14 Commits

Author SHA1 Message Date
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
James Briggs
8cd73a9d20
Add PineconeDocumentStore (#2254)
* added core install and functionality of pinecone doc store (init, upsert, query, delete)

* implemented core functionality of Pinecone doc store

* Update Documentation & Code Style

* updated filtering to use Haystack filtering and reduced default batch_size

* Update Documentation & Code Style

* removed debugging code

* updated Pinecone filtering to use filter_utils

* removed uneeded methods and minor tweaks to current methods

* fixed typing issues

* Update Documentation & Code Style

* Allow filters in al methods except get_embedding_count

* Fix skipping document store tests

* Update Documentation & Code Style

* Fix handling of Milvus1 and Milvus2 in tests

* Update Documentation & Code Style

* Fix handling of Milvus1 and Milvus2 in tests

* Update Documentation & Code Style

* Remove SQL from tests requiring embeddings

* Update Documentation & Code Style

* Fix get_embedding_count of Milvus2

* Make sure to start Milvus2 tests with a new collection

* Add pinecone to test suite

* Update Documentation & Code Style

* Fix typing

* Update Documentation & Code Style

* Add pinecone to docstores dependendcy

* Add PineconeDocStore to API Documentation

* Add missing comma

* Update Documentation & Code Style

* Adapt format of doc strings

* Update Documentation & Code Style

* Set API key as environment variable

* Skip Pinecone tests in forks

* Add sleep after deleting index

* Add sleep after deleting index

* Add sleep after creating index

* Add check if index ready

* Remove printing of index stats

* Create new index for each pinecone test

* Use RestAPI instead of Python API for describe_index_stats

* Fix accessing describe_index_stats

* Remove usages of describe_index_stats

* Run pinecone tests separately

* Update Documentation & Code Style

* Add pdftotext to pinecone tests

* Remove sleep from doc store fixture

* Add describe_index_stats

* Remove unused imports

* Use pull_request_target trigger

* Revert use pull_request_target trigger

* Remove set_config

* Add os to conftest

* Integrate review comments

* Set include_values to False

* Remove quotation marks from pinecone.Index type

* Update Documentation & Code Style

* Update Documentation & Code Style

* Fix number of args in error messages

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bogdankostic <bogdankostic@web.de>
2022-03-21 16:24:09 +01:00
Sara Zan
11cf94a965
Pipeline's YAML: syntax validation (#2226)
* Add BasePipeline.validate_config, BasePipeline.validate_yaml, and some new custom exception classes

* Make error composition work properly

* Clarify typing

* Help mypy a bit more

* Update Documentation & Code Style

* Enable autogenerated docs for Milvus1 and 2 separately

* Revert "Enable autogenerated docs for Milvus1 and 2 separately"

This reverts commit 282be4a78a6e95862a9b4c924fc3dea5ca71e28d.

* Update Documentation & Code Style

* Re-enable 'additionalProperties: False'

* Add pipeline.type to JSON Schema, was somehow forgotten

* Disable additionalProperties on the pipeline properties too

* Fix json-schemas for 1.1.0 and 1.2.0 (should not do it again in the future)

* Cal super in PipelineValidationError

* Improve _read_pipeline_config_from_yaml's error handling

* Fix generate_json_schema.py to include document stores

* Fix json schemas (retro-fix 1.1.0 again)

* Improve custom errors printing, add link to docs

* Add function in BaseComponent to list its subclasses in a module

* Make some document stores base classes abstract

* Add marker 'integration' in pytest flags

* Slighly improve validation of pipelines at load

* Adding tests for YAML loading and validation

* Make custom_query Optional for validation issues

* Fix bug in _read_pipeline_config_from_yaml

* Improve error handling in BasePipeline and Pipeline and add DAG check

* Move json schema generation into haystack/nodes/_json_schema.py (useful for tests)

* Simplify errors slightly

* Add some YAML validation tests

* Remove load_from_config from BasePipeline, it was never used anyway

* Improve tests

* Include json-schemas in package

* Fix conftest imports

* Make BasePipeline abstract

* Improve mocking by making the test independent from the YAML version

* Add exportable_to_yaml decorator to forget about set_config on mock nodes

* Fix mypy errors

* Comment out one monkeypatch

* Fix typing again

* Improve error message for validation

* Add required properties to pipelines

* Fix YAML version for REST API YAMLs to 1.2.0

* Fix load_from_yaml call in load_from_deepset_cloud

* fix HaystackError.__getattr__

* Add super().__init__()in most nodes and docstore, comment set_config

* Remove type from REST API pipelines

* Remove useless init from doc2answers

* Call super in Seq3SeqGenerator

* Typo in deepsetcloud.py

* Fix rest api indexing error mismatch and mock version of JSON schema in all tests

