├── .github ├── ISSUE_TEMPLATE │ ├── bug_report.md │ └── feature_request.md └── workflows │ ├── docs.yml │ ├── lint.yml │ └── pypi.yml ├── .gitignore ├── .isort.cfg ├── CODE_OF_CONDUCT.md ├── Docs2KG ├── __init__.py ├── agents │ ├── __init__.py │ ├── base.py │ ├── cloud.py │ ├── exceptions.py │ ├── func │ │ ├── __init__.py │ │ └── ner_llm_judge.py │ ├── hf.py │ ├── manager.py │ ├── ollama.py │ └── quantization.py ├── cli.py ├── digitization │ ├── __init__.py │ ├── base.py │ ├── image │ │ ├── __init__.py │ │ └── pdf_docling.py │ └── native │ │ ├── __init__.py │ │ ├── ebook.py │ │ ├── html_parser.py │ │ └── word_docling.py ├── kg_construction │ ├── __init__.py │ ├── base.py │ ├── layout_kg │ │ ├── __init__.py │ │ └── layout_kg.py │ ├── metadata_kg │ │ ├── __init__.py │ │ └── metadata_kg.py │ └── semantic_kg │ │ ├── __init__.py │ │ ├── base.py │ │ ├── ner │ │ ├── __init__.py │ │ ├── ner_prompt_based.py │ │ └── ner_spacy_match.py │ │ └── ontology │ │ ├── __init__.py │ │ └── entity_type_llm.py └── utils │ ├── __init__.py │ ├── config.py │ ├── constants.py │ ├── empty_check.py │ ├── models.py │ ├── neo4j_loader.py │ └── timer.py ├── LICENSE ├── README.md ├── __init__.py ├── config.example.yml ├── docs ├── CNAME ├── Tutorial │ ├── 1.GettingStarted.md │ ├── 2.HowToUseDocs2KGPackage.md │ ├── 3.HowToUseDocs2KGInterface.md │ └── 4.HowToExtendDocs2KG.md ├── Video.md ├── files │ └── Docs2KG.v2.pdf ├── images │ ├── AI4WA.png │ ├── AI4WA.svg │ ├── DataPreprocessing.jpg │ ├── Docs2KG-Design.jpg │ ├── Docs2KG.jpg │ ├── KGConstruction.jpg │ ├── Modules.jpg │ ├── RAG_DEMO.png │ ├── annotation_page.png │ ├── demo_query.png │ ├── demo_uploader.png │ ├── favicon.ico │ ├── interface-example.png │ ├── metric-example.png │ ├── metric.png │ ├── pdf_process.jpg │ ├── platform-demo.png │ ├── query.png │ └── settings.png └── index.md ├── examples ├── __init__.py └── compose │ └── docker-compose.yml ├── main.py ├── mkdocs.yml ├── pyproject.toml ├── requirements.dev.txt ├── requirements.txt ├── scripts └── gen_ref_pages.py ├── setup.cfg ├── setup.py └── tests └── __init__.py /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.github/ISSUE_TEMPLATE/bug_report.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.github/ISSUE_TEMPLATE/feature_request.md -------------------------------------------------------------------------------- /.github/workflows/docs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.github/workflows/docs.yml -------------------------------------------------------------------------------- /.github/workflows/lint.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.github/workflows/lint.yml -------------------------------------------------------------------------------- /.github/workflows/pypi.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.github/workflows/pypi.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/.gitignore -------------------------------------------------------------------------------- /.isort.cfg: -------------------------------------------------------------------------------- 1 | [settings] 2 | profile = black -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /Docs2KG/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/__init__.py -------------------------------------------------------------------------------- /Docs2KG/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/__init__.py -------------------------------------------------------------------------------- /Docs2KG/agents/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/base.py -------------------------------------------------------------------------------- /Docs2KG/agents/cloud.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/cloud.py -------------------------------------------------------------------------------- /Docs2KG/agents/exceptions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/exceptions.py -------------------------------------------------------------------------------- /Docs2KG/agents/func/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/agents/func/ner_llm_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/func/ner_llm_judge.py -------------------------------------------------------------------------------- /Docs2KG/agents/hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/hf.py -------------------------------------------------------------------------------- /Docs2KG/agents/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/manager.py -------------------------------------------------------------------------------- /Docs2KG/agents/ollama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/ollama.py -------------------------------------------------------------------------------- /Docs2KG/agents/quantization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/agents/quantization.py -------------------------------------------------------------------------------- /Docs2KG/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/cli.py -------------------------------------------------------------------------------- /Docs2KG/digitization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/__init__.py -------------------------------------------------------------------------------- /Docs2KG/digitization/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/base.py -------------------------------------------------------------------------------- /Docs2KG/digitization/image/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/digitization/image/pdf_docling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/image/pdf_docling.py -------------------------------------------------------------------------------- /Docs2KG/digitization/native/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/digitization/native/ebook.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/native/ebook.py -------------------------------------------------------------------------------- /Docs2KG/digitization/native/html_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/native/html_parser.py -------------------------------------------------------------------------------- /Docs2KG/digitization/native/word_docling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/digitization/native/word_docling.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/base.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/layout_kg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/layout_kg/layout_kg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/layout_kg/layout_kg.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/metadata_kg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/metadata_kg/metadata_kg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/metadata_kg/metadata_kg.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/semantic_kg/base.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/ner/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/ner/ner_prompt_based.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/semantic_kg/ner/ner_prompt_based.