MCPcopy Create free account

hub / github.com/adithya-s-k/omniparse / functions

Functions133 in github.com/adithya-s-k/omniparse

⨍ Functions 133◇ Types & classes 22↳ Endpoints 11
↓ 17 callersFunctionrun_example
(task_prompt, image, vision_model, vision_processor)
omniparse/image/process.py:167
↓ 10 callersFunctionencode_images
(images, inputDocument: responseDocument)
omniparse/utils.py:7
↓ 9 callersMethod__request__
Internal method to make API requests. Args: endpoint (str): API endpoint. files (dict, optional): Files to b
python-sdk/omniparse_client/omniparse.py:134
↓ 8 callersFunctionfig_to_pil
(fig)
omniparse/image/utils.py:111
↓ 8 callersFunctionplot_bbox
(image, data)
omniparse/image/utils.py:23
↓ 8 callersMethodrun
( self, url: str, word_count_threshold=MIN_WORD_THRESHOLD, bypass_cache: bool
omniparse/web/web_crawler.py:112
↓ 5 callersFunctiondecode_base64_to_pil
(base64_str)
omniparse/demo.py:164
↓ 4 callersFunctionget_shared_state
()
omniparse/__init__.py:67
↓ 4 callersMethodsave_data
Saves the parsed document data to files. Args: echo (bool): If True, prints a message after saving the data.
python-sdk/omniparse_client/utils.py:118
↓ 4 callersFunctionset_model_device
(model)
omniparse/web/model_loader.py:73
↓ 3 callersMethodadd_image
( self, image_name: str, image_data: Union[str, PILImage.Image], image_info: U
omniparse/models/__init__.py:21
↓ 2 callersFunctiondraw_polygons
(image, prediction, fill_mask=False)
omniparse/image/utils.py:67
↓ 2 callersFunctionextract_xml_data
(tags, string)
omniparse/web/utils.py:422
↓ 2 callersFunctionload_nltk_punkt
()
omniparse/web/model_loader.py:232
↓ 2 callersFunctionload_omnimodel
(load_documents: bool, load_media: bool, load_web: bool)
omniparse/__init__.py:42
↓ 2 callersFunctionsanitize_html
(html)
omniparse/web/utils.py:106
↓ 2 callersFunctiontranscribe
Transcribe the audio file using whisper
omniparse/media/utils.py:23
↓ 1 callersMethodchunk
(self, text: str)
omniparse/chunking/__init__.py:57
↓ 1 callersMethodconvert_pdf_to_markdown_and_save
(self, pdf_file_paths)
python-sdk/omniparse_client/omniparse.py:18
↓ 1 callersMethodcrawl
(self, url: str, **kwargs)
omniparse/web/crawler_strategy.py:52
↓ 1 callersFunctiondownload_all_models
Download all models required for OmniParse.