* Working on pipeline tests

* Improve errors printing slightly

* Add back test_pipeline.yaml

* _json_schema.py supports different versions with identical schemas

* Add type to 0.7 schema for backwards compatibility

* Fix small bug in _json_schema.py

* Try alternative to generate json schemas on the CI

* Update Documentation & Code Style

* Make linux CI match autoformat CI

* Fix super-init-not-called

* Accidentally committed file

* Update Documentation & Code Style

* fix test_summarizer_translation.py's import

* Mock YAML in a few suites, split and simplify test_pipeline_debug_and_validation.py::test_invalid_run_args

* Fix json schema for ray tests too

* Update Documentation & Code Style

* Reintroduce validation

* Usa unstable version in tests and rest api

* Make unstable support the latest versions

* Update Documentation & Code Style

* Remove needless fixture

* Make type in pipeline optional in the strings validation

* Fix schemas

* Fix string validation for pipeline type

* Improve validate_config_strings

* Remove type from test p[ipelines

* Update Documentation & Code Style

* Fix test_pipeline

* Removing more type from pipelines

* Temporary CI patc

* Fix issue with exportable_to_yaml never invoking the wrapped init

* rm stray file

* pipeline tests are green again

* Linux CI now needs .[all] to generate the schema

* Bugfixes, pipeline tests seems to be green

* Typo in version after merge

* Implement missing methods in Weaviate

* Trying to avoid FAISS tests from running in the Milvus1 test suite

* Fix some stray test paths and faiss index dumping

* Fix pytest markers list

* Temporarily disable cache to be able to see tests failures

* Fix pyproject.toml syntax

* Use only tmp_path

* Fix preprocessor signature after merge

* Fix faiss bug

* Fix Ray test

* Fix documentation issue by removing quotes from faiss type

* Update Documentation & Code Style

* use document properly in preprocessor tests

* Update Documentation & Code Style

* make preprocessor capable of handling documents

* import document

* Revert support for documents in preprocessor, do later

* Fix bug in _json_schema.py that was breaking validation

* re-enable cache

* Update Documentation & Code Style

* Simplify calling _json_schema.py from the CI

* Remove redundant ABC inheritance

* Ensure exportable_to_yaml works only on implementations

* Rename subclass to class_ in Meta

* Make run() and get_config() abstract in BasePipeline

* Revert unintended change in preprocessor

* Move outgoing_edges_input_node check inside try block

* Rename VALID_CODE_GEN_INPUT_REGEX into VALID_INPUT_REGEX

* Add check for a RecursionError on validate_config_strings

* Address usages of _pipeline_config in data silo and elasticsearch

* Rename _pipeline_config into _init_parameters

* Fix pytest marker and remove unused imports

* Remove most redundant ABCs

* Rename _init_parameters into _component_configuration

* Remove set_config and type from _component_configuration's dict

* Remove last instances of set_config and replace with super().__init__()

* Implement __init_subclass__ approach

* Simplify checks on the existence of _component_configuration

* Fix faiss issue

* Dynamic generation of node schemas & weed out old schemas

* Add debatable test

* Add docstring to debatable test

* Positive diff between schemas implemented

* Improve diff printing

* Rename REST API YAML files to trigger IDE validation

* Fix typing issues

* Fix more typing

* Typo in YAML filename

* Remove needless type:ignore

* Add tests

* Fix tests & validation feedback for accessory classes in custom nodes

* Refactor RAGeneratorType out

* Fix broken import in conftest

* Improve source error handling

* Remove unused import in test_eval.py breaking tests

* Fix changed error message in tests matches too

* Normalize generate_openapi_specs.py and generate_json_schema.py in the actions

* Fix path to generate_openapi_specs.py in autoformat.yml

* Update Documentation & Code Style

* Add test for FAISSDocumentStore-like situations (superclass with init params)

* Update Documentation & Code Style

* Fix indentation

* Remove commented set_config

* Store model_name_or_path in FARMReader to use in DistillationDataSilo

* Rename _component_configuration into _component_config

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-15 11:17:26 +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
bogdankostic
447baf77ef
Fix skipping of tests using document stores (#2268)
* Fix skipping document store tests

