How to Use an LLM-Powered Boilerplate for Building Your Own Node.js API

For a very long time, one of many frequent methods to start out new Node.js initiatives was utilizing boilerplate templates. These templates assist builders reuse acquainted code buildings and implement customary options, resembling entry to cloud file storage. With the newest developments in LLM, challenge boilerplates seem like extra helpful than ever.

Constructing on this progress, I’ve prolonged my present Node.js API boilerplate with a brand new device LLM Codegen. This standalone characteristic permits the boilerplate to mechanically generate module code for any goal primarily based on textual content descriptions. The generated module comes full with E2E checks, database migrations, seed information, and crucial enterprise logic.

Historical past

I initially created a GitHub repository for a Node.js API boilerplate to consolidate the very best practices I’ve developed through the years. A lot of the implementation relies on code from an actual Node.js API operating in manufacturing on AWS.

I’m keen about vertical slicing structure and Clear Code rules to maintain the codebase maintainable and clear. With latest developments in LLM, significantly its help for big contexts and its means to generate high-quality code, I made a decision to experiment with producing clear TypeScript code primarily based on my boilerplate. This boilerplate follows particular buildings and patterns that I consider are of top of the range. The important thing query was whether or not the generated code would observe the identical patterns and construction. Primarily based on my findings, it does.

To recap, right here’s a fast spotlight of the Node.js API boilerplate’s key options:

• Vertical slicing structure primarily based on DDD & MVC rules
• Providers enter validation utilizing ZOD
• Decoupling utility parts with dependency injection (InversifyJS)
• Integration and E2E testing with Supertest
• Multi-service setup utilizing Dockercompose

Over the previous month, I’ve spent my weekends formalizing the answer and implementing the required code-generation logic. Under, I’ll share the main points.

Implementation Overview

Let’s discover the specifics of the implementation. All Code Generation logic is organized on the challenge root degree, contained in the llm-codegen folder, guaranteeing straightforward navigation. The Node.js boilerplate code has no dependency on llm-codegen, so it may be used as an everyday template with out modification.

It covers the next use circumstances:

• Producing clear, well-structured code for brand spanking new module primarily based on enter description. The generated module turns into a part of the Node.js REST API utility.
• Creating database migrations and increasing seed scripts with primary information for the brand new module.
• Producing and fixing E2E checks for the brand new code and guaranteeing all checks move.

The generated code after the primary stage is clear and adheres to vertical slicing structure rules. It consists of solely the required enterprise logic for CRUD operations. In comparison with different code era approaches, it produces clear, maintainable, and compilable code with legitimate E2E checks.

The second use case includes producing DB migration with the suitable schema and updating the seed script with the required information. This job is especially well-suited for LLM, which handles it exceptionally nicely.

The ultimate use case is producing E2E checks, which assist verify that the generated code works accurately. Through the operating of E2E checks, an SQLite3 database is used for migrations and seeds.

Primarily supported LLM shoppers are OpenAI and Claude.

How you can Use It

To get began, navigate to the basis folder llm-codegen and set up all dependencies by operating:

npm i

llm-codegen doesn’t depend on Docker or every other heavy third-party dependencies, making setup and execution straightforward and easy. Earlier than operating the device, make sure that you set at the least one *_API_KEY setting variable within the .env file with the suitable API key on your chosen LLM supplier. All supported setting variables are listed within the .env.pattern file (OPENAI_API_KEY, CLAUDE_API_KEY and many others.) You need to use OpenAI, Anthropic Claude, or OpenRouter LLaMA. As of mid-December, OpenRouter LLaMA is surprisingly free to make use of. It’s doable to register here and acquire a token at no cost utilization. Nevertheless, the output high quality of this free LLaMA mannequin could possibly be improved, as a lot of the generated code fails to move the compilation stage.

To start out llm-codegen, run the next command:

npm run begin

Subsequent, you’ll be requested to enter the module description and title. Within the module description, you’ll be able to specify all crucial necessities, resembling entity attributes and required operations. The core remaining work is carried out by micro-agents: Developer, Troubleshooter, and TestsFixer.

Right here is an instance of a profitable code era:

Under is one other instance demonstrating how a compilation error was fastened:

The next is an instance of a generated orders module code:

A key element is which you could generate code step-by-step, beginning with one module and including others till all required APIs are full. This method lets you generate code for all required modules in only a few command runs.

How It Works

As talked about earlier, all work is carried out by these micro-agents: Developer, Troubleshooter and TestsFixer, managed by the Orchestrator. They run within the listed order, with the Developer producing a lot of the codebase. After every code era step, a test is carried out for lacking information primarily based on their roles (e.g., routes, controllers, providers). If any information are lacking, a brand new code era try is made, together with directions within the immediate in regards to the lacking information and examples for every function. As soon as the Developer completes its work, TypeScript compilation begins. If any errors are discovered, the Troubleshooter takes over, passing the errors to the immediate and ready for the corrected code. Lastly, when the compilation succeeds, E2E checks are run. Each time a take a look at fails, the TestsFixer steps in with particular immediate directions, guaranteeing all checks move and the code stays clear.

All micro-agents are derived from the BaseAgent class and actively reuse its base technique implementations. Right here is the Developer implementation for reference:

Every agent makes use of its particular immediate. Take a look at this GitHub link for the immediate utilized by the Developer.

After dedicating important effort to analysis and testing, I refined the prompts for all micro-agents, leading to clear, well-structured code with only a few points.

Through the improvement and testing, it was used with numerous module descriptions, starting from easy to extremely detailed. Listed below are just a few examples:

- The module chargeable for library guide administration should deal with endpoints for CRUD operations on books.
- The module chargeable for the orders administration. It should present CRUD operations for dealing with buyer orders. Customers can create new orders, learn order particulars, replace order statuses or data, and delete orders which are canceled or accomplished. Order will need to have subsequent attributes: title, standing, positioned supply, description, picture url
- Asset Administration System with an "Property" module providing CRUD operations for firm belongings. Customers can add new belongings to the stock, learn asset particulars, replace data resembling upkeep schedules or asset areas, and delete information of disposed or bought belongings.

Testing with gpt-4o-mini and claude-3-5-sonnet-20241022 confirmed comparable output code high quality, though Sonnet is dearer. Claude Haiku (claude-3–5-haiku-20241022), whereas cheaper and comparable in value to gpt-4o-mini, usually produces non-compilable code. Total, with gpt-4o-mini, a single code era session consumes a mean of round 11k enter tokens and 15k output tokens. This quantities to a price of roughly 2 cents per session, primarily based on token pricing of 15 cents per 1M enter tokens and 60 cents per 1M output tokens (as of December 2024).

Under are Anthropic utilization logs exhibiting token consumption:

Primarily based on my experimentation over the previous few weeks, I conclude that whereas there should still be some points with passing generated checks, 95% of the time generated code is compilable and runnable.

I hope you discovered some inspiration right here and that it serves as a place to begin on your subsequent Node.js API or an improve to your present challenge. Ought to you’ve options for enhancements, be happy to contribute by submitting PR for code or immediate updates.

In case you loved this text, be happy to clap or share your ideas within the feedback, whether or not concepts or questions. Thanks for studying, and joyful experimenting!

UPDATE [February 9, 2025]: The LLM-Codegen GitHub repository was up to date with DeepSeek API help. It’s cheaper than gpt-4o-mini and affords practically the identical output high quality, but it surely has an extended response time and generally struggles with API request errors.

Except in any other case famous, all pictures are by the creator