Skip to main content

Getting Started

Hello! πŸ™‚ Welcome to aiXplain, your friendly AI development and deployment platform. We offer a broad marketplace of standardized AI models, and provide tools to help you create custom AI solutions. You can interface with aiXplain in three ways:πŸ₯‡SDK, πŸ₯ˆBel Esprit, and πŸ₯‰Studio.

What is aiXplain?​

aiXplain is a platform that aims to simplify AI resources, bringing together models, datasets (soon) and metrics from both academic and commercial sources. They can be selected, combined, deployed and evaluated through different tools, and all managed using a Teams-based pay-as-you go Credits system.

Discover aiXplain's ready-to-use AI Models and Metrics.

Design and deploy custom Pipelines.

Benchmark models using Data and metrics.

FineTune pre-trained models using your data.

SDK​

The aiXplain SDK is an open-source toolkit (Python, Swift). It enables you to access aiXplain's assets and tools in a standardized format. See below for the available features.

Get started with Python, Swift, or API Requests.

SDK Architecture​

Docusaurus themed imageDocusaurus themed image

Studio​

The aiXplain Studio provides a user interface to interact with aiXplain. It provides an easy way to

  1. Manage your aiXplain Teams and Credits
  2. Search and Try out our models in Discover
  3. Prototype pipelines in Design
  4. Access FineTune and Benchmark (including Bechmark reports)

See the Studio tour to learn more!

Bel Esprit​

Bel Esprit is a Generative AI chat agent designed to simplify AI solution creation through natural language instructions. It selects AI models from aiXplain's marketplace, integrates them into deployable solutions, and offers user-friendly explanations. Bel Esprit connects users to AI specialists when further customization is needed.

info

Bel Esprit is currently integrated into Studio but will soon be available as a standalone application.

See our page on Bel Esprit to learn more!

Features Comparison​

PlatformSDK (Python)SDK (Swift)Notes
Run models, pipelines & metrics with single inputβœ…βœ…βœ…
Run models, pipelines & metrics in batch modeβŒβœ…βœ…
Run models, pipelines & metrics on datasetsβŒβœ…βŒ
Search assetsβœ…βœ…βŒSearch parameters differ between Studio and SDK
Build pipelinesβœ…βŒβŒComing soon to the Python SDK
Onboard models (custom & Hugging Face)βŒβœ…βŒ
Onboard datasetsβœ…βœ…βŒ
Benchmarkβœ…βœ…βŒ
FineTuneβœ…βœ…βŒ
AutoMode❌❌❌Currently disabled
Build agents❌❌❌Coming soon! ✨

Feedback​

πŸ˜ŠπŸ˜‘β˜ΉοΈFeedback

Please share your feedback to help us improve! πŸ™
The feedback button is at the bottom right of the Platform. Alternatively, message us on Discord.

Examples

  • Bug report: [This] models don't work!
  • Feature request: Please enable [this] use case.
  • Improvement suggestion: Please make [this] easier to do.
  • Technical support: I'm stuck trying to do [this]! Help!
Docusaurus themed imageDocusaurus themed image

Requirements​

To get started with aiXplain, follow the requirements below, then continue to a Quickstart. 😊

  1. To explore aiXplain's assets and build pipelines, you need to Create an account.

  2. To run models and pipelines, or create Benchmarks or FineTunes, you also need to Add credits.
    You gain 5 free expirable credits upon joining aiXplain.

  3. To deploy your solution or create Benchmarks or FineTunes via the SDK, you also need to Generate an API Key.