yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-08-08 16:48:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,174 Commits 74 Branches 248 Tags
Commit Graph

1204 Commits

Author SHA1 Message Date
bogdankostic
728383a149
fix: Make TransformersSimilarityRanker run with single document list (#6503) 
* Make `TransformersSimilarityRanker` run with single document list

* Add release note

* Remove unused import in test
 2023-12-08 16:18:46 +01:00
Bijay Gurung
c5342d1110
fix: Prevent invalid answer from being selected in ExtractiveReader (#6460) 
* Fix invalid answer being selected issue on ExtractiveReader

* Rename variables to not shadow arguments
 2023-12-06 09:49:02 +01:00
Massimiliano Pippi
1b247ca395
clean up tests (#6488) 2023-12-05 15:49:10 +01:00
Vladimir Blagojevic
008a322023
feat: Add Indexing Pipeline (#6424) 
* Add build_indexing_pipeline utils function

* Pylint fixes

* Move into another package to avoid circular deps

* Revert change

* Revert haystack/utils/__init__.py change

* Add example

* Use DocumentStore type, remove typing checks
 2023-12-04 16:08:53 +01:00
ZanSara
a38f871dbd
feat: Add RAG pipeline (#6461) 
* add rag pipeline

* Update examples/getting_started/rag.py

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>

---------

Co-authored-by: Vladimir Blagojevic <dovlex@gmail.com>
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2023-12-04 15:25:29 +01:00
Stefano Fiorucci
4912f7cb58
refactor!: improve the deserialization logic for components that use a Document Store (#6466) 
* improve deserialization

* rm ds decorator

* improve tests

* fix pylint

* rm decorator from module init

* rm decorator

* rm decorator from factory

* fix tests

* release note

* rm print
 2023-12-04 15:17:28 +01:00
Massimiliano Pippi
a86807b834
move Cohere generator into dedicated integration (#6475) 2023-12-04 11:16:12 +01:00
Vladimir Blagojevic
b9bf83bbef
feat: Allow flat dictionary Pipeline.run() inputs (#6413) 
* Initial implementation, release note, update API and unit test
---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2023-11-30 14:37:55 +01:00
Massimiliano Pippi
7c05f37a53
remove unit marker (#6450) 2023-11-29 19:24:25 +01:00
Massimiliano Pippi
84da80c1f3
chore: make core tests layout consistent (#6449) 
* move unit tests up

* move tests up one dir, make them unit
 2023-11-29 18:58:44 +01:00
Silvano Cerza
831d0611d9
feat: Change default DuplicatePolicy in DocumentStore.write_documents() (#6438) 
* Change default DuplicatePolicy in DocumentStore.write_documents()

* Add release notes
 2023-11-28 12:30:17 +01:00
Massimiliano Pippi
00e1dd6eb8
chore: rearrange the core package, move tests and clean up (#6427) 
* rearrange code

* fix tests

* relnote

* merge test modules

* remove extra

* rearrange draw tests

* forgot

* remove unused import
 2023-11-28 09:58:56 +01:00
Silvano Cerza
e6637f5ec2 Fix all tests 2023-11-24 14:48:43 +01:00
Massimiliano Pippi
8adb8bbab8
Remove preview folder in test/ 
---------

Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2023-11-24 11:52:55 +01:00
Massimiliano Pippi
09e7831f60
clean up 1.x code 
---------

Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2023-11-24 11:47:47 +01:00
Silvano Cerza
fd16ec63cb
refactor: Add support for new filters declaration (#6397) 
* Rework filter logic for InMemoryDocumentStore to support new filters
declaration

* Fix legacy filters tests

* Simplify logic and handle dates comparison

* Rework MetadataRouter to support new filters

* Update docstrings

* Add release notes

* Fix linting

* Avoid duplicating filters specifications

* Handle corner case

* Simplify docstring

* Fix filters logic and tests

* Fix Document Store testing legacy filters tests
 2023-11-24 11:22:46 +01:00
SebastjanPrachovskij
28c2b09d90
Add SearchApi integration for websearch (#6400) 2023-11-24 11:18:43 +01:00
ZanSara
c45d8c39c7
fix: make ExtractiveReader handle situations where token_to_chars returns None instead of a (start, end) tuple (#6382) 
* fix reader bug

