Stefano Fiorucci
c5cde40d3a
unpin ruff and update code ( #9040 )
2025-03-14 14:53:25 +00:00
Sebastian Husch Lee
6366f6577e
chore: Use thread safe import in import_class_by_name utility function ( #9028 )
...
* Use thread safe import
* fix debug string
2025-03-14 12:31:06 +01:00
Sebastian Husch Lee
3d7d65a260
Pin ruff ( #9038 )
2025-03-14 12:00:21 +01:00
Sebastian Husch Lee
363ac504dc
feat: Add warning to ChatPromptBuilder and PromptBuilder if they have variables, but required_variables is not set ( #9027 )
...
* Add warning to ChatPromptBuilder and PromptBuilder if they have variables, but required variables is not set.
* Add reno
2025-03-12 15:35:19 +01:00
Sebastian Husch Lee
4edefe3e56
Feat: Support Azure Workload Identity Credential ( #9012 )
...
* Start adding support for passing callable to Azure components
* Add to chat version
* Fix test
* Add reno
* Add support to azure doc and text embedder
* Rename
* update llm metadata extractor
* Add tests for text embedder
* Update tests
* Remove unused fixture and import
* Update reno
2025-03-12 13:45:40 +01:00
Stefano Fiorucci
4c1facdfab
fix: add dataframe to legacy fields for Document ( #9026 )
...
* fix: add dataframe to legacy fields for Document
* fmt
* small fixes
2025-03-12 13:01:03 +01:00
Sebastian Husch Lee
9905e9fa17
fix: Fix logging test ( #9024 )
...
* Pin structlog
* Fix test
2025-03-12 10:54:52 +01:00
Julian Risch
195d4031b9
chore: remove mention of 2.0 from banner ( #9010 )
...
* chore: remove mention of 2.0 from banner
* Update img alt text in readme
* Change the banner
---------
Co-authored-by: bilgeyucel <bilgeyucel96@gmail.com>
2025-03-11 09:53:51 +01:00
Mohammed Abdul Razak Wahab
7291134680
feat: Improve type validation for bare types ( #8997 )
...
* feat: Improve type validation for bare types
* added release notes
* refactor
* resolve review comments
* address review comments
* Update haystack/core/type_utils.py
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
2025-03-11 08:48:26 +01:00
Sebastian Husch Lee
3d41c04130
fix: Fix type serialization and deserialization ( #8993 )
...
* Expand tests
* New version of type serialization
* Adding more tests
* More tests
* Fix type serialization when using python 3.9
* Deserialization works with Optional now and we don't require 'typing.' to be present anymore
* Don't worry about Literal
* Add reno
* Fix mypy
* Pylint
* Add additional test
* Simplify
* Add back comment
* Fix types
* Fix
2025-03-07 11:10:16 +01:00
David S. Batista
672ab09477
fix: cleaning up InMemoryDocumentStore executor when created inside the class ( #8994 )
...
* cleaning up executor when created inside the class
* adding missed tests
2025-03-07 11:01:29 +01:00
David S. Batista
c037052581
feat: adding function to detect unmapped CID characters in PDFMinerToDocument ( #8992 )
...
* adding function to detect unmapped CID characters
* adding release notes
* adding test for logs
2025-03-06 15:44:06 +00:00
David S. Batista
4c9d08add5
feat: async support for the HuggingFaceLocalChatGenerator ( #8981 )
...
