👀Aim+LlamaIndex: Track intermediate prompts, responses, and context chunks through Aim’s sophisticated UI.

GIF

In this demo, you can see the capabilities of Aim for logging events while running queries within LlamaIndex. We use the AimCallback to store the outputs and showing how to explore them using Aim Text Explorer.

aimstack.io is an awesome tool for tracking metadata for your LLM app (e.g. experiments 🧪, prompts 📝, and more).

It’s the perfect tool for tracing within LlamaIndex, which manages multiple LLM calls on top of your data.

Now you can easily track intermediate prompts, responses, and context chunks through Aim’s sophisticated UI.

Full guide here: https://gpt-index.readthedocs.io/en/latest/examples/callbacks/AimCallback.html

Aim repo: https://github.com/aimhubio/aim
Llama_index repo: https://github.com/jerryjliu/llama_index