Index

_

_already_loaded() (_ChromaBaseLoader method) _check_parameters() (_ChromaBaseLoader method) _ChromaBaseLoader (class in docp.loaders._chromabaseloader) _ChromaBasePDFLoader (class in docp.loaders._chromabasepdfloader) _ChromaBasePPTXLoader (class in docp.loaders._chromabasepptxloader) _create_documents() (_ChromaBaseLoader method) (_ChromaBasePDFLoader method) (_ChromaBasePPTXLoader method) _create_table_directory_path() (_PDFTableParser method) _create_table_file_path() (_PDFTableParser method) _DocBase (class in docp.objects._docbaseobject) _extract_text() (_PPTXTextParser method) _extract_text_using_bbox() (_PDFTextParser method) _extract_text_using_tags() (_PDFTextParser method) _filter_tables() (_PDFTableParser static method) _get_crop_coordinates() (_PDFBaseParser method) _get_embedding_function_model() (ChromaDB method) _get_keywords() (_ChromaBaseLoader method) _load() (_ChromaBaseLoader method) _load_worker() (_ChromaBaseLoader method) _open() (_PDFBaseParser method) (_PPTXBaseParser method) _parse_text() (_ChromaBaseLoader method) (_ChromaBasePDFLoader method) (_ChromaBasePPTXLoader method) _PDFBaseParser (class in docp.parsers._pdfbaseparser) _PDFTableParser (class in docp.parsers._pdftableparser)

_PDFTextParser (class in docp.parsers._pdftextparser) _PPTXBaseParser (class in docp.parsers._pptxbaseparser) _PPTXTextParser (class in docp.parsers._pptxtextparser) _prepare_row() (_PDFBaseParser static method) _preproc() (ChromaDB static method) _print_summary() (_ChromaBaseLoader static method) _scan_common() (_PDFBaseParser method) _set_client() (ChromaDB method) _set_collection() (ChromaDB method) _set_db_client() (_ChromaBaseLoader method) _set_embedding_fn() (ChromaDB method) _set_kwargs() (ChromaPDFLoader static method) (ChromaPPTXLoader static method) _set_parser() (_ChromaBaseLoader method) (_ChromaBasePDFLoader method) (_ChromaBasePPTXLoader method) _set_paths() (_PDFBaseParser method) (_PPTXBaseParser method) _set_text_splitter() (_ChromaBaseLoader method) _split_texts() (_ChromaBaseLoader method) _store_keywords() (_ChromaBaseLoader method) _table_header_footer() (_PDFTableParser method) _test_load() (_ChromaBaseLoader method) _text_from_tags() (_PDFTextParser static method) _to_buffer() (_PDFTableParser method) _to_csv() (_PDFTableParser method) _to_df() (_PDFTableParser method) _uses_marked_content() (_PDFTextParser method)

A

add_documents() (ChromaDB method)

B

basename (_DocBase property)

C

chroma (_ChromaBaseLoader property) ChromaDB (class in docp.dbs.chroma) ChromaPDFLoader (class in docp.loaders.chromapdfloader) ChromaPPTXLoader (class in docp.loaders.chromapptxloader) client (ChromaDB property)

collect_files() (Utilities static method) collection (ChromaDB property) content (PageObject property) (SlideObject property) (TextObject property)

D

doc (_PDFBaseParser property) (_PPTXBaseParser property) docp.dbs.chroma module docp.libs.changelog module docp.libs.utilities module docp.loaders._chromabaseloader module docp.loaders._chromabasepdfloader module docp.loaders._chromabasepptxloader module docp.loaders.chromapdfloader module docp.loaders.chromapptxloader module docp.loaders.lutilities module docp.objects._docbaseobject module docp.objects._pageobject module docp.objects._slideobject module

docp.objects._textobject module docp.objects.pdfobject module docp.objects.pptxobject module docp.parsers._pdfbaseparser module docp.parsers._pdftableparser module docp.parsers._pdftextparser module docp.parsers._pptxbaseparser module docp.parsers._pptxtextparser module docp.parsers.pdfparser module docp.parsers.pptxparser module docp.parsers.putilities module DocPDF (class in docp.objects.pdfobject) DocPPTX (class in docp.objects.pptxobject)

E

embedding_function (ChromaDB property) extract_tables() (_PDFTableParser method)

extract_text() (_PDFTextParser method) (_PPTXTextParser method)

F

filepath (_DocBase property)

G

get_loader() (LoaderUtilities method)

get_parser() (ParserUtilities method)

H

hastext (PageObject property) (TextObject property)

I

images (SlideObject property)

ispdf() (Utilities static method) iszip() (Utilities static method)

L

load() (ChromaPDFLoader method) (ChromaPPTXLoader method)

LoaderUtilities (class in docp.loaders.lutilities)

M

metadata (_DocBase property) module docp.dbs.chroma docp.libs.changelog docp.libs.utilities docp.loaders._chromabaseloader docp.loaders._chromabasepdfloader docp.loaders._chromabasepptxloader docp.loaders.chromapdfloader docp.loaders.chromapptxloader docp.loaders.lutilities docp.objects._docbaseobject docp.objects._pageobject docp.objects._slideobject docp.objects._textobject docp.objects.pdfobject docp.objects.pptxobject docp.parsers._pdfbaseparser docp.parsers._pdftableparser docp.parsers._pdftextparser docp.parsers._pptxbaseparser docp.parsers._pptxtextparser docp.parsers.pdfparser docp.parsers.pptxparser docp.parsers.putilities

N

npages (_DocBase property)

ntables (_DocBase property)

P

pageno (PageObject property) (SlideObject property) PageObject (class in docp.objects._pageobject) pages (DocPDF property) parse_to_keywords() (Utilities static method) parsed_using_tags (DocPDF property) parser (_ChromaBaseLoader property) (_DocBase property) (PageObject property) (SlideObject property)

ParserUtilities (class in docp.parsers.putilities) path (ChromaDB property) PDFParser (class in docp.parsers.pdfparser) PPTXParser (class in docp.parsers.pptxparser)

S

show() (PageObject method) show_all() (ChromaDB method)

SlideObject (class in docp.objects._slideobject) slides (DocPPTX property)

T

tables (PageObject property) (SlideObject property)

TextObject (class in docp.objects._textobject) texts (SlideObject property)

U

Utilities (class in docp.libs.utilities)