MCPcopy Create free account

hub / github.com/Filimoa/rd-tablebench / functions

Functions45 in github.com/Filimoa/rd-tablebench

⨍ Functions 45◇ Types & classes 1
↓ 2 callersFunctionanalyze_document_openai_sdk
(base64_image, model: str)
providers/llm.py:30
↓ 2 callersFunctionhtml_to_numpy
(html_string: str)
convert.py:6
↓ 2 callersFunctionprocess_single_file
(file_path: str)
providers/unstructured.py:28
↓ 1 callersFunctionanalyze_document
(file_content)
providers/azure_docintelligence.py:31
↓ 1 callersFunctionanalyze_document_anthropic
(base64_image, model: str)
providers/llm.py:54
↓ 1 callersFunctionazure_to_html
(table: Any)
parsing.py:153
↓ 1 callersFunctioncell_match_score
Compute the match score between two cells considering partial matches.
grading.py:16
↓ 1 callersFunctionconvert_pdf_to_base64_image
(pdf_path)
providers/llm.py:22
↓ 1 callersFunctionextract_tables
(pdf_path: str)
providers/textract.py:22
↓ 1 callersFunctionmain
(model: str, folder: str, save_to_csv: bool)
grade_cli.py:12
↓ 1 callersFunctionmain
()
parsing.py:210
↓ 1 callersFunctionmain
()
providers/reducto.py:148
↓ 1 callersFunctionneedleman_wunsch
Perform Needleman-Wunsch alignment between two sequences with free end gaps. Parameters: seq1, seq2: sequences to align (lists of string
grading.py:35
↓ 1 callersFunctionparse_async
( file_id: str, pdf_path: str, session: aiohttp.ClientSession, semaphore: asyncio.Semaphore, )
providers/reducto.py:51
↓ 1 callersFunctionparse_gemini_response
(content: str)
providers/llm.py:81
↓ 1 callersFunctionpoll_job
( file_id: str, job_id: str, session: aiohttp.ClientSession )
providers/reducto.py:82
↓ 1 callersFunctionpoll_task
( pdf_path: str, task_id: str, session: aiohttp.ClientSession )
providers/chunkr.py:54
↓ 1 callersFunctionprocess_all_pdfs
( pdfs: list[str], model: Literal[ "gemini-2.0-flash-exp", "gemini-1.5-pro", "
providers/llm.py:121
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/reducto.py:123
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/azure_docintelligence.py:58
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/chunkr.py:78
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/unstructured.py:60
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/gcloud.py:80
↓ 1 callersFunctionprocess_all_pdfs
(pdfs: list[str])
providers/textract.py:65
↓ 1 callersFunctionprocess_document
(file_path: str)
providers/gcloud.py:29
↓ 1 callersFunctionprocess_pdf
( pdf_path: str, session: aiohttp.ClientSession, upload_semaphore: asyncio.Semaphore, parse_se
providers/reducto.py:106
↓ 1 callersFunctionprocess_pdf
( pdf_path: str, session: aiohttp.ClientSession, semaphore: asyncio.Semaphore )
providers/chunkr.py:21
↓ 1 callersFunctiontable_similarity
Compute the similarity between two tables represented as ndarrays of strings, allowing for a subset of rows at the top or bottom without pena
grading.py:120
↓ 1 callersFunctionupload_pdf
( pdf_path: str, session: aiohttp.ClientSession, semaphore: asyncio.Semaphore )
providers/reducto.py:21
Functionis_rate_limit_error
(exception)
providers/azure_docintelligence.py:24
Functionnormalize_cell
(cell: str)
grading.py:135
Functionparse_azure_response
(path: str)
parsing.py:147
Functionparse_chunkr_response
(path: str)
parsing.py:60
Functionparse_gcloud_response
(path: str)
parsing.py:23
Functionparse_gemini_response
(path: str)
parsing.py:131
Functionparse_gpt4o_response
(path: str)
parsing.py:115
Functionparse_reducto_response
(path: str)
parsing.py:36
Functionparse_textract_response
(path: str)
parsing.py:13
Functionparse_unstructured_response
(path: str)
parsing.py:93
Functionprocess_pdf
(pdf_path: str, model: str)
providers/llm.py:90
Functionprocess_pdf
(pdf_path: str)
providers/azure_docintelligence.py:37
Functionprocess_pdf
(pdf_path: str)
providers/unstructured.py:48
Functionprocess_pdf
(pdf_path: str)
providers/gcloud.py:59
Functionprocess_pdf
(pdf_path: str)
providers/textract.py:45
Functiontest_single_file
(file_path: str)
providers/unstructured.py:76