* add test

* log

* fix logging

* improve error message
 2023-11-24 09:08:56 +01:00
ZanSara
f3b73030a1
Fix wrong import in cohere.py and change model to model_name for consistency (#6405) 
* Fix wrong import in `cohere.py`

* model -> model_name

* fix tests too

* black

* typo

* typo
 2023-11-23 19:54:50 +01:00
ZanSara
4ec6a60a76
feat: CohereGenerator (#6395) 
* added CohereGenerator with unit tests

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* 1. added releasenote
2. removed commented files in test-cohere_generators
3. removed unused imports

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* 1. move client creation to __init__
2. remove dict casting of metadata in run

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* few fixes

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* add cohere to git workflows

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* 1. CohereGenerator as top level import in generators
2. small change in doc string

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* 1. corrected git workflow files for cohere import
2. changed api key env var from CO_API_KEY to COHERE_API_KEY

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* added cohere in missed out workflow installs

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* 1. Removed default_streaming_callback from cohere.py and added in test.
2. Added kwargs doc strings for CohereGenerator
3. removed type hints for metadata and replies
4. use COHERE_API_URL instead of hard coded URL.

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>

* Update haystack/preview/components/generators/cohere/cohere.py

Co-authored-by: Daria Fokina <daria.f93@gmail.com>

* Update haystack/preview/components/generators/cohere/cohere.py

Co-authored-by: Daria Fokina <daria.f93@gmail.com>

* Update haystack/preview/components/generators/cohere/cohere.py

Co-authored-by: Daria Fokina <daria.f93@gmail.com>

* Update haystack/preview/components/generators/cohere/cohere.py

Co-authored-by: Daria Fokina <daria.f93@gmail.com>

* Update haystack/preview/components/generators/cohere/cohere.py

Co-authored-by: Daria Fokina <daria.f93@gmail.com>

* move out of folder

* black

* fix tests

* feedback

* black

* remove api key from tests

* read api key from env var if missing

* typo

* black

* missing import

---------

Signed-off-by: sunilkumardash9 <sunilkumardash9@gmail.com>
Co-authored-by: sunilkumardash9 <sunilkumardash9@gmail.com>
Co-authored-by: Daria Fokina <daria.f93@gmail.com>
 2023-11-23 17:21:07 +01:00
jlonge4
c44e2cf49b
feat: add microsoft pptx file converter (#6399) 
* Create pptx.py

* feat: pptx converter import __init__.py

* feat: add pptx import __init__.py

* feat: add python-pptx dependency

* feat: add sample pptx for testing

* feat: add pptx file-converter test

* feat: release note pptx-file-converter-3e494d2747637eb2.yaml

* feat: Update releasenotes/notes/pptx-file-converter-3e494d2747637eb2.yaml

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>

* feat: refactor haystack/nodes/file_converter/pptx.py

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>

* fix imports

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
 2023-11-23 16:46:41 +01:00
Stefano Fiorucci
b0b514778d
fix!: make PyPDFToDocument JSON-serializable (#6396) 
* add registry

* release not

* add checks

* rm superflous check

* fix typo

* rm print :-)
 2023-11-23 15:37:20 +01:00
Ben Heckmann
a492771b4d
feat: PreProcessor split by token (tiktoken & Hugging Face) (#5276) 
* #4983 implemented split by token for tiktoken tokenizer

* #4983 added unit test for tiktoken splitting

* #4983 implemented and added a test for splitting documents with HuggingFace tokenizer

* #4983 added support for passing HF model names (instead of objects) and added an example to the HF token splitting test

* mocked HTTP model loading in unit tests, fixed pylint error

* fix lossy tokenizers splitting, use LazyImport, ignore UnicodeEncodeError for tiktoken

* reno

* rename reno file

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>
 2023-11-23 12:26:37 +01:00
Vladimir Blagojevic
e04a1f16bb
feat: Add DynamicPromptBuilder to Haystack 2.x (#6328) 
* Add DynamicPromptBuilder

* Improve pydocs, add unit tests

* Add release note

* Make expected_runtime_variables optional

* Add pydocs usage example

* Add more pydocs

* Remove test markers

* Update type in unit test

* Update after canals upgrade

* add to api ref

* docstrings updates

* Update test/preview/components/builders/test_dynamic_prompt_builder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>

* Update haystack/preview/components/builders/dynamic_prompt_builder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>

