pdf-to-text 5 llm 5 docx 4 document-parsing 4 pdf-to-json 4 pdf 4 retrieval-augmented-generation 3 data-pipelines 3 rag 3 deep-learning 3 information-retrieval 3 machine-learning 3 nlp 3 ocr 3 preprocessing 3 document-image-processing 2 document-image-analysis 2 donut 2 langchain 2 ml 2 natural-language-processing 2 ai 2 convert 2 documents 2 html 2 markdown 2 pdf-converter 2 pptx 2 tables 2 analysis 2 automl 2 benchmarking 2 embeddings 2 evaluation 2 llm-evaluation 2 llm-ops 2 open-source 2 ops 2 optimization 2 pipeline 2 python 2 qa 2 rag-evaluation 2 document-understanding 1 llmops 1 orchestration 1 table-structure-recognition 1