omniparse/web/model_loader.py:242
↓ 1 callersFunctiondownload_models
()
download.py:9
↓ 1 callersFunctiondownload_with_progress
(url, filename)
omniparse/web/model_loader.py:130
↓ 1 callersFunctiondraw_ocr_bboxes
(image, prediction)
omniparse/image/utils.py:94
↓ 1 callersMethodencode_image_to_base64
(self, image: PILImage.Image)
omniparse/models/__init__.py:51
↓ 1 callersFunctionescape_json_string
Escapes characters in a string to be JSON safe. Parameters: s (str): The input string to be escaped. Returns: str: The escaped
omniparse/web/utils.py:117
↓ 1 callersFunctionextract_blocks
(url, html, provider=DEFAULT_PROVIDER, api_token=None)
omniparse/web/utils.py:473
↓ 1 callersMethodextract_keywords
(self, text: str)
omniparse/chunking/__init__.py:62
↓ 1 callersFunctionextract_markdown_tables
Extracts all tables from a markdown string. Args: markdown_string (str): The input markdown string containing tables. Returns:
python-sdk/omniparse_client/utils.py:153
↓ 1 callersFunctionextract_metadata
(html)
omniparse/web/utils.py:373
↓ 1 callersMethodfetch_page
( self, url_model: UrlModel, provider: str = DEFAULT_PROVIDER, api_token: str
omniparse/web/web_crawler.py:57
↓ 1 callersFunctionflatten_nested_elements
(node)
omniparse/web/utils.py:325
↓ 1 callersFunctionget_available_memory
(device)
omniparse/web/model_loader.py:29
↓ 1 callersFunctionget_content_of_website
( url, html, word_count_threshold=MIN_WORD_THRESHOLD, css_selector=None )
omniparse/web/utils.py:175
↓ 1 callersFunctionget_device
()
omniparse/web/model_loader.py:61
↓ 1 callersFunctionget_home_folder
()
omniparse/web/model_loader.py:80
↓ 1 callersFunctionis_empty_or_whitespace
(tag: Tag)
omniparse/web/utils.py:297
↓ 1 callersFunctionload_text_multilabel_classifier
()
omniparse/web/model_loader.py:177
↓ 1 callersFunctionmain
()
server.py:41
↓ 1 callersFunctionmain
()
omniparse/web/model_loader.py:271
↓ 1 callersFunctionmarkdown_to_tables
Converts markdown tables to a list of TableObj instances. Args: markdown (str): The input markdown string containing tables. Re
python-sdk/omniparse_client/utils.py:168
↓ 1 callersFunctionparse_audio
(input_data, model_state)
omniparse/media/__init__.py:30
↓ 1 callersFunctionparse_image
(input_data, model_state)
omniparse/image/__init__.py:49
↓ 1 callersFunctionparse_url
(url: str, model_state)
omniparse/web/__init__.py:21
↓ 1 callersFunctionparse_video
(input_data, model_state)
omniparse/media/__init__.py:60
↓ 1 callersFunctionperform_completion_with_backoff
(provider, prompt_with_variables, api_token)
omniparse/web/utils.py:437
↓ 1 callersFunctionpre_process_image
(image, task_prompt, vision_model, vision_processor)
omniparse/image/process.py:97
↓ 1 callersFunctionprint_omniparse_text_art
(suffix=None)
omniparse/utils.py:24
↓ 1 callersMethodprocess_html
( self, url: str, html: str, extracted_content: str, word_count_thresh
omniparse/web/web_crawler.py:153
↓ 1 callersFunctionprocess_image
(input_data, task, model_state)
omniparse/image/__init__.py:107
↓ 1 callersFunctionprocess_image_task
( image_data: Union[str, bytes, PILImage.Image], task_prompt: str, model_state )
omniparse/image/process.py:24
↓ 1 callersMethodquit
(self)
omniparse/web/crawler_strategy.py:200
↓ 1 callersFunctionremove_empty_and_low_word_count_elements
(node, word_count_threshold)
omniparse/web/utils.py:257
↓ 1 callersFunctionremove_empty_tags
(body: Tag)
omniparse/web/utils.py:305
↓ 1 callersFunctionremove_small_text_tags
( body: Tag, word_count_threshold: int = MIN_WORD_THRESHOLD )
omniparse/web/utils.py:272
↓ 1 callersFunctionreplace_pre_tags_with_text
(node)
omniparse/web/utils.py:247
↓ 1 callersFunctionsave_images_and_markdown
(response_data, output_folder)
python-sdk/omniparse_client/utils.py:202
↓ 1 callersFunctionsplit_and_parse_json_objects
