MCPcopy Create free account

hub / github.com/VectifyAI/PageIndex / functions

Functions136 in github.com/VectifyAI/PageIndex

⨍ Functions 136◇ Types & classes 3
↓ 1 callersFunctionsingle_toc_item_index_fixer
(section_title, content, model=None)
pageindex/page_index.py:740
↓ 1 callersFunctiontoc_detector_single_page
(content, model=None)
pageindex/page_index.py:104
↓ 1 callersFunctiontoc_index_extractor
(toc, content, model=None)
pageindex/page_index.py:243
↓ 1 callersFunctiontransform_dots_to_colon
(text)
pageindex/page_index.py:223
↓ 1 callersFunctiontree_parser
(page_list, opt, doc=None, logger=None)
pageindex/page_index.py:1029
↓ 1 callersFunctiontree_thinning_for_index
(node_list, min_node_token=None, model=None)
pageindex/page_index_md.py:135
↓ 1 callersFunctionupdate_node_list_with_text_token_count
(node_list, model=None)
pageindex/page_index_md.py:89
↓ 1 callersFunctionvalidate_and_truncate_physical_indices
Validates and truncates physical indices that exceed the actual document length. This prevents errors when TOC references pages that don't ex
pageindex/page_index.py:1124
↓ 1 callersFunctionverify_toc
(page_list, list_result, start_index=1, N=None, model=None)
pageindex/page_index.py:900
Method__init__
(self, api_key: str = None, model: str = None, retrieve_model: str = None, workspace: str = None)
pageindex/client.py:35
Method__init__
(self, file_path)
pageindex/utils.py:284
Method__init__
(self, default_path: str = None)
pageindex/utils.py:655
Functionadd_node_text_with_labels
(node, pdf_pages)
pageindex/utils.py:565
Functioncheck_if_toc_extraction_is_complete
(content, toc, model=None)
pageindex/page_index.py:125
Functioncheck_token_limit
(structure, limit=110000)
pageindex/utils.py:506
Functionclean_structure_post
(data)
pageindex/utils.py:454
Functionclean_tree_for_output
(tree_nodes)
pageindex/page_index_md.py:224
Functioncreate_node_mapping
Create a flat dict mapping node_id to node for quick lookup.
pageindex/utils.py:687
Methoddebug
(self, message, **kwargs)
pageindex/utils.py:311
Methodexception
(self, message, **kwargs)
pageindex/utils.py:314
Functionextract_text_from_pdf
(pdf_path)
pageindex/utils.py:221
Functionextract_toc_content
(content, model=None)
pageindex/page_index.py:160
Functionget_document
Get document metadata: status, page count, name, and description.
examples/agentic_vectorless_rag_demo.py:63
Functionget_document_structure
Get the document's full tree structure (without text) to find relevant sections.
examples/agentic_vectorless_rag_demo.py:68
Functionget_first_start_page_from_text
(text)
pageindex/utils.py:248
Functionget_last_node
(structure)
pageindex/utils.py:217
Functionget_last_start_page_from_text
(text)
pageindex/utils.py:255
Functionget_leaf_nodes
(structure)
pageindex/utils.py:173
Functionget_nodes
(structure)
pageindex/utils.py:144
Functionget_page_content
Get the text content of specific pages or line numbers. Use tight ranges: e.g. '5-7' for pages 5 to 7, '3,8' for pages 3 and 8, '12'
examples/agentic_vectorless_rag_demo.py:73
Functionget_pdf_title
(pdf_path)
pageindex/utils.py:230
Functionget_text_of_pages
(pdf_path, start_page, end_page, tag=True)
pageindex/utils.py:236
Functionis_leaf_node
(data, node_id)
pageindex/utils.py:191
Functionprint_tree
(tree, indent=0)
pageindex/utils.py:699
Functionprint_wrapped
(text, width=100)
pageindex/utils.py:707
Functionremove_first_physical_index_section
Removes the first section between <physical_index_X> and <physical_index_X> tags, and returns the remaining text.
pageindex/page_index.py:494
← previous101–136 of 136, ranked by callers