The article also provides a quick start guide using the OpenAI API as an example. Users can create an API agent with their API key, model, and APIs, and then use the agent to execute commands. The article also explains how to use the agent via the API, including running the server, making an API call, and configuring the server/pages/api/api2ai.config.ts file to add your own APIs. The tool supports OpenAPI Spec version 3.0.0 and above and various auth schemes including Bearer authentication, API keys, and Basic auth. The article concludes with instructions for development and contributing, including running the server, accessing the app, and running tests.
Key takeaways:
- api2ai is a tool that allows you to create an API assistant from any OpenAPI Spec, interfacing with any API using plain English or any natural language.
- The tool automatically parses OpenAPI spec and auth schemes, selects endpoint and parses arguments provided in user prompt into query and body params, and invokes the API call and return the response.
- It can be installed using npm or yarn, and comes with a local API. The tool can be used via the API by running the server in your machine and making an API call.
- api2ai supports various auth schemes including Bearer authentication, API keys, and Basic auth. It currently supports OpenAPI Spec version 3.0.0 and above.