# Ensemble AI API Docs

## Ensemble AI

- [Welcome to Ensemble!](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/welcome-to-ensemble.md): The only API that offers a complete end-to-end machine learning pipeline with unlimited user customization.
- [Dark Matter](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter.md): Ensemble AI's Core IP algorithm for generating highly predictive embeddings for any machine learning dataset.
- [DarkMatterType](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/darkmattertype.md): Any of \[ numpy.ndarray | pandas.DataFrame | torch.Tensor ]
- [Fit](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/fit.md): Fit an instance of the Dark Matter algorithm.
- [Generate](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/generate.md): Transforms input into embeddings.
- [Save](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/save.md): Saves the algorithm weights for future use.
- [Load](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/load.md): Loads a previous trained Dark Matter algorithm from file.
- [Integrations](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations.md)
- [On Premise API](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api.md): We never see your data.
- [Ensemble Core 1.0](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0.md): A python package for Feature Enhancement.
- [User](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0/user.md): A python class for handling user authentication.
- [login](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0/user/login.md): The login method checks with our server to make sure that the entered credentials match a valid Ensemble account before continuing execution.
- [Generator](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0/generator.md): A python class for generating enhanced features using Feature Enhancement.
- [fit](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0/generator/fit.md): The fit method learns to generate enhanced statistical properties from the inputs and target variables using Ensemble's proprietary Feature Enhancement algorithm.
- [generate](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/on-premise-api/ensemble-core-1.0/generator/generate.md): The generate method applies the learned weights to generate new and enhanced features.
- [Cloud API](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/cloud-api.md)
- [Web Portal](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/web-portal.md): Instructions on how to interact with the web portal to train and generate new feature embeddings using Dark Matter.
- [Fit](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/web-portal/fit.md): The Fit API allows a user to define parameters and hyper-parameters to be used during Dark Matter Training, fit an instance of the Dark Matter algorithm, and get back embeddings.
- [Generate](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/web-portal/generate.md): The Generate API allows a user to get back embeddings from a trained instance of the Dark Matter algorithm.
- [Download JSON](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/dark-matter/integrations/web-portal/download-json.md): Once training and generating jobs are complete, use the following steps to download your results for use.
- [Getting Started](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started.md): Be among the first to use Dark Matter, Ensemble's newest and unpublished algorithm.
- [Quick Start](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/quick-start.md): Start using ensemble in minutes.
- [Tutorials (coming soon!)](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/tutorials-coming-soon.md)
- [Case Studies (coming soon!)](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/case-studies-coming-soon.md)
- [Environment Setup](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/environment-setup.md): Guide on how to set up Ensemble in your preferred environment.
- [On Premise API](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/environment-setup/on-premise-api.md): Step-by-step guide on how to set up Ensemble's on premise API.
- [Cloud API (coming soon!)](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/getting-started/environment-setup/cloud-api-coming-soon.md)
- [Dark Matter](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/references/dark-matter.md): Technical Introduction of Core IP
- [Explainability Mode](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/references/explainability-mode.md): Explainability Mode is a feature of the Dark Matter algorithm available for enterprise accounts.
- [Ray for Dark Matter](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/references/ray-for-dark-matter.md): Dark Matter leverages Ray to distribute algorithm training for scaling and optimizing training time.
- [The Dark Matter Environment](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/references/the-dark-matter-environment.md): Dark Matter leverages several common third party Python libraries used for Data Science tasks.
- [Feature Enhancement White Paper](https://ensemble-ai.gitbook.io/ensemble-ai-api-docs/references/feature-enhancement-white-paper.md): GitHub repo link to white paper pdf.