Introducing Daggr: Chain apps programmatically, inspect visually

Summary

Building AI applications that connect multiple models and APIs often results in fragile scripts or requires complex production orchestration tools. To address rapid experimentation needs, Daggr introduces an open-source Python library created by the Gradio team for chaining AI workflows programmatically. Developers define workflows in Python code using components like GradioNode, FnNode, and InferenceNode, which automatically generate an interactive visual canvas served on port 7860. The interface allows users to inspect intermediate outputs, modify inputs, rerun individual pipeline steps without complete re-execution, and maintain persistent state across workspaces called sheets. Currently in beta, Daggr supports local execution with automatic fallback to remote APIs and integrates directly with Hugging Face Spaces.

Takeaways

1. 1

   Daggr supports three node types: GradioNode for Gradio Space endpoints or local clones, FnNode for custom Python functions, and InferenceNode for Hugging Face Inference Providers.

2. 2

   Setting run_locally=True on GradioNode automatically clones a Space into an isolated virtual environment and falls back to remote APIs if local execution fails.

3. 3

   The automatically generated visual canvas persists state, inputs, and cached results locally, allowing individual workflow steps to be rerun without executing the entire pipeline.