World Congress 2024 • Aug 20, 2024 • Session details

Building APIs in the AI Era

Hugo Guerrero

Are commercial AI assistants compromising your proprietary data? Discover how to securely generate and refine APIs using local, open-source LLMs like Ollama and IBM Granite.

Pause
Mute Enter Fullscreen
#1 about 3 min

Understanding the relationship between APIs and AI

Why building and consuming APIs is fundamental to creating modern AI-powered applications.

#2 about 3 min

Benefits of running AI code assistants locally

How running models on local hardware reduces expensive subscription costs and improves data security.

#3 about 3 min

Exploring the API architecture of local inference

How external chat interfaces rely on background API requests and standardized protocols to communicate with inference engines.

#4 about 3 min

Selecting open-source LLMs for code generation

Downloading permissible open-source models like IBM Granite from Hugging Face to avoid legal compliance risks.

#5 about 4 min

Setting up a local AI coding environment

Configuring InstructLab and the Continue extension in VS Code to run a local inference server.

#6 about 4 min

Generating an OpenAPI specification with AI prompts

Using prompt engineering within the IDE to automatically generate OpenAPI YAML files for REST operations.

#7 about 5 min

Validating OpenAPI specifications with Spectral linting

Applying default Spectral rules to identify and fix missing governance properties like server URLs and contact records.

#8 about 3 min

Authoring custom Spectral rules via AI chat

Formulating prompt instructions to generate specific OpenAPI linting rules for enforcing internal organizational standards.

#9 about 6 min

Implementing a Java REST API with Quarkus

Translating an OpenAPI definition into functional Quarkus code and replacing outdated Java dependency imports interactively.

#10 about 2 min

Evaluating the risks of AI code generation

Recognizing the limitations of AI context windows to appropriately mix generated code with reliable predefined SDK tools.

Matching moments

3:14 min

Building a community-governed LAMP stack for open AI

Raffi Krikorian Raffi Krikorian · World Congress 2026 Europe

1:48 min

Exploring AI integrations in modern agile development workflows

Markus Walker Markus Walker · World Congress 2023

1:49 min

Why developers should run AI models locally

Cedric Clyburn Cedric Clyburn +1 · World Congress 2025

1:20 min

Exploring open source AI resources and learning paths

Cedric Clyburn Cedric Clyburn · World Congress 2024

1:59 min

Designing governed and AI-native API platforms

Gbadebo Bello Gbadebo Bello · Europe 2026 Virtual

5:11 min

Developing a containerized AI code assistant locally

Cedric Clyburn Cedric Clyburn +1 · World Congress 2025