Initial commit: QMD - Quick Markdown Search
A CLI tool for searching markdown knowledge bases using hybrid retrieval: - BM25 full-text search via SQLite FTS5 - Vector semantic search via sqlite-vec + Ollama embeddings - LLM re-ranking with qwen3-reranker (logprobs-based scoring) - Reciprocal Rank Fusion with weighted queries and position-aware blending Features: - `qmd add .` - Index markdown files in current directory - `qmd embed` - Generate vector embeddings - `qmd search` - BM25 full-text search - `qmd vsearch` - Vector similarity search - `qmd query` - Hybrid search with query expansion + reranking 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Tobi Lutke
commit
39193ea252
9
.gitignore
vendored
Normal file
9
.gitignore
vendored
Normal file
@ -0,0 +1,9 @@
|
||||
node_modules/
|
||||
*.sqlite
|
||||
.DS_Store
|
||||
archive/
|
||||
texts/
|
||||
.cursor/
|
||||
*.md
|
||||
!README.md
|
||||
!CLAUDE.md
|
||||
111
CLAUDE.md
Normal file
111
CLAUDE.md
Normal file
@ -0,0 +1,111 @@
|
||||
---
|
||||
description: Use Bun instead of Node.js, npm, pnpm, or vite.
|
||||
globs: "*.ts, *.tsx, *.html, *.css, *.js, *.jsx, package.json"
|
||||
alwaysApply: false
|
||||
---
|
||||
|
||||
Default to using Bun instead of Node.js.
|
||||
|
||||
- Use `bun <file>` instead of `node <file>` or `ts-node <file>`
|
||||
- Use `bun test` instead of `jest` or `vitest`
|
||||
- Use `bun build <file.html|file.ts|file.css>` instead of `webpack` or `esbuild`
|
||||
- Use `bun install` instead of `npm install` or `yarn install` or `pnpm install`
|
||||
- Use `bun run <script>` instead of `npm run <script>` or `yarn run <script>` or `pnpm run <script>`
|
||||
- Bun automatically loads .env, so don't use dotenv.
|
||||
|
||||
## APIs
|
||||
|
||||
- `Bun.serve()` supports WebSockets, HTTPS, and routes. Don't use `express`.
|
||||
- `bun:sqlite` for SQLite. Don't use `better-sqlite3`.
|
||||
- `Bun.redis` for Redis. Don't use `ioredis`.
|
||||
- `Bun.sql` for Postgres. Don't use `pg` or `postgres.js`.
|
||||
- `WebSocket` is built-in. Don't use `ws`.
|
||||
- Prefer `Bun.file` over `node:fs`'s readFile/writeFile
|
||||
- Bun.$`ls` instead of execa.
|
||||
|
||||
## Testing
|
||||
|
||||
Use `bun test` to run tests.
|
||||
|
||||
```ts#index.test.ts
|
||||
import { test, expect } from "bun:test";
|
||||
|
||||
test("hello world", () => {
|
||||
expect(1).toBe(1);
|
||||
});
|
||||
```
|
||||
|
||||
## Frontend
|
||||
|
||||
Use HTML imports with `Bun.serve()`. Don't use `vite`. HTML imports fully support React, CSS, Tailwind.
|
||||
|
||||
Server:
|
||||
|
||||
```ts#index.ts
|
||||
import index from "./index.html"
|
||||
|
||||
Bun.serve({
|
||||
routes: {
|
||||
"/": index,
|
||||
"/api/users/:id": {
|
||||
GET: (req) => {
|
||||
return new Response(JSON.stringify({ id: req.params.id }));
|
||||
},
|
||||
},
|
||||
},
|
||||
// optional websocket support
|
||||
websocket: {
|
||||
open: (ws) => {
|
||||
ws.send("Hello, world!");
|
||||
},
|
||||
message: (ws, message) => {
|
||||
ws.send(message);
|
||||
},
|
||||
close: (ws) => {
|
||||
// handle close
|
||||
}
|
||||
},
|
||||
development: {
|
||||
hmr: true,
|
||||
console: true,
|
||||
}
|
||||
})
|
||||
```
|
||||
|
||||
HTML files can import .tsx, .jsx or .js files directly and Bun's bundler will transpile & bundle automatically. `<link>` tags can point to stylesheets and Bun's CSS bundler will bundle.
