qmd/package.json

114 lines
2.8 KiB
JSON
Raw Permalink Normal View History

{
"name": "@tobilu/qmd",
2026-04-06 06:18:41 +08:00
"version": "2.1.0",
"description": "Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking",
"type": "module",
"main": "dist/index.js",
"types": "dist/index.d.ts",
"exports": {
".": {
"import": "./dist/index.js",
"types": "./dist/index.d.ts"
}
},
"bin": {
"qmd": "bin/qmd"
},
"files": [
"bin/",
"dist/",
"LICENSE",
"CHANGELOG.md"
],
"scripts": {
"prepare": "[ -d .git ] && ./scripts/install-hooks.sh || true",
"build": "tsc -p tsconfig.build.json && printf '#!/usr/bin/env node\n' | cat - dist/cli/qmd.js > dist/cli/qmd.tmp && mv dist/cli/qmd.tmp dist/cli/qmd.js && chmod +x dist/cli/qmd.js",
"test": "vitest run --reporter=verbose test/",
"qmd": "tsx src/cli/qmd.ts",
"index": "tsx src/cli/qmd.ts index",
"vector": "tsx src/cli/qmd.ts vector",
"search": "tsx src/cli/qmd.ts search",
"vsearch": "tsx src/cli/qmd.ts vsearch",
"rerank": "tsx src/cli/qmd.ts rerank",
"inspector": "npx @modelcontextprotocol/inspector tsx src/cli/qmd.ts mcp",
"release": "./scripts/release.sh"
},
"publishConfig": {
"access": "public"
},
"repository": {
"type": "git",
"url": "git+https://github.com/tobi/qmd.git"
},
"homepage": "https://github.com/tobi/qmd#readme",
"bugs": {
"url": "https://github.com/tobi/qmd/issues"
},
"dependencies": {
"@modelcontextprotocol/sdk": "1.29.0",
"better-sqlite3": "12.8.0",
"fast-glob": "3.3.3",
"node-llama-cpp": "3.18.1",
"pg": "8.13.1",
"picomatch": "4.0.4",
"sqlite-vec": "0.1.9",
feat: AST-aware chunking for code files via tree-sitter Add opt-in AST-aware chunk boundary detection for code files using web-tree-sitter. When enabled with `--chunk-strategy auto`, code files (.ts, .tsx, .js, .jsx, .py, .go, .rs) are chunked at function, class, and import boundaries instead of arbitrary text positions. Default behavior (`regex`) is unchanged — no surprises on upgrade. In testing on QMD's own codebase, AST mode split 42% fewer function bodies across chunk boundaries compared to regex-only chunking. Usage: qmd embed --chunk-strategy auto qmd query "search terms" --chunk-strategy auto What's included: - Language detection from file extension with support for TypeScript, JavaScript (including arrow functions and function expressions), Python, Go, and Rust - Per-language tree-sitter queries with scored break points aligned to the existing markdown scale (class=100, function=90, type=80, import=60) - AST break points merged with regex break points — highest score wins at each position, so embedded markdown (comments, docstrings) still benefits from regex patterns - Refactored chunking core: chunkDocumentWithBreakPoints() extracted, mergeBreakPoints() added, async chunkDocumentAsync() wrapper for AST - ChunkStrategy type ("auto" | "regex") threaded through generateEmbeddings(), hybridQuery(), structuredSearch(), CLI, and SDK - getASTStatus() health check wired into `qmd status` - Parse failures log a warning and fall back to regex — never crash Hardening: - Grammar packages are optionalDependencies with pinned versions to prevent ABI breaks from semver drift - web-tree-sitter is a direct dependency (pinned) - Errors are logged (not silently swallowed) for debuggability - Tested on both Node.js and Bun (Bun is actually faster) Testing: - 26 unit tests (test/ast.test.ts) — all 4 languages, error handling - 7 integration tests (test/store.test.ts) — merge, equivalence, bypass - Standalone test-ast-chunking.mjs with 63 synthetic tests and a real-collection performance scanner (npx tsx test-ast-chunking.mjs ~/code) - Validated end-to-end with qmd embed + qmd query on QMD's own codebase - Zero markdown regressions across all test paths Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 13:22:39 +08:00