Splits a JSON string which is a list of objects and tries to parse each object. Parameters: json_string (str): A string representation o
omniparse/web/utils.py:61
↓ 1 callersMethodtake_screenshot
(self, save_path: str)
omniparse/web/crawler_strategy.py:56
↓ 1 callersMethodupdate_user_agent
(self, user_agent: str)
omniparse/web/crawler_strategy.py:60
↓ 1 callersFunctionwrap_text
(draw, text, font, max_width)
omniparse/web/utils.py:615
Method__init__
(self, api_key=None, base_url="http://localhost:8000")
python-sdk/omniparse_client/omniparse.py:11
Method__init__
(self, api_key=None, base_url="http://localhost:8000", timeout=120)
python-sdk/omniparse_client/omniparse.py:102
Method__init__
(self, *args, **kwargs)
omniparse/web/utils.py:148
Method__init__
(self, use_cached_html=False, js_code=None, **kwargs)
omniparse/web/crawler_strategy.py:65
Method__init__
( self, crawler_strategy: CrawlerStrategy = None, always_by_pass_cache: bool = True,
omniparse/web/web_crawler.py:33
Method__init__
(self, patterns=None, **kwargs)
omniparse/chunking/__init__.py:21
Method__init__
(self, **kwargs)
omniparse/chunking/__init__.py:38
Method__init__
(self, num_keywords=3, **kwargs)
omniparse/chunking/__init__.py:51
Method__init__
(self, chunk_size=100, **kwargs)
omniparse/chunking/__init__.py:91
Method__init__
(self, window_size=100, step=50, **kwargs)
omniparse/chunking/__init__.py:104
Function_classifier
(texts, threshold=0.5, max_length=64)
omniparse/web/model_loader.py:200
Functionbeautify_html
Beautifies an escaped HTML string. Parameters: escaped_html (str): A string containing escaped HTML. Returns: str: A beautifull
omniparse/web/utils.py:41
Functioncalculate_batch_size
(device)
omniparse/web/model_loader.py:41
Methodchunk
Abstract method to chunk the given text.
omniparse/chunking/__init__.py:12
Methodchunk
(self, text: str)
omniparse/chunking/__init__.py:26
Methodchunk
(self, text: str)
omniparse/chunking/__init__.py:42
Methodchunk
(self, text: str)
omniparse/chunking/__init__.py:94
Methodchunk
(self, text: str)
omniparse/chunking/__init__.py:108
Methodchunk_text
(self, chunker: Callable[[str], List[str]])
omniparse/models/__init__.py:63
Methodchunk_with_topics
(self, text: str)
omniparse/chunking/__init__.py:79
Functionconvert_to_od_format
(data)
omniparse/image/utils.py:87
Methodcrawl
(self, url: str)
omniparse/web/crawler_strategy.py:104
Functioncrawl_website
(url: str)
omniparse/web/router.py:25
Functionextract_blocks_batch
(batch_data, provider="groq/llama3-70b-8192", api_token=None)
omniparse/web/utils.py:514
Functionextract_xml_tags
(string)
omniparse/web/utils.py:417
Methodfetch_page_wrapper
(url_model, *args, **kwargs)
omniparse/web/web_crawler.py:91
Methodfetch_pages
( self, url_models: List[UrlModel], provider: str = DEFAULT_PROVIDER, api_toke
omniparse/web/web_crawler.py:79
Functionget_active_models
()
omniparse/__init__.py:71
Functionget_home_folder
()
omniparse/web/utils.py:33
Methodhandle_tag
(self, tag, attrs, start)
omniparse/web/utils.py:154
Methodimage_processor
(self, image_processor: Callable[[str], str])
omniparse/models/__init__.py:58
Functionimport_strategy
(module_name: str, class_name: str, *args, **kwargs)
omniparse/web/utils.py:633
Functionload_bert_base_uncased
()
omniparse/web/model_loader.py:89
Functionload_bge_small_en_v1_5
()
omniparse/web/model_loader.py:100
Methodload_data
(self, file_path)
python-sdk/omniparse_client/omniparse.py:15
Functionload_onnx_all_MiniLM_l6_v2
()
omniparse/web/model_loader.py:113
Functionload_text_classifier
()
omniparse/web/model_loader.py:159
Functionmerge_chunks_based_on_token_threshold
Merges small chunks into larger ones based on the total token threshold. :param chunks: List of text chunks to be merged based on token coun
omniparse/web/utils.py:563
Functionparse_any_endpoint
(file: UploadFile = File(...))
omniparse/documents/router.py:132
next →1–100 of 133, ranked by callers