|
||||
|
||||
```html#index.html
|
||||
<html>
|
||||
<body>
|
||||
<h1>Hello, world!</h1>
|
||||
<script type="module" src="./frontend.tsx"></script>
|
||||
</body>
|
||||
</html>
|
||||
```
|
||||
|
||||
With the following `frontend.tsx`:
|
||||
|
||||
```tsx#frontend.tsx
|
||||
import React from "react";
|
||||
|
||||
// import .css files directly and it works
|
||||
import './index.css';
|
||||
|
||||
import { createRoot } from "react-dom/client";
|
||||
|
||||
const root = createRoot(document.body);
|
||||
|
||||
export default function Frontend() {
|
||||
return <h1>Hello, world!</h1>;
|
||||
}
|
||||
|
||||
root.render(<Frontend />);
|
||||
```
|
||||
|
||||
Then, run index.ts
|
||||
|
||||
```sh
|
||||
bun --hot ./index.ts
|
||||
```
|
||||
|
||||
For more information, read the Bun API docs in `node_modules/bun-types/docs/**.md`.
|
||||
333
README.md
Normal file
333
README.md
Normal file
@ -0,0 +1,333 @@
|
||||
# QMD - Quick Markdown Search
|
||||
|
||||
A CLI tool for searching markdown knowledge bases using hybrid retrieval: combining BM25 full-text search, vector semantic search, and LLM re-ranking.
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ QMD Search Pipeline │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
|
||||
┌─────────────────┐
|
||||
│ User Query │
|
||||
└────────┬────────┘
|
||||
│
|
||||
┌──────────────┴──────────────┐
|
||||
▼ ▼
|
||||
┌────────────────┐ ┌────────────────┐
|
||||
│ Query Expansion│ │ Direct Query │
|
||||
│ (qwen3:0.6b) │ │ (×2 weight) │
|
||||
└───────┬────────┘ └───────┬────────┘
|
||||
│ │
|
||||
│ 1 alternative query │
|
||||
└──────────────┬──────────────┘
|
||||
│
|
||||
┌─────────────────┼─────────────────┐
|
||||
▼ ▼ ▼
|
||||
┌────────────────┐ ┌────────────────┐ ┌────────────────┐
|
||||
│ FTS Search │ │ FTS Search │ │ FTS Search │
|
||||
│ (BM25) │ │ (BM25) │ │ (BM25) │
|
||||
└───────┬────────┘ └───────┬────────┘ └───────┬────────┘
|
||||
│ │ │
|
||||
┌───────┴────────┐ ┌───────┴────────┐ ┌───────┴────────┐
|
||||
│ Vector Search │ │ Vector Search │ │ Vector Search │
|
||||
│(embeddinggemma)│ │(embeddinggemma)│ │(embeddinggemma)│
|
||||
└───────┬────────┘ └───────┬────────┘ └───────┬────────┘
|
||||
│ │ │
|
||||
└──────────────────┼──────────────────┘
|
||||
│
|
||||
▼
|
||||
┌───────────────────────┐
|
||||
│ RRF Fusion + Bonus │
|
||||
│ (Top-rank preserved) │
|
||||
│ Top 30 Kept │
|
||||
└───────────┬───────────┘
|
||||
│
|
||||
▼
|
||||
┌───────────────────────┐
|
||||
│ LLM Re-ranking │
|
||||
│ (qwen3-reranker) │
|
||||
│ Yes/No + logprobs │
|
||||
└───────────┬───────────┘
|
||||
│
|
||||
▼
|
||||
┌───────────────────────┐
|
||||
│ Position-Aware Blend │
|
||||
│ (RRF + Reranker) │
|
||||
└───────────────────────┘
|
||||
```
|
||||
|
||||
## Score Normalization & Fusion
|
||||
|
||||
### Search Backends
|
||||
|
||||
| Backend | Raw Score | Conversion | Range |
|
||||
|---------|-----------|------------|-------|
|
||||
| **FTS (BM25)** | SQLite FTS5 BM25 | `Math.abs(score)` | 0 to ~25+ |
|
||||
| **Vector** | Cosine distance | `1 / (1 + distance)` | 0.0 to 1.0 |
|
||||
| **Reranker** | LLM 0-10 rating | `score / 10` | 0.0 to 1.0 |
|
||||
|
||||
### Fusion Strategy
|
||||
|
||||
The `query` command uses **Reciprocal Rank Fusion (RRF)** with position-aware blending:
|
||||
|
||||
1. **Query Expansion**: Original query (×2 for weighting) + 1 LLM variation
|
||||
2. **Parallel Retrieval**: Each query searches both FTS and vector indexes
|
||||
3. **RRF Fusion**: Combine all result lists using `score = Σ(1/(k+rank+1))` where k=60
|
||||
4. **Top-Rank Bonus**: Documents ranking #1 in any list get +0.05, #2-3 get +0.02
|
||||
5. **Top-K Selection**: Take top 30 candidates for reranking
|
||||
6. **Re-ranking**: LLM scores each document (yes/no with logprobs confidence)
|
||||
7. **Position-Aware Blending**:
|
||||
- RRF rank 1-3: 75% retrieval, 25% reranker (preserves exact matches)
|
||||
- RRF rank 4-10: 60% retrieval, 40% reranker
|
||||
- RRF rank 11+: 40% retrieval, 60% reranker (trust reranker more)
|
||||
|
||||
**Why this approach**: Pure RRF can dilute exact matches when expanded queries don't match. The top-rank bonus preserves documents that score #1 for the original query. Position-aware blending prevents the reranker from destroying high-confidence retrieval results.