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/ner/ner_spacy_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/semantic_kg/ner/ner_spacy_match.py -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/ontology/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/kg_construction/semantic_kg/ontology/entity_type_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/kg_construction/semantic_kg/ontology/entity_type_llm.py -------------------------------------------------------------------------------- /Docs2KG/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Docs2KG/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/config.py -------------------------------------------------------------------------------- /Docs2KG/utils/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/constants.py -------------------------------------------------------------------------------- /Docs2KG/utils/empty_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/empty_check.py -------------------------------------------------------------------------------- /Docs2KG/utils/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/models.py -------------------------------------------------------------------------------- /Docs2KG/utils/neo4j_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/neo4j_loader.py -------------------------------------------------------------------------------- /Docs2KG/utils/timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/Docs2KG/utils/timer.py -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/README.md -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /config.example.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/config.example.yml -------------------------------------------------------------------------------- /docs/CNAME: -------------------------------------------------------------------------------- 1 | docs2kg.ai4wa.com -------------------------------------------------------------------------------- /docs/Tutorial/1.GettingStarted.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/Tutorial/1.GettingStarted.md -------------------------------------------------------------------------------- /docs/Tutorial/2.HowToUseDocs2KGPackage.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/Tutorial/2.HowToUseDocs2KGPackage.md -------------------------------------------------------------------------------- /docs/Tutorial/3.HowToUseDocs2KGInterface.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/Tutorial/3.HowToUseDocs2KGInterface.md -------------------------------------------------------------------------------- /docs/Tutorial/4.HowToExtendDocs2KG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/Tutorial/4.HowToExtendDocs2KG.md -------------------------------------------------------------------------------- /docs/Video.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/Video.md -------------------------------------------------------------------------------- /docs/files/Docs2KG.v2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/files/Docs2KG.v2.pdf -------------------------------------------------------------------------------- /docs/images/AI4WA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/AI4WA.png -------------------------------------------------------------------------------- /docs/images/AI4WA.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/AI4WA.svg -------------------------------------------------------------------------------- /docs/images/DataPreprocessing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/DataPreprocessing.jpg -------------------------------------------------------------------------------- /docs/images/Docs2KG-Design.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/Docs2KG-Design.jpg -------------------------------------------------------------------------------- /docs/images/Docs2KG.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/Docs2KG.jpg -------------------------------------------------------------------------------- /docs/images/KGConstruction.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/KGConstruction.jpg -------------------------------------------------------------------------------- /docs/images/Modules.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/Modules.jpg -------------------------------------------------------------------------------- /docs/images/RAG_DEMO.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/RAG_DEMO.png -------------------------------------------------------------------------------- /docs/images/annotation_page.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/annotation_page.png -------------------------------------------------------------------------------- /docs/images/demo_query.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/demo_query.png -------------------------------------------------------------------------------- /docs/images/demo_uploader.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/demo_uploader.png -------------------------------------------------------------------------------- /docs/images/favicon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/favicon.ico -------------------------------------------------------------------------------- /docs/images/interface-example.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/interface-example.png -------------------------------------------------------------------------------- /docs/images/metric-example.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/metric-example.png -------------------------------------------------------------------------------- /docs/images/metric.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/metric.png -------------------------------------------------------------------------------- /docs/images/pdf_process.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/pdf_process.jpg -------------------------------------------------------------------------------- /docs/images/platform-demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/platform-demo.png -------------------------------------------------------------------------------- /docs/images/query.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/query.png -------------------------------------------------------------------------------- /docs/images/settings.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/images/settings.png -------------------------------------------------------------------------------- /docs/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/docs/index.md -------------------------------------------------------------------------------- /examples/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/compose/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/examples/compose/docker-compose.yml -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mkdocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/mkdocs.yml -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/requirements.dev.txt -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/gen_ref_pages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/scripts/gen_ref_pages.py -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4WA/Docs2KG/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | --------------------------------------------------------------------------------