Index

_

__init__() (docviz.DetectionConfig method) (docviz.Document method), [1] (docviz.ExtractionChunk method) (docviz.ExtractionConfig method) (docviz.ExtractionEntry method) (docviz.ExtractionResult method) (docviz.lib.document.class_.Document method) (docviz.lib.document.Document method) (docviz.LLMConfig method) (docviz.OCRConfig method) (docviz.types.detection_config.DetectionConfig method) (docviz.types.detection_result.DetectionResult method) (docviz.types.DetectionConfig method) (docviz.types.DetectionResult method) (docviz.types.extraction_chunk.ExtractionChunk method) (docviz.types.extraction_config.ExtractionConfig method) (docviz.types.extraction_result.ExtractionEntry method), [1] (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionChunk method) (docviz.types.ExtractionConfig method) (docviz.types.ExtractionEntry method) (docviz.types.ExtractionResult method) (docviz.types.llm_config.LLMConfig method) (docviz.types.LLMConfig method) (docviz.types.ocr_config.OCRConfig method) (docviz.types.OCRConfig method)

__str__() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method) _check_dependencies_once() (in module docviz) _convert_pipeline_results_to_extraction_result() (in module docviz.lib.functions), [1] _get_page_count_cached() (in module docviz.lib.document.class_) _run_async_dependency_check() (in module docviz)

A

ALL (docviz.ExtractionType attribute) (docviz.types.extraction_type.ExtractionType attribute) (docviz.types.ExtractionType attribute)

api_key (docviz.LLMConfig attribute) (docviz.types.llm_config.LLMConfig attribute) (docviz.types.LLMConfig attribute)

B

base_url (docviz.LLMConfig attribute) (docviz.types.llm_config.LLMConfig attribute) (docviz.types.LLMConfig attribute) batch_extract() (in module docviz) (in module docviz.lib.functions), [1]

bbox (docviz.ExtractionEntry attribute) (docviz.types.detection_result.DetectionResult attribute) (docviz.types.DetectionResult attribute) (docviz.types.extraction_result.ExtractionEntry attribute), [1] (docviz.types.ExtractionEntry attribute)

C

chart_labels (docviz.OCRConfig attribute) (docviz.types.ocr_config.OCRConfig attribute) (docviz.types.OCRConfig attribute) class_ (docviz.ExtractionEntry attribute) (docviz.types.extraction_result.ExtractionEntry attribute), [1] (docviz.types.ExtractionEntry attribute) Color (in module docviz.types.aliases) confidence (docviz.DetectionConfig attribute) (docviz.ExtractionEntry attribute) (docviz.types.detection_config.DetectionConfig attribute) (docviz.types.detection_result.DetectionResult attribute) (docviz.types.DetectionConfig attribute) (docviz.types.DetectionResult attribute) (docviz.types.extraction_result.ExtractionEntry attribute), [1] (docviz.types.ExtractionEntry attribute)

CSV (docviz.SaveFormat attribute) (docviz.types.save_format.SaveFormat attribute) (docviz.types.SaveFormat attribute)

D

DetectionConfig (class in docviz) (class in docviz.types) (class in docviz.types.detection_config) DetectionResult (class in docviz.types) (class in docviz.types.detection_result) device (docviz.DetectionConfig attribute) (docviz.types.detection_config.DetectionConfig attribute) (docviz.types.DetectionConfig attribute) Document (class in docviz), [1] (class in docviz.lib.document) (class in docviz.lib.document.class_) docviz module docviz.cli module docviz.lib module docviz.lib.document module docviz.lib.document.class_ module docviz.lib.functions module, [1]

docviz.types module docviz.types.aliases module docviz.types.detection_config module docviz.types.detection_result module docviz.types.extraction_chunk module docviz.types.extraction_config module docviz.types.extraction_result module, [1] docviz.types.extraction_type module docviz.types.llm_config module docviz.types.ocr_config module docviz.types.save_format module

E

end_page (docviz.ExtractionChunk attribute) (docviz.types.extraction_chunk.ExtractionChunk attribute) (docviz.types.ExtractionChunk attribute) EQUATION (docviz.ExtractionType attribute) (docviz.types.extraction_type.ExtractionType attribute) (docviz.types.ExtractionType attribute) EXCEL (docviz.SaveFormat attribute) (docviz.types.save_format.SaveFormat attribute) (docviz.types.SaveFormat attribute) extract_chunked() (docviz.Document method), [1], [2], [3] (docviz.lib.document.class_.Document method), [1] (docviz.lib.document.Document method), [1] extract_content() (docviz.Document method), [1], [2], [3] (docviz.lib.document.class_.Document method), [1] (docviz.lib.document.Document method), [1] (in module docviz) (in module docviz.lib.functions), [1] extract_content_streaming() (in module docviz) (in module docviz.lib.functions), [1] extract_content_streaming_sync() (in module docviz) (in module docviz.lib.functions), [1] extract_content_sync() (docviz.Document method), [1], [2], [3] (docviz.lib.document.class_.Document method), [1] (docviz.lib.document.Document method), [1] (in module docviz) (in module docviz.lib.functions), [1]

extract_streaming() (docviz.Document method), [1], [2], [3] (docviz.lib.document.class_.Document method), [1] (docviz.lib.document.Document method), [1] extract_streaming_sync() (docviz.Document method), [1], [2], [3] (docviz.lib.document.class_.Document method), [1] (docviz.lib.document.Document method), [1] ExtractionChunk (class in docviz) (class in docviz.types) (class in docviz.types.extraction_chunk) ExtractionConfig (class in docviz) (class in docviz.types) (class in docviz.types.extraction_config) ExtractionEntry (class in docviz) (class in docviz.types) (class in docviz.types.extraction_result), [1] ExtractionResult (class in docviz) (class in docviz.types) (class in docviz.types.extraction_result), [1] ExtractionType (class in docviz) (class in docviz.types) (class in docviz.types.extraction_type)

