3 results found Sort:

Unstructured-IO
unstructured Unstructured-IO
704
8.6k
apache-2.0
58
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
ml llm nlp ocr pdf docx donut langchain pdf-to-json pdf-to-text deep-learning preprocessing data-pipelines document-parser document-parsing machine-learning information-retrieval document-image-analysis document-image-processing natural-language-processing
Created 2022-09-26
1,580 commits to main branch, last one a day ago
edenai
edenai-apis edenai
56
410
apache-2.0
7
Eden AI: simplify the use and deployment of AI technologies by providing a unique API that connects to the best possible AI engines
ai api nlp ocr python aggregator speech-to-text text-to-speech ai-as-a-service computer-vision document-parsing image-processing pre-trained-model video-recognition speech-recognition machine-translation natural-language-processing optical-character-recognition
Created 2022-10-24
2,174 commits to master branch, last one 2 days ago
papercast-dev
papercast papercast-dev
1
42
mit
1
A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines...
dag nlp tts arxiv grobid python podcast pipeline pdf-to-text pdf-converter document-parser document-parsing semantic-scholar pdf-document-processor
Created 2023-03-31
108 commits to main branch, last one about a month ago