|
||||
|
||||
### Score Interpretation
|
||||
|
||||
| Score | Meaning |
|
||||
|-------|---------|
|
||||
| 0.8 - 1.0 | Highly relevant |
|
||||
| 0.5 - 0.8 | Moderately relevant |
|
||||
| 0.2 - 0.5 | Somewhat relevant |
|
||||
| 0.0 - 0.2 | Low relevance |
|
||||
|
||||
## Requirements
|
||||
|
||||
### System Requirements
|
||||
|
||||
- **Bun** >= 1.0.0
|
||||
- **macOS**: Homebrew SQLite (for extension support)
|
||||
```sh
|
||||
brew install sqlite
|
||||
```
|
||||
- **Ollama** running locally (default: `http://localhost:11434`)
|
||||
|
||||
### Ollama Models
|
||||
|
||||
QMD uses three models (auto-pulled if missing):
|
||||
|
||||
| Model | Purpose | Size |
|
||||
|-------|---------|------|
|
||||
| `embeddinggemma` | Vector embeddings | ~1.6GB |
|
||||
| `ExpedientFalcon/qwen3-reranker:0.6b-q8_0` | Re-ranking (trained) | ~640MB |
|
||||
| `qwen3:0.6b` | Query expansion | ~400MB |
|
||||
|
||||
```sh
|
||||
# Pre-pull models (optional)
|
||||
ollama pull embeddinggemma
|
||||
ollama pull ExpedientFalcon/qwen3-reranker:0.6b-q8_0
|
||||
ollama pull qwen3:0.6b
|
||||
```
|
||||
|
||||
## Installation
|
||||
|
||||
```sh
|
||||
bun install
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
### Index Markdown Files
|
||||
|
||||
```sh
|
||||
# Index all .md files in current directory
|
||||
qmd index
|
||||
|
||||
# Index with custom glob pattern
|
||||
qmd index "**/*.md"
|
||||
|
||||
# Index specific directory
|
||||
qmd index "docs/**/*.md"
|
||||
```
|
||||
|
||||
### Generate Vector Embeddings
|
||||
|
||||
```sh
|
||||
# Embed all indexed documents
|
||||
qmd embed
|
||||
```
|
||||
|
||||
### Search Commands
|
||||
|
||||
```
|
||||
┌──────────────────────────────────────────────────────────────────┐
|
||||
│ Search Modes │
|
||||
├──────────┬───────────────────────────────────────────────────────┤
|
||||
│ search │ BM25 full-text search only │
|
||||
│ vsearch │ Vector semantic search only │
|
||||
│ query │ Hybrid: FTS + Vector + Query Expansion + Re-ranking │
|
||||
└──────────┴───────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
```sh
|
||||
# Full-text search (fast, keyword-based)
|
||||
qmd search "authentication flow"
|
||||
|
||||
# Vector search (semantic similarity)
|
||||
qmd vsearch "how to login"
|
||||
|
||||
# Hybrid search with re-ranking (best quality)
|
||||
qmd query "user authentication"
|
||||
```
|
||||
|
||||
### Options
|
||||
|
||||
```sh
|
||||
-n <num> # Number of results (default: 5)
|
||||
--min-score <num> # Minimum score threshold (default: 0)
|
||||
--full # Show full document content
|
||||
-csv # CSV output (for piping/scripting)
|
||||
-md # Output as markdown
|
||||
-xml # Output as XML
|
||||
--index <name> # Use named index
|
||||
```
|
||||
|
||||
### Output Format
|
||||
|
||||
Default output is colorized CLI format (respects `NO_COLOR` env):
|
||||
|
||||
```
|
||||
93% docs/guide.md:42
|
||||
│ This section covers the **craftsmanship** of building
|
||||
│ quality software with attention to detail.
