sift-kg
Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents β knowledge that persists and compounds, for you and your AI agents. All from the CLI.
File Explorer
Download Latest Version (.zip)- SKILL.md
- ci.yml
- pages.yml
- alameda_research.txt
- binance.txt
- caroline_ellison.txt
- changpeng_zhao.txt
- collapse_of_ftx.txt
- ftx_company.txt
- john_ray_iii.txt
- ryan_salame.txt
- sam_bankman_fried.txt
- alameda_research.json
- binance.json
- caroline_ellison.json
- changpeng_zhao.json
- collapse_of_ftx.json
- ftx_company.json
- john_ray_iii.json
- ryan_salame.json
- sam_bankman_fried.json
- communities.json
- entity_descriptions.json
- graph.html
- graph_data.json
- merge_proposals.yaml
- narrative.md
- README.md
- communities.json
- entity_descriptions.json
- graph.html
- narrative.md
- README.md
- sift.yaml
- communities.json
- entity_descriptions.json
- graph.html
- narrative.md
- README.md
- sift.yaml
- index.html
- domain.yaml
- domain.yaml
- domain.yaml
- domain.yaml
- __init__.py
- discovery.py
- loader.py
- models.py
- __init__.py
- extractor.py
- llm_client.py
- models.py
- prompts.py
- __init__.py
- builder.py
- communities.py
- knowledge_graph.py
- postprocessor.py
- prededup.py
- __init__.py
- base.py
- chunker.py
- kreuzberg_extractor.py
- ocr.py
- pdfplumber_extractor.py
- reader.py
- __init__.py
- generator.py
- prompts.py
- __init__.py
- clustering.py
- engine.py
- io.py
- models.py
- resolver.py
- reviewer.py
- __init__.py
- app.js
- controls.html
- styles.css
- __init__.py
- __main__.py
- cli.py
- config.py
- export.py
- pipeline.py
- visualize.py
- conftest.py
- test_cli_json.py
- test_clustering.py
- test_communities.py
- test_config.py
- test_domains.py
- test_export.py
- test_extract.py
- test_graph.py
- test_ingest.py
- test_llm_client.py
- test_narrate.py
- test_prededup.py
- test_resolve.py
- test_review.py
- test_view_filters.py
- .env.example
- .gitignore
- LICENSE
- pyproject.toml
- README.md
# Installation Guide
git clone https://github.com/juanceresa/sift-kg
Downloads the entire project code from GitHub to your computer.
cd sift-kg
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommendedpip install sift-kg
Installs the package published on PyPI directly β no need to clone the source.
brew install tesseract # macOS
Installs the pre-built package via Homebrew β no source build required.
sudo apt install tesseract-ocr # Ubuntu/Debian
Installs directly from the APT package repository (Debian/Ubuntu-based).
pip install sift-kg[ocr]
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install sift-kg
Installs the package published on PyPI directly β no need to clone the source.
pip install sift-kg[ocr]
Installs the package published on PyPI directly β no need to clone the source.
pip install sift-kg[embeddings]
Installs the package published on PyPI directly β no need to clone the source.
pip install -e ".[dev]"
Installs the Python libraries listed in requirements.txt (or similar).
pip install sift-kg[embeddings] # sentence-transformers + scikit-learn (~2GB, pulls PyTorch)
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.