Building APIs in the AI Era

What if you could run a powerful AI coding assistant locally, avoiding cloud costs and privacy risks?

#1about 1 minute

The fundamental relationship between AI and APIs

AI systems rely on APIs for data and connectivity, and conversely, AI can be used to accelerate API development.

#2about 2 minutes

Using local AI models for code assistance

Running large language models locally for code assistance can reduce costs and improve data privacy compared to cloud-based services.

#3about 3 minutes

Understanding the architecture of AI-powered applications

AI applications typically consist of a user interface that communicates with a model inference server via a standardized API, like the OpenAI API.

#4about 2 minutes

Selecting open source models for code generation

Using open source models from platforms like Hugging Face, such as IBM's Granite, ensures compliance and avoids potential licensing issues.

#5about 6 minutes

Setting up a local AI development environment

Configure a local environment by running a model with InstructLab and connecting it to a VS Code extension like Continue via its OpenAI-compatible API.

#6about 2 minutes

Generating an OpenAPI specification from a prompt

Use a local AI assistant integrated into an IDE to generate a complete OpenAPI specification from a simple natural language prompt.

#7about 4 minutes

Linting and refining an AI-generated API specification

Identify and correct issues in an AI-generated OpenAPI specification by using a linter like Spectral and then prompting the AI to make specific fixes.

#8about 4 minutes

Using AI to generate custom API linting rules

Generate custom Spectral linting rules by providing a natural language prompt to the AI assistant, enforcing specific governance policies for your API.

#9about 6 minutes

Generating a Java API implementation with Quarkus

Provide the OpenAPI specification as context to an AI assistant to generate the corresponding Java backend implementation using the Quarkus framework.

#10about 2 minutes

Best practices for using AI in development

Use AI-generated code with caution as context can be limited, and leverage open source tools to experiment with these capabilities in your local environment.