An open and advanced enterprise Generative AI platform for organizations
Enterprise Generative AI
Amplify is an open source enterprise Generative AI platform for organizations. The platform has advanced Gen AI capabilities and gives you choice in which model providers you use, from Anthropic Claude to OpenAI GPT-4 Turbo. Build your own assistants, integrate your data, and share across your organization.
Get Started
123

An advanced open source enterprise Generative AI platform.

Build assistants using your own documents and data with any of the supported large language models (LLMs), from Anthropic, OpenAI, Mistral, Meta, or Google.

  • Control over your data
  • Custom assistants similar to GPTs
  • File upload, tagging, and management
  • Cost accounting to the message level and per-user limits
  • Sharing across your organization
  • Advanced Retrieval Augmented Generation (RAG)
  • Prompt templates
  • Powerpoint and Word document creation
  • Visualizations, diagrams, markdown, and more
  • Folders, workspaces, and search
f1
f2
f1
f2
Build Amazing Custom Assistants

Easily create custom Assistants with just a few clicks.

Your assistants will automatically answer questions using your documents, customize their responses based on your guidance, and can be shared across your organization. Build expense, travel, HR, and other assistants in minutes.

  • Build assistants by uploading documents
  • Plug in your own data sources
  • Create Assistants with a conversational interface
  • Chat with multiple assistants in one conversation
Cost Effective

Pay for what you actually use rather than fixed monthly per user fees.

You deploy and run Amplify GenAI yourself in your own Amazon Web Services account. You pay for the Amazon Web Services costs and the token costs for the models you use.

Case Study: Vanderbilt University currently provides unlimited usage of the platform to 1,300 pilot users. In April of 2024, the Vanderbilt cost per user was around $3/mo, including Amazon Web Services costs. The largest part of the bill was not token costs. The largest token cost was GPT-4 Turbo usage. For some organizations, per user pricing may be more cost effective. For Vanderbilt, paying for actual usage was far more cost effective. 50% of Vanderbilt users consumed less than $1/mo in token costs.

Get Started
f1
Help Your Organization Innovate

Pair Amplify with Generative AI training.

Over 300,000 people have learned to innovate with Generative AI using the courses that we have selected. Although some of the classes may have ChatGPT or OpenAI in the title, the fundamental concepts, particularly Prompt Engineering, will translate across most LLMs. Look for updated versions of these courses with Amplify GenAI soon.

f1
f2
About Us
The People Behind Amplify GenAI
"Dr. Jules White is Senior Advisor to the Chancellor on Generative AI in Enterprise and Professor of Computer Science in the Dept. of Computer Science at Vanderbilt University. He created one of the first online classes for Prompt Engineering, which is the study of how you converse with AI effectively, which has had over ~250,000 enroll."
Jules White
Founding co-Director of Amplify GenAI
"Allen is the Principal Cloud Architect for Vanderbilt University IT. He is a leader in understanding the intersection of Generative AI, cloud architecture, RAG, and assistants. He has decades of experience in running large-scale enterprise software systems."
Allen Karns
Founding co-Director of Amplify GenAI
"Max is a Generative AI Research Engineer who completed a Bachelor's of Science in Computer Science from Vanderbilt University in May 2023. His background in software development and IT infrastructure underpins his deep passion for generative AI. Max is committed to advancing research and expanding the practical applications of generative AI technologies."
Maximillian Moundas
Amplify GenAI Engineer
"Karely is a Generative AI Engineer and a graduate of Vanderbilt University, where she earned her Master's in Computer Science. She actively engages with cross-disciplinary teams, employing her skills to innovate and refine solutions within the realms of software development and prompt engineering."
Karely Rodriguez
Amplify GenAI Engineer
"ChatBot-UI provided the original user interface that we started with. We built on this base to add SSO, enterprise accounting, advanced assistant features, and many other things. Their work helped spawn many great projects like this one. We recommending checking out their work at: https://github.com/mckaywrigley/chatbot-ui"
ChatBot-UI
The Original UI

Our Mission:

We want to help make enterprise Gen AI more open, cost-effective, and accessible.

Our Goals:

  • Provide the most advanced Generative AI capabilities
  • Support low-cost options and usage-based pricing to increase accessibility
  • Allow choice in model providers so that you can always pick the best models for your needs and avoid vendor lock-in
  • Make it easy to innovate in every discipline without having to know how to code
  • Allow you to control security and privacy
  • Build a community around an open platform
  • Support integration of your data, but in a way that you have full visibility and control over
  • Give you the tools to control security and privacy

If you are an organization deploying Amplify GenAI, we want you to have a voice in the direction of the platform. Please reach out to learn more about how you can help contribute to the vision and direction of Amplify GenAI.

Have any questions?

Frequently Asked Questions

What does this cost?

The platform is MIT-licensed. In order to run it, you will need to pay for Amazon Web Services costs. In addition, you will need to pay for usage of models from Anthropic, OpenAI, Meta, Google, etc.

Is my data private?

You run the platform in your own Amazon Web Services account. Your agreement with Amazon Web Services and your agreements with the model providers determine the privacy of your data. Most organizations can sign an enterprise agreement with a provider to obtain data privacy guarantees, including not training on your data.

Can I contribute?

Yes! We are happy to review and accept pull requests. In addition, you can reach out to us using the Contact Us button.

How do I deploy it?

You will need an Amazon Web Services account and experience deploying applications using Terraform and the Serverless Framework. We try to help with general or architectural questions if you Contact Us.

Who built this?

Jules White, Allen Karns, Karely Rodriguez, and Max Moundas at Vanderbilt University build and maintain the platform. The user interface started with the excellent MIT-licensed Chatbot-UI https://github.com/mckaywrigley/chatbot-ui. We enhanced the user interface and then built a new back-end with advanced Generative AI features and enterprise capabilities to support our needs at Vanderbilt University.

Why did you build it?

There are some great, but expensive and closed enterprise options out there. There are some fantastic non-enterprise platforms and interfaces, such as the UI we started with. However, none of the options gave us the advanced Gen AI features, enterprise security, and cost that we needed. We wanted to be able to provide the latest in Generative AI research to as many people as possible at a low cost. At Vanderbilt, we believe our approach has led to a more advanced platform at a dramatically lower cost for Vanderbilt. Currently, at Vanderbilt, our costs are ~$3/mo per user and we have access to models from the top providers. In addition, we find that our platform outperforms many or all commercial options across many tasks. There are lots of 'engines' being built (e.g., the models), but the cars around the engines have lagged behind. You can think of Amplify GenAI as the car around the engine. Amplify GenAI gives you the steering, brakes, wheels, and safety systems to use engines from many different providers. Just because you like one engine, doesn't mean you have to buy their car and only use it. Amplify GenAI gives you a choice of engine and the freedom to customize the car to your organization's needs.

Do you provide support?

We can't provide support for your deployment of Amplify GenAI, but we can help with general questions about the platform. We are happy to connect you to commercial entities that can help you set up and run the platform.

What models do you support?

We currently support models from Anthropic and Mistral via Amazon Bedrock and OpenAI via OpenAI or Microsoft Azure.

Can I run my own model locally?

We don't have this feature implemented yet, but it should be fairly easy to set up if you are already building your own models.

Who is using Amplify GenAI?

Vanderbilt University has 1,300 users in Amplify and will be releasing it enterprise-wide July, 2024.

Who steers the development and direction of the platform?

We are building several open advisory boards that will help guide the direction of the platform. If your organization is interested in participating, please Contact Us.