tstadel
158460504b
Make FAISSDocumentStore work with yaml ( #1727 )
...
* add faiss_index_path and faiss_config_path
* Add latest docstring and tutorial changes
* remove duplicate cleaning stuff
* refactoring + test for invalid param combination
* adjust type hints
* Add latest docstring and tutorial changes
* add documentation to @preload_index
* Add latest docstring and tutorial changes
* recursive __init__ instead of decorator
* Add latest docstring and tutorial changes
* validate instead of check
* combine ifs
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2021-11-11 11:02:22 +01:00
tstadel
14515a861b
Tutorial for DocumentClassifier at Index Time ( #1697 )
...
* basic example of document classifier in preprocessing logic
* add batch_size to TransformersDocumentClassifier
* complete tutorial16
* Add latest docstring and tutorial changes
* fix missing batch_size
* add notebook
* test for batch_size use added
* add tutorial 16 to headers.py
* Add latest docstring and tutorial changes
* make DocumentClassifier indexing pipeline rdy
* Add latest docstring and tutorial changes
* flexibility improvements for DocumentClassifier in Pipelines
* Add latest docstring and tutorial changes
* fix index time usage
* remove query from documentclassifier tests
* improve classification_field resolving + minor fixes
* Add latest docstring and tutorial changes
* tutorial 16 extended with zero shot and pipelines
* Add latest docstring and tutorial changes
* install graphviz in notebook
* Add latest docstring and tutorial changes
* remove convert_to_dicts
* Add latest docstring and tutorial changes
* Fix typo
* Add latest docstring and tutorial changes
* remove retriever from indexing pipeline
* Add latest docstring and tutorial changes
* fix save_to_yaml when using FileTypeClassifier
* emphasize the impact with zero shot classification
* Add latest docstring and tutorial changes
* adjust use_gpu to boolean in test
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-11-09 18:43:00 +01:00
Julian Risch
33b2663fdc
ensure tf-idf matrix calculation before retrieval ( #1665 )
...
* ensure tf-idf matrix calculation before retrieval
* Run fit() automatically if new documents have been added
* Add latest docstring and tutorial changes
* Fix type error
* Add test case for tfidf retriever yaml pipeline
* Use InMemoryDocStore and add 2nd test case
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2021-10-28 16:48:06 +02:00
Sara Zan
6354528336
Add /documents/get_by_filters
endpoint ( #1580 )
...
* Add endpoint to get documents by filter
* Add test for /documents/get_by_filter and extend the delete documents test
* Add rest_api/file-upload to .gitignore
* Make sure the document store is empty for each test
* Improve docstrings of delete_documents_by_filters and get_documents_by_filters
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2021-10-12 10:53:54 +02:00
oryx1729
a71180a2ca
Refactor replicas
config for Ray Pipelines ( #1378 )
2021-08-31 10:14:55 +02:00
oryx1729
bafa1b46de
Add Ray integration for Pipelines ( #1255 )
2021-08-02 14:51:24 +02:00
oryx1729
8c68699e1c
Refactor REST APIs to use Pipelines ( #922 )
2021-04-07 17:53:32 +02:00
Tanay Soni
07907f9eac
Add support for indexing pipelines ( #816 )
2021-02-16 16:24:28 +01:00
Tanay Soni
8a5dc8f826
Load Pipeline with YAML config file ( #785 )
2021-02-02 17:32:17 +01:00