* Update Documentation & Code Style

* Fix handling of Milvus1 and Milvus2 in tests

* Update Documentation & Code Style

* Fix handling of Milvus1 and Milvus2 in tests

* Update Documentation & Code Style

* Remove SQL from tests requiring embeddings

* Update Documentation & Code Style

* Fix get_embedding_count of Milvus2

* Make sure to start Milvus2 tests with a new collection

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-03 15:19:27 +01:00
MichelBartels
2c423ba063
Introduce support for pymilvus>=2.0.0 (#2126)
* update remaining occurences of get_connection

* fix milvus2 import and fix wrong extra references

* change MilvusDocumentStore to Milvus1DocumentStore

* update milvus docstrings to reflect updated dependency management

* enable milvus 2 tests

* fix milvus2 env variable processing

* fix dropping collections for each milvus 2 test

* make Milvus 2 doc store tests work

* allow user to specify consistency level

* Fist attempt at running Milvus2 in the CI

* Install the correct pymilvus

* add batch deletion for milvus2

* change default from milvus 1 to milvus 2

* make milvus2 the default in the docstores extra

* Switch milvus1 and milvus2 in base test run on CI

* Rename docstore flags for pytest: 'milvus'->'milvus1', 'milvus2'->'milvus'

* Rename milvus.py->milvus1.py and milvus2x.py->milvus2.py

* Enable autogenerated docs for Milvus1 and 2 separately

* Partial fix to docstring of Milvus2DocumentStore

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Michel Bartels <kontakt@michelbartels.com>
Co-authored-by: Sara Zan <sara.zanzottera@deepset.ai>
2022-02-24 17:43:38 +01:00
tstadel
fe03ca70de
Fix Pipeline.components (#2215)
* add components property, improve get_document_store()

* Update Documentation & Code Style

* use pipeline.get_document_store() instead of retriever.document_store

* add tests

* Update Documentation & Code Style

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-22 15:01:07 +01:00
mathislucka
f11494a9d0
Join node should allow reciprocal rank fusion as additional merging method (#2133)
* join node should allow reciprocal rank fusion

* Update Documentation & Code Style

* add missing merging mode

* tuples are immutable

* take correct results from pipeline

* Update Documentation & Code Style

* Simple docstrings, use ValueError

* Use K=60

* Minor refactoring

* precalculate expected result in test

* Update Documentation & Code Style

* refactor to make more clear

* rm unused imports

* tests should test only one thing

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: dmigo <d.f.goryunov@gmail.com>
2022-02-10 16:58:40 +01:00
bogdankostic
f062911040
Extend metadata filtering support in ElasticsearchDocumentStore (#2108)
* Add extended filtering to ESDocumentStore

* Add Docstrings

* Fix definition of filter queries

* Fix mypy

* Add tests

* Add latest docstring and tutorial changes

* Adapt Docstrings

* Adapt tests to added test_docs

* Adapt tests to added test_docs

* Adapt tests to added test_docs

* Adapt tests to added test_docs

* Add filtering utils for same representation in all doc stores

* Apply balck formatting

* Update documentation

* Fix mypy

* Apply Black

* Fix mypy

* Adopt Doc Strings

* Add more tests

* Apply Black

* Allow filtering in OpenSearchDocStore

* Update documentation

* Adapt Docstrings

* Update documentation

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-04 13:43:12 +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
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
Adrien Wald
2edc421a09
Add top_k_join parameter to JoinDocuments.run (#2065)
* add top_k_join parameter to JoinDocuments.run

* test JoinDocuments concatenate with top_k_join parameter

* test two different top_k_join parameters
2022-01-26 17:30:16 +01:00
MichelBartels
3e4dbbb32c
Align similarity scores across document stores (#1967)
* align document store similarity functions

* remove unnecessary imports

* undone accidental change

* stopped weaviate from pretending to support dot product similarity

* stopped weaviate from pretending to support dot product similarity

* Add latest docstring and tutorial changes

* fix fixture params for document stores

* use cosine similarity for most tests

* fix cosine similarity test

* fix faiss test

* fix weaviate test

* fix accidental deletion

* fix document_store fixture

* test fix; shouldn't be merged

* fix test_normalize_embeddings_diff_shapes

* probably a better fix

* fix for parameter combinations

* revert new pytest_generate_tests functionality

* simplify pytest_generate_tests

* normalize embeddings for test_dpr_embedding

* add to faiss doc that embeddings are normalized

* Add latest docstring and tutorial changes

* remove unnecessary parameters and add comments

* simplify two lines of memory.py into one

* test similarity scores with smaller language model

* fix test_similarity_score


Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-01-12 19:28:20 +01:00
Sara Zan
1a10de506c
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
2021-11-15 12:16:27 +01:00