http4k-connect 188.8.131.52 released with OpenAI API support
Team http4k is excited to have just released v184.108.40.206 of http4k-connect, which has initial support for the OpenAI API. You can use this http4k-compatible API from your Kotlin programs to generate answers to GPT prompts, create embeddings, or generating images from text prompts. The included FakeOpenAI server will also allow you to test your OpenAI integrations without using up those valuable tokens, and is also testable entirely in-memory for super fast test-cycles. Just plug in your OpenAI API key and get coding!
is a set of lightweight (zero-reflection) API libraries for connecting to popular third-party cloud services using http4k clients, along with Fake implementations for usage during local testing. It is based around the Connect pattern
, which allows you to express client-side adapters in modular and composable way.
These adapter libraries are all underpinned by a variation on the uniform Server as a Function (SaaF) model powered by the ubiquitous HttpHandler interface, so you can:
a. Take advantage of the simple and powerful SaaF model and APIs used in http4k to plug everything together completely in-memory for testing.
b. Have access to the underlying HTTP clients (and hence add metrics, logging or other crosscutting concerns).
c. Run stateful Fake implementations of 3rd party systems locally or in test environments
Although focussed around usage in http4k-based projects, http4k-connect does not require this and the libraries are usable from any JVM-based application.
http4k-connect v220.127.116.11 is available from Maven Central right now.