* adding async run method
* passing an optional ThreadExecutor
* adding tests
* adding release notes
* nit: license
* fixing linting
* Update releasenotes/notes/adding-async-huggingface-local-chat-generator-962512f52282d12d.yaml
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
* Use Phi isntead (#8982 )
* build: drop Python 3.8 support (#8978 )
* draft
* readd typing_extensions
* small fix + release note
* remove ruff target-version
* Update releasenotes/notes/drop-python-3.8-868710963e794c83.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* Update unstable version to 2.12.0-rc0 (#8983 )
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* fix: allow support for `include_usage` in streaming using OpenAIChatGenerator (#8968 )
* fix error in handling usage completion chunk
* ci: improve release notes format checking (#8984 )
* chore: fix invalid release note
* try improving relnote linting
* add relnotes path
* fix bad release note
* improve reno config
* fix: handle async tests in`HuggingFaceAPIChatGenerator` to prevent error (#8986 )
* add missing asyncio
* explicitly close connection in the test
* Fix tests (#8990 )
* docs: Update docstrings of `BranchJoiner` (#8988 )
* Update docstrings
* Add a bit more explanatory text
* Add reno
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Fix formatting
---------
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* PR comments
* destroying ThreadPoolExecutor when the generator instance is being destroyied, only if it was not passed externally
* fixing bug in streaming_callback
* PR comments
---------
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
Co-authored-by: Haystack Bot <73523382+HaystackBot@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
2025-03-06 15:57:11 +01:00
Sebastian Husch Lee
c4fafd9b04
docs: Update docstrings of BranchJoiner ( #8988 )
...
* Update docstrings
* Add a bit more explanatory text
* Add reno
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Update haystack/components/joiners/branch.py
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* Fix formatting
---------
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
2025-03-06 13:08:07 +01:00
Sebastian Husch Lee
24084e6431
Fix tests ( #8990 )
2025-03-06 11:17:57 +01:00
Amna Mubashar
ae26e7580b
fix: handle async tests inHuggingFaceAPIChatGenerator to prevent error ( #8986 )
...
* add missing asyncio
* explicitly close connection in the test
2025-03-06 10:55:01 +01:00
Stefano Fiorucci
40798bc4f2
ci: improve release notes format checking ( #8984 )
...
* chore: fix invalid release note
* try improving relnote linting
* add relnotes path
* fix bad release note
* improve reno config
2025-03-05 19:07:46 +01:00
Amna Mubashar
13c3768d49
fix: allow support for include_usage in streaming using OpenAIChatGenerator ( #8968 )
...
* fix error in handling usage completion chunk
2025-03-05 18:30:26 +01:00
Haystack Bot
ab67a76ecd
Update unstable version to 2.12.0-rc0 ( #8983 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-03-05 16:15:09 +01:00
Stefano Fiorucci
c04c900f26
build: drop Python 3.8 support ( #8978 )
...
* draft
* readd typing_extensions
* small fix + release note
* remove ruff target-version
* Update releasenotes/notes/drop-python-3.8-868710963e794c83.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
2025-03-05 14:59:56 +00:00
Sebastian Husch Lee
4a87ceb0ed
Use Phi isntead ( #8982 )
2025-03-05 15:53:26 +01:00
Sebastian Husch Lee
f741df88df
fix: Update flaky HugginFace Generator tests to use more reliable model and add instruction tokens ( #8980 )
...
* Fix test
* Make other HF tests more reliable
* Add back test
2025-03-05 15:26:17 +01:00
Stefano Fiorucci
ec97f4d991
update transformers test dependency to 4.48.3 ( #8979 )
2025-03-05 14:49:34 +01:00
Julian Risch
b77f2bad79
feat: Add async run to DocumentWriter ( #8962 )
...
* add async run to DocumentWriter
* reno
2025-03-05 11:53:35 +01:00
Stefano Fiorucci
bb0e36f712
feat: increase Mermaid timeout and make it configurable ( #8973 )
...
* increase Mermaid timeout and make it configurable
* rm e2e trigger
* simplify test
2025-03-05 10:49:34 +00:00
David S. Batista
9581fea3bc
feat: adding async version of InMemoryDocumentStore and associated retrievers ( #8963 )
...
* adding classes from experimental
* adding release notes
* adding tests
* merging all into a single class
* adding async retriever methods
* Update haystack/document_stores/in_memory/document_store.py
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* adding missed tests
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
2025-03-05 11:36:24 +01:00
Stefano Fiorucci
9da6696a45
chore: make openapi-llm an optional dependency ( #8958 )
...
