yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-03 02:16:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,874 Commits 102 Branches 264 Tags
Commit Graph

11 Commits

Author SHA1 Message Date
Ulises M
bfdad40a80
feat: Add ONNX & OpenVINO backend support, and torch dtype kwargs in Sentence Transformers Components (#8813) 
* initial rough draft

* expose backend instead of extracting from model_kwargs

* explictly set backend model path

* add reno

* expose backend for ST diversity backend

* add dtype tests and expose kwargs to ST ranker for backend parameters

* skip dtype tests as torch isnt compiled with cuda

* add new openvino dependency release, unskip tests

* resolve suggestion

* mock calls, turn integrations into unit tests

* remove unnecessary test dependencies
 2025-02-13 12:04:14 +01:00
Stefano Fiorucci
5ae94886b2
fix: fix test failures with Transformers models in PRs from forks (#8809) 
* trigger

* try pinning sentence transformers

* make integr tests run right away

* pin transformers instead

* older transformers version

* rm transformers pin

* try ignoring cache

* change ubuntu version

* try removing token

* try again

* more HF_API_TOKEN local deletions

* restore test priority

* rm leftover

* more deletions

* moreee

* more

* deletions

* restore jobs order
 2025-02-04 19:08:37 +01:00
Stefano Fiorucci
f2b5f123b3
del HF token in tests (#8634) 2024-12-13 09:50:23 +01:00
David S. Batista
b5a2fad642
feat: adding Maximum Margin Relevance Ranker (#8554) 
* initial import

* linting

* adding MRR tests

* adding release notes

* fixing tests

* adding linting ignore to cross-encoder ranker

* update docstring

* refactoring

* making strategy Optional instead of Literal

* wip: adding unit tests

* refactoring MMR algorithm

* refactoring tests

* cleaning up and updating tests

* adding empty line between license + code

* bug in tests

* using Enum for strategy and similarity metric

* adding more tests

* adding empty line between license + code

* removing run time params

* PR comments

* PR comments

* fixing

* fixing serialisation

* fixing serialisation tests

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Update haystack/components/rankers/sentence_transformers_diversity.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* fixing tests

* PR comments

* PR comments

* PR comments

* PR comments

---------

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
 2024-11-22 14:58:45 +00:00
Sebastian Husch Lee
c121c86c4c
fix: Fix from_dict methods of components using HF models to work with default values (#8003) 
* Fix from_dict to work if device isn't provided in init params

* Minor refactoring of from_dict for components that load HF models

* Add tests

* Update tests to test loading with all default parameters

* Add more tests

* Add release notes

* Add unit test for whisper local

* Update reno

* Add fix for ExtractiveReader

* Fix NamedEntityExtractor
 2024-07-10 12:18:05 +02:00
Vladimir Blagojevic
535a281eec
feat: Add option to use HF_TOKEN as env var for authentication across all HF components (#7942) 
* Read both HF_API_TOKEN and HF_TOKEN env vars in all HF related components

* Add reno note

* Test fixes

* More test updates

* More test updates
 2024-06-27 10:31:58 +02:00
Massimiliano Pippi
0ceeb733ba
chore: make warm_up() usage consistent (#7752) 
* make  usage consistent

* fix error type

* release notes

* pylint fix

* change of plan

* revert

* fix test

* revert

* fix HF tests

* Apply suggestions from code review

Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com>

* fix formatting

* reformat

* fix regex match with the new error message

* fix integration test

---------

Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
 2024-05-29 10:54:21 +02:00
Sebastian Husch Lee
a2be90b95a
fix: Update device deserialization for components that use local models (#7686) 
* fix: Update device deserializtion for SentenceTransformersTextEmbedder

* Add unit test

* Fix unit test

* Make same change to doc embedder

* Add release notes

* Add same change to Diversity Ranker and Named Entity Extractor

* Add unit test

* Add the same for whisper local

* Update release notes
 2024-05-14 08:36:14 +02:00
Massimiliano Pippi
10c675d534
chore: add license header to all modules (#7675) 
* add license header to modules
* check license header at linting time
 2024-05-09 13:40:36 +00:00
Silvano Cerza
ff269db12d
Fix unit tests failing if HF_API_TOKEN is set (#7491) 2024-04-05 18:05:43 +02:00
Ashwin Mathur
38b3472bb2
feat: Add SentenceTransformersDiversityRanker (#7095) 
* Add Diversity Ranker

* Update tests

* Add separate suffix, prefix params for query and documents; allow empty query

* Update docstrings

* Make changes based on review

* Add additional tests

* Add test for warm up

* Update release notes

---------

Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
 2024-03-11 13:14:59 +01:00