Build powerful workflows on top of LLMs🔥
Chained LLM apps
- Chain arbitrarily between calls to models and code execution.
- Avoid overfitting by iterating on your LLM app design on several inputs simultaneously.
- Design against models served by Cohere, OpenAI, AI21 and more soon. Switch models seamlessly.
- Have easy access to iterations, model outputs and few-shot examples saved automatically.
- Speed up iterations and reduce costs with cached model interactions.
Apps that do things
- Interact with Google search, code execution blocks and other action blocks to come.
- Deploy to an API endpoint or the Dust assistant XP1.
Semantic searchcoming soon
- Add your team's Notion, Google Docs or Slack to adapt app behaviour to your own data.
Community Example Apps
Discover apps created by the community. They serve as great examples to get started with Dust.
Generate code to answer maths questions
Solving the blank page problem for wedding thank you notes
Answer questions with high factual accuracy by searching online and compiling responses based on content downloaded from websites (with references).
Teach LLM to teach itself new tasks by teaching it to generate few shot examples from high-level tasks descriptions and prompting itself with them.
Dust is open source and part of AI Grant