ocr 4 text-extraction 3 tesseract 3 metadata-extraction 3 table-extraction 3 pdf-extraction 3 pdfium 3 python 3 rag 3 llm 2 llama 2 information-extraction 2 ernie 2 embedding 2 distributed-training 2 compression 2 bert 2 vision-language-transformer 2 vision-language-model 2 vision-language 2 text-recognition 2 neural-search 2 nlp 2 paddlenlp 2 pretrained-models 2 question-answering 2 search-engine 2 semantic-analysis 2 sentiment-analysis 2 transformers 2 uie 2 async 2 mcp 2 pandoc 2 artificial-intelligence 2 computer-vision 2 document 2 document-analysis 2 document-recognition 2 document-understanding 2 documentai 2 end-to-end-ocr 2 multimodal 2 multimodal-deep-learning 2 scene-text-detection 2 scene-text-detection-recognition 2 scene-text-recognition 2 text-detection 2 bun 1 csharp 1 elixir 1 ffi 1 golang 1 java 1 node 1 php 1 ruby 1 rust 1 wasm 1