| | data | |
| | experimental | |
| | legacy | |
| | advanced_chunking_and_serialization.ipynb | 35.0 KB |
| | asr_pipeline_performance_comparison.py | 9.9 KB |
| | backend_csv.ipynb | 3.5 KB |
| | backend_xml_rag.ipynb | 39.8 KB |
| | batch_convert.py | 8.4 KB |
| | chart_extraction.py | 4.1 KB |
| | code_formula_granite_docling.py | 3.7 KB |
| | compare_vlm_models.py | 7.8 KB |
| | custom_convert.py | 7.9 KB |
| | demo_layout_vlm.py | 5.7 KB |
| | develop_formula_understanding.py | 3.7 KB |
| | develop_picture_enrichment.py | 4.1 KB |
| | dpk-ingest-chunk-tokenize.ipynb | 30.8 KB |
| | enrich_doclingdocument.py | 5.1 KB |
| | enrich_simple_pipeline.py | 916 B |
| | export_figures.py | 4.2 KB |
| | export_multimodal.py | 4.5 KB |
| | export_tables.py | 2.3 KB |
| | extraction.ipynb | 34.2 KB |
| | full_page_ocr.py | 2.5 KB |
| | gpu_standard_pipeline.py | 2.4 KB |
| | gpu_vlm_pipeline.py | 3.7 KB |
| | granitedocling_repetition_stopping.py | 3.8 KB |
| | hybrid_chunking.ipynb | 22.5 KB |
| | index.md | 1.7 KB |
| | inspect_picture_content.py | 1.5 KB |
| | minimal_asr_pipeline.py | 3.3 KB |
| | minimal_vlm_pipeline.py | 3.2 KB |
| | minimal.py | 1009 B |
| | mlx_whisper_example.py | 5.7 KB |
| | model_family_engines_example.py | 5.7 KB |
| | parquet_images.py | 6.5 KB |
| | picture_description_inline.py | 5.4 KB |
| | pictures_description_api.py | 7.7 KB |
| | pictures_description.ipynb | 767.3 KB |
| | pii_obfuscate.py | 13.5 KB |
| | post_process_ocr_with_vlm.py | 26.9 KB |
| | rag_azuresearch.ipynb | 94.1 KB |
| | rag_haystack.ipynb | 15.7 KB |
| | rag_langchain.ipynb | 15.1 KB |
| | rag_llamaindex.ipynb | 19.3 KB |
| | rag_milvus.ipynb | 17.3 KB |
| | rag_mongodb.ipynb | 36.5 KB |
| | rag_opensearch.ipynb | 78.8 KB |
| | rag_weaviate.ipynb | 39.9 KB |
| | rapidocr_with_custom_models.py | 2.6 KB |
| | retrieval_qdrant.ipynb | 14.0 KB |
| | run_md.py | 1.2 KB |
| | run_with_accelerator.py | 2.9 KB |
| | run_with_formats_html_rendered_mp.py | 11.7 KB |
| | run_with_formats_html_rendered.py | 4.2 KB |
| | run_with_formats.py | 4.1 KB |
| | serialization.ipynb | 72.0 KB |
| | suryaocr_with_custom_models.py | 1.9 KB |
| | tesseract_lang_detection.py | 1.7 KB |
| | translate.py | 3.6 KB |
| | visual_grounding.ipynb | 1.2 MB |
| | vlm_pipeline_api_model.py | 17.7 KB |
| | xbrl_conversion.ipynb | 17.3 KB |