openedx_ai_extensions.processors.openedx.utils package

Contents

openedx_ai_extensions.processors.openedx.utils package#

Submodules#

openedx_ai_extensions.processors.openedx.utils.component_extractors module#

Clean, LLM-friendly formatting for HTML, Video, Problem, and all other XBlocks.

openedx_ai_extensions.processors.openedx.utils.component_extractors.extract_discussion_info(block) → dict#: Return discussion block metadata (IDs, category, target).

openedx_ai_extensions.processors.openedx.utils.component_extractors.extract_generic_info(block) → dict#: Catch-all extractor for unknown block types with allow-list filtering. Only fields explicitly allowed or matching allowed substrings are included.

openedx_ai_extensions.processors.openedx.utils.component_extractors.extract_html_info(block) → dict#: Return cleaned HTML block content as plain text with metadata.

openedx_ai_extensions.processors.openedx.utils.component_extractors.extract_problem_info(block, show_answer) → dict#: Return processed problem content, optionally including answers/hints.

openedx_ai_extensions.processors.openedx.utils.component_extractors.extract_video_info(block) → dict#: Extract rich metadata for video blocks, including transcripts.

openedx_ai_extensions.processors.openedx.utils.component_extractors.html_to_text(raw_html: str) → str#: Convert HTML into clean, LLM-friendly text, preserving embedded content info.

openedx_ai_extensions.processors.openedx.utils.json_to_olx module#

Utility for converting a problem definition dictionary into OLX (XML) format.

openedx_ai_extensions.processors.openedx.utils.json_to_olx.json_to_olx(problem_dict)#

Module contents#