diff --git a/haystack/components/preprocessors/document_cleaner.py b/haystack/components/preprocessors/document_cleaner.py index f186e75fcf9..c8f761be7f8 100644 --- a/haystack/components/preprocessors/document_cleaner.py +++ b/haystack/components/preprocessors/document_cleaner.py @@ -270,6 +270,8 @@ def _find_and_remove_header_footer( Note: This heuristic uses exact matches and therefore works well for footers like "Copyright 2019 by XXX", but won't detect "Page 3 of 4" or similar. + :param text: The text to remove headers and footers from, with pages separated by the + form feed character described above. :param n_chars: The number of first/last characters where the header/footer shall be searched in. :param n_first_pages_to_ignore: The number of first pages to ignore (e.g. TOCs often don't contain footer/header). diff --git a/haystack/core/pipeline/base.py b/haystack/core/pipeline/base.py index c2e62f31587..531f9d6f797 100644 --- a/haystack/core/pipeline/base.py +++ b/haystack/core/pipeline/base.py @@ -1226,6 +1226,8 @@ def _consume_component_inputs( :param component_name: The name of a component. :param component: Component with component metadata. :param inputs: Global inputs state. + :param is_resume: Whether the component is being resumed from a breakpoint. If True, the inputs + have already been consumed, so the first available value is returned for each socket. :returns: The inputs for the component. """ component_inputs = inputs.get(component_name, {}) diff --git a/haystack/core/pipeline/draw.py b/haystack/core/pipeline/draw.py index 1e2a9f7f8f1..4efa4f27c50 100644 --- a/haystack/core/pipeline/draw.py +++ b/haystack/core/pipeline/draw.py @@ -262,6 +262,9 @@ def _to_mermaid_image( Dictionary of customization parameters. See `validate_mermaid_params` for valid keys. :param timeout: Timeout in seconds for the request to the Mermaid server. + :param super_component_mapping: + Mapping of component names to the name of the SuperComponent that contains them, used to + group those components visually in the rendered diagram. :returns: The image, SVG, or PDF data returned by the Mermaid server as bytes. :raises ValueError: diff --git a/haystack/core/pipeline/pipeline.py b/haystack/core/pipeline/pipeline.py index 5419a926ca0..1932fe01172 100644 --- a/haystack/core/pipeline/pipeline.py +++ b/haystack/core/pipeline/pipeline.py @@ -141,6 +141,8 @@ def _run_component( :param component_visits: Current state of component visits. :param parent_span: The parent span to use for the newly created span. This is to allow tracing to be correctly linked to the pipeline run. + :param break_point: An optional breakpoint. If it targets this component and its visit + count matches the current one, a `BreakpointException` is raised before the Component runs. :raises PipelineRuntimeError: If Component doesn't return a dictionary. :return: The output of the Component. """