"web-tree-sitter": "0.26.7",
"yaml": "2.8.3",
"zod": "4.2.1"
},
"optionalDependencies": {
"sqlite-vec-darwin-arm64": "0.1.9",
"sqlite-vec-darwin-x64": "0.1.9",
"sqlite-vec-linux-arm64": "0.1.9",
"sqlite-vec-linux-x64": "0.1.9",
"sqlite-vec-windows-x64": "0.1.9",
feat: AST-aware chunking for code files via tree-sitter Add opt-in AST-aware chunk boundary detection for code files using web-tree-sitter. When enabled with `--chunk-strategy auto`, code files (.ts, .tsx, .js, .jsx, .py, .go, .rs) are chunked at function, class, and import boundaries instead of arbitrary text positions. Default behavior (`regex`) is unchanged — no surprises on upgrade. In testing on QMD's own codebase, AST mode split 42% fewer function bodies across chunk boundaries compared to regex-only chunking. Usage: qmd embed --chunk-strategy auto qmd query "search terms" --chunk-strategy auto What's included: - Language detection from file extension with support for TypeScript, JavaScript (including arrow functions and function expressions), Python, Go, and Rust - Per-language tree-sitter queries with scored break points aligned to the existing markdown scale (class=100, function=90, type=80, import=60) - AST break points merged with regex break points — highest score wins at each position, so embedded markdown (comments, docstrings) still benefits from regex patterns - Refactored chunking core: chunkDocumentWithBreakPoints() extracted, mergeBreakPoints() added, async chunkDocumentAsync() wrapper for AST - ChunkStrategy type ("auto" | "regex") threaded through generateEmbeddings(), hybridQuery(), structuredSearch(), CLI, and SDK - getASTStatus() health check wired into `qmd status` - Parse failures log a warning and fall back to regex — never crash Hardening: - Grammar packages are optionalDependencies with pinned versions to prevent ABI breaks from semver drift - web-tree-sitter is a direct dependency (pinned) - Errors are logged (not silently swallowed) for debuggability - Tested on both Node.js and Bun (Bun is actually faster) Testing: - 26 unit tests (test/ast.test.ts) — all 4 languages, error handling - 7 integration tests (test/store.test.ts) — merge, equivalence, bypass - Standalone test-ast-chunking.mjs with 63 synthetic tests and a real-collection performance scanner (npx tsx test-ast-chunking.mjs ~/code) - Validated end-to-end with qmd embed + qmd query on QMD's own codebase - Zero markdown regressions across all test paths Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 13:22:39 +08:00
"tree-sitter-go": "0.23.4",
"tree-sitter-python": "0.23.4",
"tree-sitter-rust": "0.24.0",
"tree-sitter-typescript": "0.23.2"
},
"devDependencies": {
"@types/better-sqlite3": "7.6.13",
"@types/pg": "8.11.10",
"tsx": "4.21.0",
"vitest": "3.2.4"
},
"pnpm": {
"onlyBuiltDependencies": [
"better-sqlite3",
"esbuild",
"node-llama-cpp",
"tree-sitter-go",
"tree-sitter-javascript",
"tree-sitter-python",
"tree-sitter-rust",
"tree-sitter-typescript"
]
},
"peerDependencies": {
2025-12-22 02:50:17 +08:00
"typescript": "^5.9.3"
},
"engines": {
"node": ">=22.0.0"
},
"keywords": [
"markdown",
"search",
"fts",
"full-text-search",
"vector",
"semantic-search",
"sqlite",
"bm25",
"embeddings",
"rag",
"mcp",
"reranking",
"knowledge-base",
"local-ai",
"llm"
],
"author": "Tobi Lutke <tobi@lutke.com>",
"license": "MIT"
}