* experimenting with py.typed
* try changing run method in protocol
* Trigger Build
* better docstring + release note
* remove type:ignore where possible
* Removed a few more type: ignores
---------
Co-authored-by: Sebastian Husch Lee <sjrl423@gmail.com>
* First pass at fix for deepcopying inputs and outputs
* Add reno
* Add recursion for dict objects
* Bump recursion depth
* More tests and some improvments
* Fix unit tests
* PR comments
* fix: make QUOTE_SPANS_RE regex ReDoS-safe
* Removing the capture of leading non-character on double quotes, allowing quote with new lines, adding tests
* cleaning
* fixing release notes
* changing import
* adding test for Regex Denial of Service (ReDoS)
* reducing the size/time of tests
* Update test/components/preprocessors/test_sentence_tokenizer.py
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* Update test/components/preprocessors/test_sentence_tokenizer.py
---------
Co-authored-by: Waivey <waivey@proton.me>
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* feat: add visualization methods to SuperComponent for pipeline representation
* refactor: update show and draw methods in SuperComponent to return None
* test: add unit tests
* add release note
* chore: update copyright year
* test: move unit tests to test_super_component
* Update releasenotes/notes/add-pipeline-viz-to-supercomponent-80165756cc777056.yaml
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* feat: Add sanitization for Meta field during serialization
* Revert "feat: Add sanitization for Meta field during serialization"
This reverts commit c529f7c25b69aed626bb2072c8bf171815b591cc.
* feat: add nested serialization in openai usage object
* add reno
* add nested serialization in OpenAiChatGenerator
* Update releasenotes/notes/nested-serialization-openai-usage-object-3817b07342999edf.yaml
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
* merge tests
* Adjust the test
---------
Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* AzureOCR: convert integration test to unit test and simplify
* clean up HuggingFaceAPITextEmbedder
* clean up LinkContentFetcher
* simplify HuggingFaceLocalGenerator
* clean up OpenAIGenerator
* OpenAIChatGenerator
* SentenceTransformersDiversityRanker
* TransformersSimilarityRanker
* ChatMessage: rm outdated tests
* fail fast false
* typo
* feat: Add support for multiple outputs in ConditionalRouter
* Update haystack/components/routers/conditional_router.py
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* add additional route
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* Fix for handling wrapped ChatCompletion instances in streaming (used by tools like weave)
* Add release note
* Applied same fix to OpenAIGenerator ; Refactoring ; Update release note
* Fix integration test error after refactoring
* fix: use coerce_tag_value in LoggingTracer to serialize tag values
* add rn
* fix tests
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* try setting hatch variables
* debug steps
* stop caching on ubuntu
* remove debug steps
* cache should work for mac and wind
* bring back cache and log verbose; temp skip win and mac
* try
* stop caching Hatch python environment for Ubuntu
* remove trigger
* added async support for HuggingFaceAPIDocumentEmbedder
* added type anotations, removed unused import
* Trigger mark test complited
* Apply suggestions from code review
* utility function
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* Agent tracing
* Small changes
* Some changes and refactoring
* Refactoring to reuse code
* Fix
* Add reno
* Fix tests
* Fix tests
* Fix linting
* Refactor and add tracing support to run_async of Agent
* Reduce duplicate code
* Remove finalize_run
* Use break instead of copying code three times
* Adding a test
* Add tracing unit tests
* Make async tracing test actually run async
* Increase test coverage
* Unit test for traces in pipeline
* Add cleanup
* Fix proper indentation
* PR comments
* PR comments and new test
* Update warning message
* Update warning message
---------
Co-authored-by: Vladimir Blagojevic <dovlex@gmail.com>
