Welcome! This is the official companion codebase for the book Vector Search with JavaScript. Explore each chapter branch to follow along with the book’s journey from basic search to advanced, production-ready vector search systems.
| Chapter | Branch | Description |
|---|---|---|
| 3 | chapter-3 |
Generating Vector Embeddings |
| 4 | chapter-4 |
Building the Foundation for Vector Search |
| 5 | chapter-5 |
Structuring the Backend for Vector Search |
| 6 | chapter-6 |
Building the Vector Embedding Generation Service |
| 7 | chapter-7 |
Creating a Vector Search Service |
| 8 | chapter-8 |
Creating a Vector Search Index |
| 9 | chapter-9 |
Incorporating Vector Search Functionality |
| 10 | chapter-10 |
Optimizing Search Results |
| 11 | chapter-11 |
Key Takeaways and Practical Applications |
| Main | main |
Complete App (latest) |
🧭 Tip: Checkout any branch to see the code as it appears at the end of that book chapter.
This project is a full-featured blog platform demonstrating vector search, hybrid search, and modern backend patterns using:
- Express.js for the web server
- Couchbase as the database
- Ottoman.js for ODM
- OpenAI (or compatible) for generating embeddings
- Modular, testable, and production-ready code structure
Each chapter branch is carefully aligned with the book’s content.
- Clone the repo:
git clone https://github.com/hummusonrails/vector-example-blog-platform.git cd vector-example-blog-platform - Checkout a chapter branch (optional):
git checkout chapter-7 # Or any other chapter branch - Install dependencies:
npm install
- Start the app:
npm run dev # or npm start
📚 See the book for setup details and chapter-by-chapter walkthroughs.
- Vector Embeddings: Generate and store vector representations for articles
- Vector Search: Find articles by semantic similarity
- Hybrid Search: Combine keyword and vector search
- Ranking & Optimization: Weighted ranking, stop words, recency/popularity
- Production Patterns: Modular services, error handling, and more
Pull requests, issues, and suggestions are welcome! See the CONTRIBUTING.md if available, or open an issue to get started.
This project is licensed under the MIT License - see the LICENSE file for details.
