentation & Code Style

* Change naming and docstring

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-10 11:47:00 +02:00
Sara Zan
15a9ff6f67
PR template mention of enabling Actions (#2523)
* Update version to 1.4.1rc0

* Add hint of enabling action on the fork in the PR template

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-10 09:46:09 +02:00
Sara Zan
3d8bdf3cb6
Remove safe import from ElasticsearchDocumentStore (#2522)
* Update version to 1.4.1rc0

* Elasticsearch is not an optional dependency

* Fix import path

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-09 18:07:42 +02:00
Gabriel Altay
988568882a
fix small typo in Document doc string (#2520)
* fix small typo in Document doc string

Was going through the tutorial, then digging through the code and just noticed a small typo

* generate markdown file changes from docstrings

Co-authored-by: Julian Risch <julian.risch@deepset.ai>
2022-05-09 18:04:33 +02:00
bogdankostic
bce84577c6
Upgrade transformers version to 4.18.0 (#2514)
* Upgrade transformers version to 4.18.0

* Adapt tokenization test to upgrade

* Adapt tokenization test to upgrade
2022-05-06 16:57:13 +02:00
Branden Chan
caf1336424
Adjust pydoc markdown config so methods shown with classes (#2511)
* add_member_class_prefix: true

* Update Documentation & Code Style

* Trigger redeploy

* Trigger redeploy

* Fix pydoc param

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-06 16:00:08 +02:00
Sara Zan
1ed407cb5a
Update version to 1.4.1rc0 (#2509)
* Update version to 1.4.1rc0

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-06 11:46:31 +02:00
Julian Risch
081b886aa1
Release v1.4.0 (#2502)
* delete unneeded files of last release

* add v1.4.0 docs with updated links

* upgrade version number

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
v1.4.0
2022-05-05 12:24:45 +02:00
Sara Zan
f3e0ba4be9
Fix OpenSearchDocumentStore's __init__ (#2498)
* Move super in OpenSearchDocumentStore and add small test

* Update Documentation & Code Style

* Add Opensearch container to the CI

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-05 10:38:09 +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
Julian Risch
1418f0c603
change milvus links from 2.0.0 to 2.0.x (#2496)
* change milvus links from 2.0.0 to 2.0.x

* Update Documentation & Code Style

* fix two broken links

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-04 18:30:50 +02:00
Julian Risch
fa277bcea8
Upgrade xpdf to 4.04 in Exception text (#2488)
* Upgrade xpdf to 4.04 in Exception text

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-04 17:42:32 +02:00
Sara Zan
f8e02310bf
Validate YAML files without loading the nodes (#2438)
* Remove BasePipeline and make a module for RayPipeline

* Can load pipelines from yaml, plenty of issues left

* Extract graph validation logic into _add_node_to_pipeline_graph & refactor load_from_config and add_node to use it

* Fix pipeline tests

* Move some tests out of test_pipeline.py and create MockDenseRetriever

* myoy and pylint (silencing too-many-public-methods)

* Fix issue found in some yaml files and in schema files

* Fix paths to YAML and fix some typos in Ray

* Fix eval tests

* Simplify MockDenseRetriever

* Fix Ray test

* Accidentally pushed merge coinflict, fixed

* Typo in schemas

* Typo in _json_schema.py

* Slightly reduce noisyness of version validation warnings

* Fix version logs tests

* Fix version logs tests again

* remove seemingly unused file

* Add check and test to avoid adding the same node to the pipeline twice

* Update Documentation & Code Style

* Revert config to pipeline_config

* Remo0ve unused import

* Complete reverting to pipeline_config

* Some more stray config=

* Update Documentation & Code Style

* Feedback

* Move back other_nodes tests into pipeline tests temporarily

* Update Documentation & Code Style

* Fixing tests

* Update Documentation & Code Style

* Fixing ray and standard pipeline tests

* Rename colliding load() methods in dense retrievers and faiss

* Update Documentation & Code Style

* Fix mypy on ray.py as well

* Add check for no root node

* Fix tests to use load_from_directory and load_index

* Try to workaround the disabled add_node of RayPipeline

* Update Documentation & Code Style

* Fix Ray test

* Fix FAISS tests

* Relax class check in _add_node_to_pipeline_graph

* Update Documentation & Code Style

* Try to fix mypy in ray.py

* unused import

* Try another fix for Ray

* Fix connector tests

* Update Documentation & Code Style

* Fix ray

* Update Documentation & Code Style

* use BaseComponent.load() in pipelines/base.py

* another round of feedback

* stray BaseComponent.load()

* Update Documentation & Code Style

* Fix FAISS tests too

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
2022-05-04 17:39:06 +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
bogdankostic
a4e603ce87
Deprecate Milvus1DocumentStore (#2495)
* Add warning message

* Update doc string

* Update Documentation & Code Style

* Change DeprecationWarning to FutureWarning

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-04 15:09:57 +02:00
Julian Risch
970c476615
Align TransformersReader defaults with FARMReader (#2490)
* Align TransformersReader defaults with vFARMReader

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-04 10:04:18 +02:00
James Briggs
a0bf34036f
fix dot_product metric in pinecone (#2494) 2022-05-04 09:24:10 +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
tstadel
509944f47d
Add support for positional args in pipeline.get_config() (#2478)
* add support for positional args in pipeline.get_config()