* Deparametrize init test

* Rename expected_runtime_variables to runtime_variables

* Rephrase docstring so meaning is clearer

---------

Co-authored-by: Darja Fokina <daria.f93@gmail.com>
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2023-11-23 11:41:57 +01:00
Vladimir Blagojevic
e57a593d2e
fix: Revert back to straightforward PromptBuilder (#6335) 
* Revert back to simple PromptBuilder

* Updating to full typing
 2023-11-23 11:34:06 +01:00
Vladimir Blagojevic
cfff0d5212
Rename file_converters to converters (#6390) 2023-11-23 10:28:40 +01:00
Vladimir Blagojevic
b557f3035e
feat: Add ConditionalRouter Haystack 2.x component (#6147) 
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
 2023-11-23 10:28:08 +01:00
Stefano Fiorucci
e91f7a8a4d
refactor!: improve the public interface of Generators (#6374) 
* merge lazy import blocks

* refactor generators

* release note

* revert unrelated changes
 2023-11-22 10:40:48 +01:00
ZanSara
b751978d65
Extends input types of RemoteWhisperTranscriber (#6218) 
* fix tests

* reno

* tests

* retain file name

* paths are strings for openai sdk

* streams->sources

* feedback

* always add name to file

* mypy

* test placeholder with extension

* fallback

* paths

* path test

* path must be a string

* fix test
 2023-11-22 09:57:45 +01:00
Ashwin Mathur
e6c8374562
feat: Add ByteStream metadata and other metadata to Documents created by HTMLToDocument (#6304) 
* Refactor HTMLToDocument

* Add release notes

* Add additional tests

* remove progress bar

* Add additional test for metadata

* remove progress bar from release notes

* Update tests

* Use truthiness checks instead of is not None
 2023-11-21 21:44:02 +01:00
Silvano Cerza
76165d024f
Fix corner cases and error handling with filters conversion (#6376) 2023-11-21 18:22:48 +01:00
Stefano Fiorucci
456902235a
feat: make DocumentWriter return the actual number of documents written (#6366) 
* make DocumentWriter return the actual number of documents written

* add/improve tests
 2023-11-21 15:54:25 +01:00
Daniel Fleischer
0cef17ac13
feat: embedding instructions for dense retrieval (#6372) 
* Embedding instructions in EmbeddingRetriever

Query and documents embeddings are prefixed with instructions, useful
for retrievers finetuned on specific tasks, such as Q&A.

* Tests

Checking vectors 0th component vs. reference, using different stores.

* Normalizing vectors

* Release notes
 2023-11-21 12:56:40 +01:00
Silvano Cerza
a7f742fdbd
refactor: Rename docstore fixture to document_store (#6360) 
* Prevent pytest_generate_tests from polluting preview tests

* Rename docstore fixture to document_store
 2023-11-20 17:41:48 +01:00
Silvano Cerza
83c245db74
feat: Implement function to convert legacy filters to new style (#6314) 
* Implement function to convert legacy filters to new style

* Reduce return statements in conversion to fix linting

* Move convert function in different module

* Fix typos in docstrings

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

---------

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>
 2023-11-20 13:00:05 +01:00
Agnieszka Marzec
497299c27a
Docs: Update Rankers docstrings and messages (#6296) 
* Update docstrings and messages

* Fix tests

* Fix formatting

* Update haystack/preview/components/rankers/meta_field.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>

* Fix tests

---------

Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
 2023-11-20 12:24:01 +01:00
Julian Risch
4ef2a680bb
feat: Add DocumentJoiner component 2.0 (#6105) 
* draft DocumentJoiner

* implement merge and rrf

* draft end-to-end test with DocumentJoiner in hybrid doc search pipeline

* adjust for variadics Canals PR #122

* fix text_embedder input

* adapt to the new Document class

* adapt to new doc id

* specify documents input as Variadic in run method

* compare doc ids instead of full docs

* rename text_file_converter input to sources

* update docstring

* Update haystack/preview/components/routers/document_joiner.py

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

* Apply suggestions from docstring review

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

* capitalize Documents and Retrievers in docstrings

* fix log message in test

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>
 2023-11-20 10:56:56 +01:00
ZanSara
e905066458
feat: make InMemoryDocumentStore return the number of docs actually written (#6274) 
* make InMemoryDocumentStore return the number of documents actually written

