Prompt engineering, re-imagined🔥
Built on years of experience working with large language models.
With one goal, help accelerate their deployment.
Chained LLM apps
- Chain arbitrarily between calls to models and code execution.
Multiple inputs
- Avoid overfitting by iterating on your LLM app design on several inputs simultaneously.
Switch models
- Design against models served by Cohere, OpenAI, and more soon. Switch models seamlessly.
Few-shot examples sanity
- Manage few-shot examples in isolated and versioned datasets.
History preserved
- Iterations, model outputs and few-shot examples are saved and versioned automatically.
Caching
- Speed up iterations and reduce costs with cached model interactions.
Models that act
- Build apps that take action: search Google, curl block and more integrations to come.
Easy deployment
- Deploy in one click. Aggregate production traffic for later testing and fine-tuning.
Community Example Apps
Discover apps created by the community. They serve as great examples to get started with Dust.
maths-generate-code
public
Generate code to answer maths questions
d12ac33169
wedding-thank-yous
public
Solving the blank page problem for wedding thank you notes
cc20d98f70
web-search-assistant
public
Answer questions with high factual accuracy by searching online and compiling responses based on content downloaded from websites (with references).
2316f9c6b0
toolbot-repro
public
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.
b39f8e9023