Dust solves this problem by providing a user-friendly interface where you can create workflows that combine LLMs, code execution, and queries to external services. You can also use Data Sources, which are fully managed semantic search engines that you can query from your workflows. Dust supports various LLMs from providers such as OpenAI, Cohere, AI21 and more. You can switch models seamlessly and compare their outputs.
Dust also makes it easy to deploy and use your LLM apps. You can either use them directly from Dust or deploy them to an API endpoint. You can also connect your team's Notion, Google Docs or Slack to managed DataSources that are kept up-to-date automatically. Dust also provides a version history feature that lets you track your iterations, model outputs and few-shot examples.
If you want to get inspired by some examples of LLM apps created by the community, you can check out the Community Example Apps section on Dust's website. You can find apps for various use cases such as answering questions about the IPCC AR6 report, generating wedding thank you notes, summarizing news articles, extracting structured data from unstructured text, generating code from math expressions, and more.
Dust is a great way to unleash the power of LLMs for your projects and tasks. Whether you want to create a productivity assistant, a content generator, a data extractor, or anything else that involves natural language processing, Dust can help you achieve your goals faster and easier. To get started with Dust, you can visit their website at https://dust.tt/ and sign up for free.
- It allows users to design and deploy large language model apps with powerful workflows and semantic search capabilities.
- It supports multiple models from different providers such as OpenAI, Cohere, AI21 and more.
- It offers a free productivity assistant extension (XP1) that can access browser tabs content and help with various tasks such as summarizing, extracting, generating and more.
- It does not work with Google Docs and Google Sheets yet (work in progress).
- It has a limited model context size that can affect the performance of long documents especially when using multiple tabs.
- It requires users to send their tab content through its servers to OpenAI's API, which may raise privacy concerns.
Alternative AI Tools
What is Moonbeam AI? Moonbeam AI is a platform that aims to globalize creativity by connecting innovators and investors, government and entrepreneurs, with tools for data-driven collaboration and through an experienced brokerage network. Moonbeam AI consists of two main products: Moonbeam Exchange and Moonbeam Envision.
If you are looking for a way to add AI-powered search and generative answers to your application, you might want to check out Nuclia. Nuclia is an end-to-end and easy-to-use API that can process any kind of data, from text and documents to video and audio, and provide optimized search results and generative answers from any data source.
If you are looking for a way to transcribe audio and video files into text, you might want to check out AssemblyAI. AssemblyAI is a cloud-based service that uses artificial intelligence to convert speech to text in minutes. You can use AssemblyAI to transcribe podcasts, interviews, lectures, meetings, and more.
Datature is a company that provides a complete platform for building and deploying computer vision applications. Computer vision is a field of artificial intelligence that enables machines to see and understand images and videos. Datature simplifies the workflow to annotate, train, visualise, and deploy computer vision models, so you can launch products faster and better.
Juice Labs is a company that develops software for GPU virtualization and sharing. GPU stands for graphics processing unit, which is a specialized chip that can perform complex calculations faster than a CPU (central processing unit). GPU is often used for applications that require high-performance computing, such as graphics, gaming, artificial intelligence, and machine learning.