agentskillexchange Evaluate and trace agent workflows with RagaAI Catalyst
Use RagaAI Catalyst to instrument agent runs, collect traces, manage evaluation datasets, inspect execution graphs, and review regressions before deployment.
Prerequisites
Python environment, ragaai-catalyst SDK, Catalyst project credentials, instrumented LLM or agent workflow, and evaluation datasets or trace samples.
Installation
Use the upstream install or setup path that matches your environment:
- To install RagaAI Catalyst, you can use pip:
- pip install ragaai-catalyst
Requirements and caveats from upstream:
- python
Basic usage or getting-started notes:
Before using RagaAI Catalyst, you need to set up your credentials. You can do this by setting environment variables or passing them directly to the RagaAICatalyst class:
from ragaai_catalyst import RagaAICatalyst
Extracted from upstream docs: https://raw.githubusercontent.com/raga-ai-hub/RagaAI-Catalyst/HEAD/README.md