* openapi-llm should be and optional dependency
* rm empty line
2025-03-05 11:15:19 +01:00
Stefano Fiorucci
10f11d40d4
build: support python 3.13 ( #8965 )
...
* support python 3.13
* release note
* add python version info to contributing guide
* better explanation
2025-03-05 09:49:10 +00:00
Mohammed Abdul Razak Wahab
e33a9e46ed
fix: add chat message name field ( #8969 )
...
* add-chat-message-name-field
* add release notes
* Update add-chat-message-name-field-a8ae96fb9ff13f7b.yaml
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
2025-03-05 09:29:36 +00:00
Julian Risch
830e7497c3
chore: update EvalRunResult deprecation warning to 2.12 ( #8957 )
...
* chore: update EvalRunResult deprecation warning to 2.12
* Update warning message
* format
2025-03-04 11:38:18 +00:00
Stefano Fiorucci
f3c44be904
refactor!: remove dataframe field from Document and ExtractedTableAnswer; make pandas optional ( #8906 )
...
* remove dataframe
* release note
* small fix
* group imports
* Update pyproject.toml
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
* Update pyproject.toml
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
* address feedback
---------
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
2025-03-04 11:06:07 +00:00
Mohammed Abdul Razak Wahab
0d65b4caa7
feat: Enhance error handling in Azure document embedder ( #8941 )
...
* feat: Enhance error handling in Azure document embedder
* add release notes
* address review comments
* Update releasenotes/notes/add-azure-embedder-exception-handler-c10ea46fb536de3b.yaml
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* more alignment with OpenAI impl
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
2025-03-04 11:16:08 +01:00
Amna Mubashar
28db039bca
feat: add run_async to HuggingfaceAPIChatGenerator ( #8943 )
...
* add run_async
* add release notes
* Add integration test
2025-03-03 16:51:30 +01:00
Amna Mubashar
1b2053b358
Small fix in the docstring example ( #8950 )
2025-03-03 16:26:42 +01:00
tstadel
13968cc15b
fix: in OpenAIChatGenerator set additionalProperties to False when tools_strict=True ( #8913 )
...
* fix: set ComponentTool addtionalProperties for OpenAI tools_strict=True
* add reno
* Move the additionalProperties into the OpenAIChatGenerator
* Remove
* Put additionalProperties into the correct place
* Fix test
* Update releasenotes/notes/fix-componenttool-for-openai-tools_strict-998e5cd7ebc6ec19.yaml
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
---------
Co-authored-by: Sebastian Husch Lee <sebastian.lee@deepset.ai>
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
2025-03-03 16:23:24 +01:00
Sebastian Husch Lee
296e31c182
feat: Add Type Validation parameter for Pipeline Connections ( #8875 )
...
* Starting to refactor type util tests to be more systematic
* refactoring
* Expand tests
* Update to type utils
* Add missing subclass check
* Expand and refactor tests, introduce type_validation Literal
* More test refactoring
* Test refactoring, adding type validation variable to pipeline base
* Update relaxed version of type checking to pass all newly added tests
* trim whitespace
* Add tests
* cleanup
* Updates docstrings
* Add reno
* docs
* Fix mypy and add docstrings
* Changes based on advice from Tobi
* Remove unused imports
* Doc strings
* Add connection type validation to to_dict and from_dict
* Update tests
* Fix test
* Also save connection_type_validation at global pipeline level
* Fix tests
* Remove connection type validation from the connect level, only keep at pipeline level
* Formatting
* Fix tests
* formatting
2025-03-03 16:00:22 +01:00
Sebastian Husch Lee
00fe4d157d
feat: Add run async for AzureOpenAIChatGenerator ( #8948 )
...