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-02 14:41:07 +02:00
tstadel
7d6b3fe954
Add flag to disable scaling scores to probabilities (#2454)
* add scale_scores_to_probabilities flag

* Update Documentation & Code Style

* fix tests

* fix sql mypy

* Update Documentation & Code Style

* fix responses

* Update Documentation & Code Style

* rename to scale_score_to_probability + docstrings

* use BaseDocumentStore.score_to_probability in elasticsearch and milvus2

* Update Documentation & Code Style

* fix tests

* Update Documentation & Code Style

* add tests

* improve naming

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-05-02 13:35:07 +02:00
tstadel
32ee271225
fix reader.eval and reader.eval_on_file output (#2476) 2022-04-29 13:52:24 +02:00
Tuana Celik
e2b85e2913
Renaming the ElasticsearchFilterOnlyRetriever to FilterRetriever (#2461)
* Renaming the ElasticsearchFilterOnlyRetriever to FilterRetriever

* adding missed init file

* Update Documentation & Code Style

* fixed docstring

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-29 10:16:02 +02:00
MichelBartels
0a80cc452c
Linearize tables in EmbeddingRetriever (#2462)
* Linearize tables in EmbeddingRetriever

* Update Documentation & Code Style

* Fix typing

* Update Documentation & Code Style

* simplify table linearization method + make it private

* Update Documentation & Code Style

* fix typing

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-28 12:06:59 +02:00
Jonathan Gallon
25b87e8cf0
Add support for aliases in elasticsearch document store (#2448)
* Add support for aliases in elasticsearch document store

* Add alias support for OpenSearch

* Missing variable index

* Update Documentation & Code Style

* Add unit test for elasticsearch alias support

* Fix unit test when index is not compatible with haystack

* Fix auto format conflict

* Add comment explaining for loop for alias

* Update Documentation & Code Style

Co-authored-by: Jonathan Gallon <jonathan.gallon@totalenergies.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
2022-04-28 10:10:37 +02:00
tstadel
2a44840f82
Ignore mypy issues regarding files param of requests.post (#2468)
* ignore mypy issues regarding files param of requests.post

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-28 08:36:29 +02:00
Malte Pietsch
766e75370c
Update docs of DeepsetCloudDocumentStore (#2460)
* Update docs of DeepsetCloudDocumentStore

* Update Documentation & Code Style

* Update docstring

Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>

* Update Documentation & Code Style

* move DEFAULT_API_ENDPOINT

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
2022-04-27 19:40:39 +02:00
tstadel
7a1e0bb7bc
rename dataset to evaluation_set when logging to mlflow (#2457) 2022-04-26 20:28:48 +02:00
tstadel
cc1bb9ad73
Disable telemetry logs per default (#2463) 2022-04-26 20:28:12 +02:00
tstadel
7498c7c6fb
Fix and use delete_index instead of delete_documents in tests (#2453)
* use delete_index instead of delete_documents in tests

* fix delete_index

* fix  delete_index() in memory and milvus

* fix imports

* fix memory keyerrors

* Update Documentation & Code Style

* increase timeout for pinecone tests to 60 minutes

* clean get_document_store()

* use recreate_index in tests

* Update Documentation & Code Style

* fix tests

* fix remaining tests

* log index deleted

* fix test_eval_pipeline

* simplify existing index detection in weaviate

* delete label_index on recreate_index for pinecone and milvus

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-26 19:06:30 +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
34bca2ba83
Make sure that debug=True and params={'debug': True} behaves the same way (#2442)
* Make sure that debug=True and params={'debug': True} behaves the same way

* Update Documentation & Code Style

* Account for the possibility of node_input being None

* Fix condition

* Avoid situation where params=None

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-26 09:24:19 +02:00
tstadel
60ff46e4e1
Log evaluation results to MLflow (#2337)
* track eval results in mlflow

* Update Documentation & Code Style

* add pipeline.yaml and environment info

* improve logging to mlflow

* Update Documentation & Code Style

* introduce ExperimentTracker

* Update Documentation & Code Style

* move modeling.utils.logger to utils.experiment_tracking

* renaming: tracker and TrackingHead

* Update Documentation & Code Style

* refactor env tracking

* fix pylint findings

* Update Documentation & Code Style

* rename MLFlowTrackingHead to MLflowTrackingHead

* implement dataset hash

* Update Documentation & Code Style

* set docstrings

* Update Documentation & Code Style

* introduce PipelineBundle and Corpus

* Update Documentation & Code Style

* support reusing index

* Update Documentation & Code Style

* rename Corpus to FileCorpus

* fix Corpus -> FileCorpus

* Update Documentation & Code Style

* resolve cyclic dependencies

* fix linter issues

* Update Documentation & Code Style

* remove helper classes

* Update Documentation & Code Style

* fix imports

* fix another unused import

* update docstrings

* Update Documentation & Code Style

* simplify usage of experiment tracking tools

* fix Literal import

* revert schema changes

* Update Documentation & Code Style

* always end run

* Update Documentation & Code Style

* fix mypy issue

* rename to execute_eval_run

* Update Documentation & Code Style

* fix merge of get_or_create_env_meta_data

* improve docstrings

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-04-25 20:14:48 +02:00