F

FIGURE (docviz.ExtractionType attribute) (docviz.types.extraction_type.ExtractionType attribute) (docviz.types.ExtractionType attribute)

from_url() (docviz.Document class method), [1] (docviz.lib.document.class_.Document class method) (docviz.lib.document.Document class method)

G

get_all() (docviz.ExtractionType class method) (docviz.types.extraction_type.ExtractionType class method) (docviz.types.ExtractionType class method)

I

imagesize (docviz.DetectionConfig attribute) (docviz.types.detection_config.DetectionConfig attribute) (docviz.types.DetectionConfig attribute)

IncludesPreset (class in docviz.types)

J

JSON (docviz.SaveFormat attribute) (docviz.types.save_format.SaveFormat attribute) (docviz.types.SaveFormat attribute)

L

label (docviz.types.detection_result.DetectionResult attribute) (docviz.types.DetectionResult attribute) label_name (docviz.types.detection_result.DetectionResult attribute) (docviz.types.DetectionResult attribute) labels_to_exclude (docviz.ExtractionConfig attribute) (docviz.OCRConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute) (docviz.types.ocr_config.OCRConfig attribute) (docviz.types.OCRConfig attribute)

lang (docviz.OCRConfig attribute) (docviz.types.ocr_config.OCRConfig attribute) (docviz.types.OCRConfig attribute) layout_detection_backend (docviz.DetectionConfig attribute) (docviz.types.detection_config.DetectionConfig attribute) (docviz.types.DetectionConfig attribute) LLMConfig (class in docviz) (class in docviz.types) (class in docviz.types.llm_config)

M

MEDIA (docviz.types.IncludesPreset attribute) model (docviz.LLMConfig attribute) (docviz.types.llm_config.LLMConfig attribute) (docviz.types.LLMConfig attribute) model_path (docviz.DetectionConfig attribute) (docviz.types.detection_config.DetectionConfig attribute) (docviz.types.DetectionConfig attribute) module docviz docviz.cli docviz.lib docviz.lib.document docviz.lib.document.class_ docviz.lib.functions, [1] docviz.types docviz.types.aliases docviz.types.detection_config docviz.types.detection_result docviz.types.extraction_chunk docviz.types.extraction_config docviz.types.extraction_result, [1] docviz.types.extraction_type docviz.types.llm_config docviz.types.ocr_config docviz.types.save_format

N

numeric (in module docviz.types.aliases)

O

OCRConfig (class in docviz) (class in docviz.types) (class in docviz.types.ocr_config)

OTHER (docviz.ExtractionType attribute) (docviz.types.extraction_type.ExtractionType attribute) (docviz.types.ExtractionType attribute)

P

page_count (docviz.Document property), [1] (docviz.lib.document.class_.Document property) (docviz.lib.document.Document property) page_limit (docviz.ExtractionConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute) page_number (docviz.ExtractionEntry attribute) (docviz.types.extraction_result.ExtractionEntry attribute), [1] (docviz.types.ExtractionEntry attribute)

page_range (docviz.ExtractionChunk property) (docviz.types.extraction_chunk.ExtractionChunk property) (docviz.types.ExtractionChunk property) pdf_text_threshold_chars (docviz.ExtractionConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute) prefer_pdf_text (docviz.ExtractionConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute)

R

RectangleList (in module docviz.types.aliases) RectangleTuple (in module docviz.types.aliases) RectangleUnion (in module docviz.types.aliases)

result (docviz.ExtractionChunk attribute) (docviz.types.extraction_chunk.ExtractionChunk attribute) (docviz.types.ExtractionChunk attribute)

S

save() (docviz.ExtractionChunk method) (docviz.ExtractionResult method) (docviz.types.extraction_chunk.ExtractionChunk method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionChunk method) (docviz.types.ExtractionResult method)

SaveFormat (class in docviz) (class in docviz.types) (class in docviz.types.save_format) start_page (docviz.ExtractionChunk attribute) (docviz.types.extraction_chunk.ExtractionChunk attribute) (docviz.types.ExtractionChunk attribute)

T

TABLE (docviz.ExtractionType attribute) (docviz.types.extraction_type.ExtractionType attribute) (docviz.types.ExtractionType attribute) text (docviz.ExtractionEntry attribute) TEXT (docviz.ExtractionType attribute) text (docviz.types.extraction_result.ExtractionEntry attribute), [1] TEXT (docviz.types.extraction_type.ExtractionType attribute) text (docviz.types.ExtractionEntry attribute) TEXT (docviz.types.ExtractionType attribute) TEXT_DATA (docviz.types.IncludesPreset attribute) to_canonical_label() (docviz.ExtractionType method) (docviz.types.extraction_type.ExtractionType method) (docviz.types.ExtractionType method) to_csv() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method)

to_dataframe() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method) to_dict() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method) to_excel() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method) to_json() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method) to_xml() (docviz.ExtractionResult method) (docviz.types.extraction_result.ExtractionResult method), [1] (docviz.types.ExtractionResult method)

X

XML (docviz.SaveFormat attribute) (docviz.types.save_format.SaveFormat attribute) (docviz.types.SaveFormat attribute)

Z

zoom_x (docviz.ExtractionConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute)

zoom_y (docviz.ExtractionConfig attribute) (docviz.types.extraction_config.ExtractionConfig attribute) (docviz.types.ExtractionConfig attribute)