* Parametrize document joiner tests with empty lists
* Skip loop in _distribution_based_rank_fusion if document list is empty
* Parametrize test_empty_list with join_mode
* Prevent division by zero in _merge and _reciprocal_rank_fusion
* Add release notes
---------
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
* Add log lines for PDF conversion and make skipping more explicit in DocumentSplitter
* Add logging statement for PDFMinerToDocument as well
* Add tests
* Remove unused line
* Remove unused line
* add reno
* Add in PDF file
* Update checks in PDF converters and add tests for document splitter
* Revert
* Remove line
* Fix comment
* Make mypy happy
* Make mypy happy
* draft
* Enhance
* Almost works
* Simplify some parts and handle intermediate outputs
* Handle connections with default
* Handle cycles with multiple connections from two components
* Update distributed outputs at the correct time
* Remove Component inputs after it runs
* Add agent pipeline test case
* Fix infite loop test
* Handle some corner cases with loops checking and inputs deletion
* Fix tests
* Add new behavioral test
* Remove unused code in behavioural test
* Fix behavioural test
* Fix max run check
* Simplify outputs distribution
* Simplify subgraph run check
* Remove unused _init_run_queue function
* Remove commented code
* Add some missing type hints
* Simplify cycles breaking
* Fix _distribute_output test
* Fix _find_components_that_will_receive_no_input test
* Fix validation test
* Fix tracer losing Component inputs
* Fix some linting issues
* Remove ignore pylint rule
* Rename method that break cycles and make it raise
* Add docstring to _run_subgraph
* Update Pipeline.run() docstring
* Update comment to clarify cycles execution
* Remove SelfLoop sample Component
* Add behavioural test for unsupported cycles
* Rename behavioural test to be more specific
* Add new behavioural test
* Add release notes
* Remove commented out code and random pass
* Use more efficient function to find cycles
* Simplify _break_supported_cycles_in_graph by using defaultdict
* Stop breaking edges as soon as we make the graph acyclic
* Fix docstring and add some more comments
* Fix _distribute_output docstring
* Fix _find_receivers_from docstring
* More detailed release notes
* Minimize calls to networkx.is_directed_acyclic_graph
* Add some more info on edges keys
* Adjust components_in_cycles comment
* Add new Pipeline behavioural test
* Enhance _find_components_that_will_receive_no_input to cover more cases
* Explain why run_queue is reset after running a subgraph cycle
* Rename _init_inputs_state to _normalize_input_data
* Better explain the subgraph output distribution
* Remove for else
* Fix some comments and docstrings
* Fix linting
* Add missing return type
* Fix typo
* Rename _normalize_input_data to _normalize_varidiac_input_data and add more documentation
* Remove unused import
---------
Co-authored-by: Sebastian Husch Lee <sjrl423@gmail.com>
* initial import
* Update haystack/components/generators/openai.py
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* docs: fixing
* supporting the three use cases: no system prompt, using system prompt defined at init, using system prompt defined at run time
* renaming 'run_time_system_prompt' to 'system_prompt'
* adding tests, converting methods to static
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* reduced usage of numpy and substituted built-in libraries
* added release note
* edited expit function to support both float as well as list (this case was giving error CI)
* revert code , numpy can't be removed here
* more cleaning
* fix relnote
---------
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
* add config_kwargs
* disable PLR0913 for a specific function
* add a release note
* refer to AutoConfig in config_kwargs docstring
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
Co-authored-by: Julian Risch <julianrisch@gmx.de>
* draft new component and tests
* draft new component and tests
* fix tests, replace usage of get_attr
* improve docstrings, refactor tests
* add test for mixed documents w/wo scores
* add test with multiple lists and update docstring
* validate inputs, add tests, make methods static
* change fallback to binary relevance
* rename validate_init_parameters to validate_inputs
* fix: make `from_dict` of `PyPDFToDocument` more robust
* chore: drop trailing space
* converting method to static and making the comment shorter
* reverting method to static
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
