OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Gateway — adaline

Gateway — adaline is a TypeScript SDK that gives applications a common interface for calling language models through provider integrations. It supports chat and embedding requests and is designed to run within an application’s own environment rather than as a hosted proxy.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gateway — adaline — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when building a TypeScript application that needs chat or embedding calls through one SDK interface and you want the integration to run within the application environment.

Who it is for

  • TypeScript developers integrating language models into applications.
  • Teams seeking a shared model-calling interface across multiple providers.
  • Developers connecting model requests to application infrastructure through features such as callbacks or OpenTelemetry.

Documented uses

  • Call chat models through a consistent application interface.
  • Stream chat responses or request a complete response.
  • Generate embeddings from text using a supported embedding provider.
  • Add provider-specific integrations or custom providers to an application.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. The README documents npm installation.

  • The gateway is an SDK integrated into an application, not a hosted model endpoint.
  • Provider packages are installed separately as needed.
  • Provider capabilities differ: the README lists chat and embedding support separately for each provider.
  • Provider credentials are configured as part of model setup; the OpenAI example uses an API key.
  • The repository is written in TypeScript and documents typed interfaces.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a TypeScript chat call with OpenAI

Install the documented packages and prepare an OpenAI chat model for use through Gateway.

Before you start

  • A TypeScript application using npm.
  • An OpenAI API key.

Steps

  1. Install @adaline/gateway and @adaline/types.

  2. Install the optional @adaline/openai provider package.

  3. Import Gateway, OpenAI, and the relevant types; create a Gateway instance and an OpenAI instance.

  4. Define a chat model with a model name and API key, then prepare the request configuration and messages as shown in the README.

Expected outcome

A configured Gateway instance, OpenAI chat model, request configuration and messages, ready for the documented chat invocation.

Guide limitations

  • This guide covers setup only; the README’s invocation examples are not included as a completed run here.
  • The example’s model name and configuration are specific to its OpenAI quickstart.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
adaline/gateway · Official homepage title · retained in its source language
How we review sourcesSuggest a correction