Files
graphify/pyproject.toml
T
Safi 64e07abd98 docs: CI, architecture guide, worked examples, README fixes
- Add GitHub Actions CI workflow (Python 3.10 and 3.12)
- Add CI badge to README
- Add ARCHITECTURE.md: pipeline overview, module table, schema, how to
  add a language extractor, security summary
- Move eval reports from tests/ to worked/httpx/ and worked/mixed-corpus/
- Fix README: test count 163→212, language table (13 languages via
  tree-sitter), extract.py description, worked examples links

benchmark: 8.8x token reduction on nanoGPT + minGPT + micrograd

- Run AST extraction on 29 Python files across 3 Karpathy repos
- 177 nodes, 246 edges, 17 communities (Leiden)
- 8.8x avg token reduction vs naive full-corpus context stuffing
- Notable: micrograd cleanly splits into engine/nn communities;
  nanoGPT model vs training loop correctly separated
- Honest: stdlib import noise flagged, config isolates documented

benchmark: 71.5x token reduction on mixed corpus (code+papers+images)

Full run: nanoGPT+minGPT+micrograd + 5 research papers + 4 images
285 nodes, 340 edges, 53 communities
Average BFS query: 1,726 tokens vs 123,488 naive (71.5x)
Code-only (AST) sub-benchmark: 8.8x on 13k-word corpus
2026-04-06 16:06:31 +01:00

54 lines
1.4 KiB
TOML

[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"
[project]
name = "graphifyy"
version = "0.1.3"
description = "Claude Code skill — turn any folder of code, docs, papers, images, or tweets into a queryable knowledge graph"
readme = "README.md"
license = { text = "MIT" }
keywords = ["claude", "claude-code", "knowledge-graph", "rag", "graphrag", "obsidian", "community-detection", "tree-sitter", "leiden", "llm"]
requires-python = ">=3.10"
dependencies = [
"networkx",
"graspologic",
"pyvis",
"tree-sitter",
"tree-sitter-python",
"tree-sitter-javascript",
"tree-sitter-typescript",
"tree-sitter-go",
"tree-sitter-rust",
"tree-sitter-java",
"tree-sitter-c",
"tree-sitter-cpp",
"tree-sitter-ruby",
"tree-sitter-c-sharp",
"tree-sitter-kotlin",
"tree-sitter-scala",
"tree-sitter-php",
]
[project.urls]
Homepage = "https://github.com/safishamsi/graphify"
Repository = "https://github.com/safishamsi/graphify"
Issues = "https://github.com/safishamsi/graphify/issues"
[project.optional-dependencies]
mcp = ["mcp"]
neo4j = ["neo4j"]
pdf = ["pypdf", "html2text"]
watch = ["watchdog"]
all = ["mcp", "neo4j", "pypdf", "html2text", "watchdog"]
[project.scripts]
graphify = "graphify.__main__:main"
[tool.setuptools.packages.find]
where = ["."]
include = ["graphify*"]
[tool.setuptools.package-data]
graphify = ["skill.md"]