* Add tests for run_async
* Add reno
* Add async client
* Add init test
* Add comment
* Fix test
* Update releasenotes/notes/run-async-azure-54450f0c2495f5c8.yaml
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
---------
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
2025-03-03 14:17:18 +00:00
Sebastian Husch Lee
52a028251c
refactor!: update AzureOCRDocumentConverter to not use the dataframe field for tabular Documents ( #8885 )
...
* Save document as a csv table now
* Fix tests
* Fix tests
* Add reno
2025-03-03 12:45:02 +00:00
Michele Pangrazzi
209e6d5ff0
remove duplicate test ( #8944 )
2025-02-28 13:27:43 +00:00
mathislucka
ee81570f37
fix: only overwrite existing socket inputs when we provide a new value ( #8940 )
...
* fix: only overwrite existing socket inputs when we provide a new value
* chore: add release notes
* Apply suggestions from code review
---------
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
2025-02-27 09:13:41 +00:00
Michele Pangrazzi
db4f23771a
Avoid mutating self.routes in ConditionalRouter to_dict method ( #8936 )
...
* Avoid mutating self.routes in ConditionalRouter to_dict method
* Add release note
* Update releasenotes/notes/fix-conditional-router-to-dict-5af887da50effe11.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* Make test_router_to_dict_does_not_mutate_routes more robut (add another roundtrip)
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
2025-02-26 12:34:35 +01:00
Michele Pangrazzi
d1e503e5c7
skip HF API integration test ( #8938 )
2025-02-26 12:10:54 +01:00
Julian Risch
6652dd7550
Revert "test: skip HF API live integration tests ( #8889 )" ( #8914 )
...
* Revert "test: skip HF API live integration tests (#8889 )"
This reverts commit 56a3a9bd61b7391ae91e3d8179b3b33918ef4932.
* Replace zephyr-7b-beta model with SmolLM2-1.7B-Instruct
* Use zephyr-7b-beta model but extend instructions
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
2025-02-25 09:03:20 +01:00
mathislucka
76753fd4c6
fix: reduce number of edge cases where lazy variadic components wait for inputs that can't arrive anymore ( #8907 )
...
* wip
* fix: running order with lazy variadic components
* fix: tests
* format
* comment
* fix: alternative approach to fixing running order
* unused imports
* revert fix
* remove unneeded return
* remove data based approach to tie breaking
* release note
* trailing spaces
* newline eof
* unused import
* add more explanations to release note
2025-02-24 15:17:17 +00:00
mathislucka
a902af1db2
fix: set tags before context manager closes ( #8911 )
2025-02-24 12:34:49 +01:00
Sebastian Husch Lee
af3c89a257
feat: In FileTypeRouter add .msg to "application/vnd.ms-outlook" mapping ( #8910 )
...
* Add .msg mimetype support in file type router
* Add reno
* Update tests
2025-02-24 09:10:17 +01:00
Sebastian Husch Lee
99a998f90b
feat: Add MSGToDocument converter ( #8868 )
...
* Initial commit of MSG converter from Bijay
* Updates to the MSG converter
* Add license header
* Add tests for msg converter
* Update converter
* Expanding tests
* Update docstrings
* add license header
* Add reno
* Add to inits and pydocs
* Add test for empty input
* Fix types
* Fix mypy
---------
Co-authored-by: Bijay Gurung <bijay.learning@gmail.com>
2025-02-24 08:12:32 +01:00
Tobias Wochinger
d7dfc5222c
fix: right tracer import path ( #8908 )
2025-02-21 20:04:54 +01:00
Sebastian Husch Lee
a516672cfb
fix: Fix data dog tracing ( #8900 )
...
* Fix data dog tracing
* Add reno
* Update imports
* Fix
2025-02-21 14:35:04 +01:00
Stefano Fiorucci
3339097e99
ci: refactor job to check imports ( #8892 )
...
* refactor
* Trigger CI
* run tests if this file changes
* show failure
* revert
* rm duplicate subdir and explain in comment
2025-02-21 11:37:41 +01:00