|
||||
│ See also: engineering principles
|
||||
|
||||
67% notes/meeting.md:15
|
||||
│ Discussion about code quality and craftsmanship
|
||||
│ in the development process.
|
||||
```
|
||||
|
||||
- **Score**: Color-coded (green >70%, yellow >40%, dim otherwise)
|
||||
- **Path**: Shortened relative to current directory
|
||||
- **Line**: Line number where match was found (omitted for vector-only results)
|
||||
- **Snippet**: Context around match with query terms highlighted
|
||||
|
||||
### Examples
|
||||
|
||||
```sh
|
||||
# Get 10 results with minimum score 0.3
|
||||
qmd query -n 10 --min-score 0.3 "API design patterns"
|
||||
|
||||
# Output as markdown for LLM context
|
||||
qmd search -md --full "error handling"
|
||||
|
||||
# Use separate index for different knowledge base
|
||||
qmd --index work search "quarterly reports"
|
||||
```
|
||||
|
||||
### Manage Collections
|
||||
|
||||
```sh
|
||||
# List all indexed collections
|
||||
qmd list
|
||||
|
||||
# Show database statistics
|
||||
qmd stats
|
||||
|
||||
# Forget a collection
|
||||
qmd forget
|
||||
```
|
||||
|
||||
## Data Storage
|
||||
|
||||
Index stored in: `~/.cache/qmd/index.sqlite`
|
||||
|
||||
### Schema
|
||||
|
||||
```sql
|
||||
collections -- Indexed directories and glob patterns
|
||||
documents -- Markdown content with metadata
|
||||
documents_fts -- FTS5 full-text index
|
||||
content_vectors -- Embedding cache (by content hash)
|
||||
vectors_vec -- sqlite-vec vector index
|
||||
```
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Variable | Default | Description |
|
||||
|----------|---------|-------------|
|
||||
| `OLLAMA_URL` | `http://localhost:11434` | Ollama API endpoint |
|
||||
| `XDG_CACHE_HOME` | `~/.cache` | Cache directory location |
|
||||
|
||||
## How It Works
|
||||
|
||||
### Indexing Flow
|
||||
|
||||
```
|
||||
Markdown Files ──► Parse Title ──► Hash Content ──► Store in SQLite
|
||||
│ │
|
||||
└─► FTS5 Index ◄─────────────────────┘
|
||||
```
|
||||
|
||||
### Embedding Flow
|
||||
|
||||
```
|
||||
Document ──► Format for EmbeddingGemma ──► Ollama API ──► Store Vector
|
||||
"title: X | text: Y" /api/embed
|
||||
```
|
||||
|
||||
### Query Flow (Hybrid)
|
||||
|
||||
```
|
||||
Query ──► Expand (3 variations) ──► FTS + Vector (per variation)
|
||||
│
|
||||
▼
|
||||
Merge (max score)
|
||||
│
|
||||
▼
|
||||
Top 25 candidates
|
||||
│
|
||||
▼
|
||||
LLM Re-rank (0-10)
|
||||
│
|
||||
▼
|
||||
Final ranked results
|
||||
```
|
||||
|
||||
## Model Configuration
|
||||
|
||||
Models are configured as constants in `qmd.ts`:
|
||||
|
||||
```typescript
|
||||
const DEFAULT_EMBED_MODEL = "embeddinggemma";
|
||||
const DEFAULT_RERANK_MODEL = "ExpedientFalcon/qwen3-reranker:0.6b-q8_0";
|
||||
const DEFAULT_QUERY_MODEL = "qwen3:0.6b";
|
||||
```
|
||||
|
||||
### EmbeddingGemma Prompt Format
|
||||
|
||||
```
|
||||
// For queries
|
||||
"task: search result | query: {query}"
|
||||
|
||||
// For documents
|
||||
"title: {title} | text: {content}"
|
||||
```
|
||||
|
||||
### Qwen3-Reranker
|
||||
|
||||
A dedicated reranker model trained on relevance classification:
|
||||
|
||||
```
|
||||
System: Judge whether the Document meets the requirements based on the Query
|
||||
and the Instruct provided. Note that the answer can only be "yes" or "no".
|
||||
|
||||
User: <Instruct>: Given a search query, determine if the document is relevant...
