LlamaIndex Workflows is a new way to easily create agents that is built to move past linear workflows to more dynamic, decision-making processes. This video walks through a concrete example of getting started, evaluating and tracing an agent. Learn how to leverage LlamaIndex’s Workflow functionality – and the ability to define cyclical events, cyclical workflows with LLMs – and instrument with Phoenix, tracing the path that the LLMs are following to better understand how tools are getting used and how various steps in the workflow are being executed.
🔗 Learn more about LlamaIndex Workflows, how it compares to graphs, and how to trace and evaluate workflows: https://arize.com/blog/llamaindex-workflows-a-new-way-to-build-cyclical-agents/
LlamaIndex blog introducing Workflows: https://www.llamaindex.ai/blog/introducing-workflows-beta-a-new-way-to-create-complex-ai-applications-with-llamaindex
Example notebooks of using Workflows with Arize Phoenix:
🦙 Function Calling Agent: https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/workflow/function_calling_agent.ipynb
🦙 RAG Agent: https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/workflow/rag.ipynb
🦙 ReAct Agent: https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/workflow/react_agent.ipynb
Please consider giving Phoenix a ⭐ on GitHub: https://github.com/Arize-ai/phoenix/