* add fixme

* reno

* add missing continue
 2023-11-20 10:03:22 +01:00
ZanSara
e888852aec
Standardize TextFileToDocument (#6232) 
* simplify textfiletodocument

* fix error handling and tests

* stray print

* reno

* streams->sources

* reno

* feedback

* test

* fix tests
 2023-11-17 15:39:39 +01:00
Silvano Cerza
c26a932423
Change preview tests to run all tests except integration ones (#6325) 2023-11-17 15:33:43 +01:00
ZanSara
dfc1d452bb
feat: upgrade canals to 0.10.1 (#6309) 
* upgrade canals

* reno

* trigger preview e2e

* bump canals

* fix decorator

* fix test

* test factory

* tests inmemory

* tests writer

* test audio

* tests builders

* tests caching

* tests embedders

* tests converters

* tests generators

* tests rankers

* tests retrievers

* fix pipeline and telemetry tests

* remove trigger
 2023-11-17 14:46:23 +01:00
Silvano Cerza
6dda6e5b2d
Change Document.__eq__ to compare all fields (#6323) 2023-11-16 17:17:43 +01:00
Massimiliano Pippi
ff3165b8b8
fix: fix un-flattening of metadata (#6318) 
* fix un-flattening of metadata

* test should pass

* add relnote

* change policy: raise an error if both meta and keys are passed

* Update document.py

* support python 3.8

* adjust wording in the error message
 2023-11-16 17:10:53 +01:00
x110
c4cfe6cb90
fix: Load additional fields from SQUAD-format file to meta field for labels #5978 (#6301) 
* Load additional fields from SQUAD-format file to meta field for labels

* added a test function

* rewritten test using pytest

* added release notes

* improve release note

* clean up test

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
 2023-11-16 10:44:51 +01:00
Vivek Silimkhan
f998bf4a4f
feat: add Amazon Bedrock support (#6226) 
* Add Bedrock

* Update supported models for Bedrock

* Fix supports and add extract response in Bedrock

* fix errors imports

* improve and refactor supports

* fix install

* fix mypy

* fix pylint

* fix existing tests

* Added Anthropic Bedrock

* fix tests

* fix sagemaker tests

* add default prompt handler, constructor and supports tests

* more tests

* invoke refactoring

* refactor model_kwargs

* fix mypy

* lstrip responses

* Add streaming support

* bump boto3 version

* add class docstrings, better exception names

* fix layer name

* add tests for anthropic and cohere model adapters

* update cohere params

* update ai21 args and add tests

* support cohere command light model

* add tital tests

* better class names

* support meta llama 2 model

* fix streaming support

* more future-proof model adapter selection

* fix import

* fix mypy

* fix pylint for preview

* add tests for streaming

* add release notes

* Apply suggestions from code review

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

* fix format

* fix tests after msg changes

* fix streaming for cohere

---------

Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
Co-authored-by: tstadel <thomas.stadelmann@deepset.ai>
Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>
 2023-11-15 13:26:29 +01:00
Julian Risch
08ec492039
refactor!: Remove routing from DocumentLanguageClassifier and rename TextLanguageClassifier (#6307) 
* remove routing from DocumentLanguageClassifier

* fix MetadataRouter typo
 2023-11-15 13:10:07 +01:00
Ashwin Mathur
4e4d5eb3e2
feat!: Remove unused query parameter from MetaFieldRanker (#6300) 
* Remove unused query parameter from MetaFieldRanker

* Add release notes
 2023-11-14 12:33:38 +01:00
Stefano Fiorucci
f708cf6056
refactor!: set scale_score default value to False (#6276) 
* set default scale_score to False

* release note
 2023-11-13 11:59:18 +01:00
Silvano Cerza
8e7ce208fc
Fix Document init when passing non existing fields (#6286) 
* Fix Document init when passing non existing fields

* Update releasenotes/notes/fix-document-init-09c1cbb14202be7d.yaml

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>

* Fix linting

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2023-11-13 11:42:42 +01:00
Vladimir Blagojevic
b4d8d1c904
feat: Add custom conversion callable to PyPDFToDocument - Haystack 2.x (#6258) 
* Allow user specified converter hook

* Add a release note

* More unit tests

* PR review - Massi, use protocol as converter
 2023-11-09 17:35:33 +01:00