|
||||
<Query>: {query}
|
||||
<Document>: {doc}
|
||||
```
|
||||
|
||||
- Uses `logprobs: true` to extract token probabilities
|
||||
- Outputs yes/no with confidence score (0.0 - 1.0)
|
||||
- `num_predict: 1` - Only need the yes/no token
|
||||
|
||||
### Qwen3 (Query Expansion)
|
||||
|
||||
- `num_predict: 150` - For generating query variations
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
47
bun.lock
Normal file
47
bun.lock
Normal file
@ -0,0 +1,47 @@
|
||||
{
|
||||
"lockfileVersion": 1,
|
||||
"configVersion": 1,
|
||||
"workspaces": {
|
||||
"": {
|
||||
"name": "2025-12-07-bm25-q",
|
||||
"dependencies": {
|
||||
"sqlite-vec": "^0.1.7-alpha.2",
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/bun": "latest",
|
||||
},
|
||||
"optionalDependencies": {
|
||||
"sqlite-vec-darwin-arm64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-darwin-x64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-linux-x64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-win32-x64": "^0.1.7-alpha.2",
|
||||
},
|
||||
"peerDependencies": {
|
||||
"typescript": "^5",
|
||||
},
|
||||
},
|
||||
},
|
||||
"packages": {
|
||||
"@types/bun": ["@types/bun@1.3.3", "", { "dependencies": { "bun-types": "1.3.3" } }, "sha512-ogrKbJ2X5N0kWLLFKeytG0eHDleBYtngtlbu9cyBKFtNL3cnpDZkNdQj8flVf6WTZUX5ulI9AY1oa7ljhSrp+g=="],
|
||||
|
||||
"@types/node": ["@types/node@24.10.1", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GNWcUTRBgIRJD5zj+Tq0fKOJ5XZajIiBroOF0yvj2bSU1WvNdYS/dn9UxwsujGW4JX06dnHyjV2y9rRaybH0iQ=="],
|
||||
|
||||
"bun-types": ["bun-types@1.3.3", "", { "dependencies": { "@types/node": "*" } }, "sha512-z3Xwlg7j2l9JY27x5Qn3Wlyos8YAp0kKRlrePAOjgjMGS5IG6E7Jnlx736vH9UVI4wUICwwhC9anYL++XeOgTQ=="],
|
||||
|
||||
"sqlite-vec": ["sqlite-vec@0.1.7-alpha.2", "", { "optionalDependencies": { "sqlite-vec-darwin-arm64": "0.1.7-alpha.2", "sqlite-vec-darwin-x64": "0.1.7-alpha.2", "sqlite-vec-linux-arm64": "0.1.7-alpha.2", "sqlite-vec-linux-x64": "0.1.7-alpha.2", "sqlite-vec-windows-x64": "0.1.7-alpha.2" } }, "sha512-rNgRCv+4V4Ed3yc33Qr+nNmjhtrMnnHzXfLVPeGb28Dx5mmDL3Ngw/Wk8vhCGjj76+oC6gnkmMG8y73BZWGBwQ=="],
|
||||
|
||||
"sqlite-vec-darwin-arm64": ["sqlite-vec-darwin-arm64@0.1.7-alpha.2", "", { "os": "darwin", "cpu": "arm64" }, "sha512-raIATOqFYkeCHhb/t3r7W7Cf2lVYdf4J3ogJ6GFc8PQEgHCPEsi+bYnm2JT84MzLfTlSTIdxr4/NKv+zF7oLPw=="],
|
||||
|
||||
"sqlite-vec-darwin-x64": ["sqlite-vec-darwin-x64@0.1.7-alpha.2", "", { "os": "darwin", "cpu": "x64" }, "sha512-jeZEELsQjjRsVojsvU5iKxOvkaVuE+JYC8Y4Ma8U45aAERrDYmqZoHvgSG7cg1PXL3bMlumFTAmHynf1y4pOzA=="],
|
||||
|
||||
"sqlite-vec-linux-arm64": ["sqlite-vec-linux-arm64@0.1.7-alpha.2", "", { "os": "linux", "cpu": "arm64" }, "sha512-6Spj4Nfi7tG13jsUG+W7jnT0bCTWbyPImu2M8nWp20fNrd1SZ4g3CSlDAK8GBdavX7wRlbBHCZ+BDa++rbDewA=="],
|
||||
|
||||
"sqlite-vec-linux-x64": ["sqlite-vec-linux-x64@0.1.7-alpha.2", "", { "os": "linux", "cpu": "x64" }, "sha512-IcgrbHaDccTVhXDf8Orwdc2+hgDLAFORl6OBUhcvlmwswwBP1hqBTSEhovClG4NItwTOBNgpwOoQ7Qp3VDPWLg=="],
|
||||
|
||||
"sqlite-vec-windows-x64": ["sqlite-vec-windows-x64@0.1.7-alpha.2", "", { "os": "win32", "cpu": "x64" }, "sha512-TRP6hTjAcwvQ6xpCZvjP00pdlda8J38ArFy1lMYhtQWXiIBmWnhMaMbq4kaeCYwvTTddfidatRS+TJrwIKB/oQ=="],
|
||||
|
||||
"typescript": ["typescript@5.9.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw=="],
|
||||
|
||||
"undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
|
||||
}
|
||||
}
|
||||
47
package.json
Normal file
47
package.json
Normal file
@ -0,0 +1,47 @@
|
||||
{
|
||||
"name": "qmd",
|
||||
"version": "1.0.0",
|
||||
"description": "Quick Markdown Search - Full-text and vector search for markdown files",
|
||||
"type": "module",
|
||||
"bin": {
|
||||
"qmd": "./qmd"
|
||||
},
|
||||
"scripts": {
|
||||
"qmd": "bun qmd.ts",
|
||||
"index": "bun qmd.ts index",
|
||||
"vector": "bun qmd.ts vector",
|
||||
"search": "bun qmd.ts search",
|
||||
"vsearch": "bun qmd.ts vsearch",
|
||||
"rerank": "bun qmd.ts rerank",
|
||||
"link": "bun link"
|
||||
},
|
||||
"dependencies": {
|
||||
"sqlite-vec": "^0.1.7-alpha.2"
|
||||
},
|
||||
"optionalDependencies": {
|
||||
"sqlite-vec-darwin-arm64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-darwin-x64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-linux-x64": "^0.1.7-alpha.2",
|
||||
"sqlite-vec-win32-x64": "^0.1.7-alpha.2"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/bun": "latest"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"typescript": "^5"
|
||||
},
|
||||
"engines": {
|
||||
"bun": ">=1.0.0"
|
||||
},
|
||||
"keywords": [
|
||||
"markdown",
|
||||
"search",
|
||||
"fts",
|
||||
"vector",
|
||||
"sqlite",
|
||||
"bm25",
|
||||
"embeddings",
|
||||
"ollama"
|
||||
],
|
||||
"license": "MIT"
|
||||
}
|
||||
14
qmd
Executable file
14
qmd
Executable file
@ -0,0 +1,14 @@
|
||||
#!/bin/bash
|
||||
# qmd - Quick Markdown Search
|
||||
# Run with: ./qmd or symlink to PATH
|
||||
|
||||
# Resolve symlinks to find actual script location
|
||||
SOURCE="${BASH_SOURCE[0]}"
|
||||
while [ -L "$SOURCE" ]; do
|
||||
DIR="$(cd -P "$(dirname "$SOURCE")" && pwd)"
|
||||
SOURCE="$(readlink "$SOURCE")"
|
||||
[[ $SOURCE != /* ]] && SOURCE="$DIR/$SOURCE"
|
||||
done
|
||||
SCRIPT_DIR="$(cd -P "$(dirname "$SOURCE")" && pwd)"
|
||||
|
||||
exec bun "$SCRIPT_DIR/qmd.ts" "$@"
|
||||
29
tsconfig.json
Normal file
29
tsconfig.json
Normal file
@ -0,0 +1,29 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
// Environment setup & latest features
|
||||
"lib": ["ESNext"],
|
||||
"target": "ESNext",
|
||||
"module": "Preserve",
|
||||
"moduleDetection": "force",
|
||||
"jsx": "react-jsx",
|
||||
"allowJs": true,
|
||||
|
||||
// Bundler mode
|
||||
"moduleResolution": "bundler",
|
||||
"allowImportingTsExtensions": true,
|
||||
"verbatimModuleSyntax": true,
|
||||
"noEmit": true,
|
||||
|
||||
// Best practices
|
||||
"strict": true,
|
||||
"skipLibCheck": true,
|
||||
"noFallthroughCasesInSwitch": true,
|
||||
"noUncheckedIndexedAccess": true,
|
||||
"noImplicitOverride": true,
|
||||
|
||||
// Some stricter flags (disabled by default)
|
||||
"noUnusedLocals": false,
|
||||
"noUnusedParameters": false,
|
||||
"noPropertyAccessFromIndexSignature": false
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user