Observability

First-class, built-in observability to understand the operations Spice performs.

Observability in Spice enables task tracking and performance monitoring through a built-in distributed tracing system that can export to Zipkin or be viewed via the runtime.task_history SQL table.

Spice records detailed information about runtime operations through trace IDs, timings, and labels - from SQL queries to AI completions. This task history system helps operators monitor performance, debug issues, and understand system behavior across individual requests and overall patterns.

Use-Cases

Debugging and Troubleshooting

  • Trace AI chat completion steps and tool interactions to identify why a request isn't responding as expected
  • Investigate failed queries and other task errors

Performance Analysis

  • Track SQL query/tool use execution times
  • Identify slow-running tasks

Usage Analytics

  • Track usage patterns by protocol and dataset
  • Understand how AI models are using tools to retrieve data from the datasets available to them

Portal Interface

The Spice platform provides a built-in UI for visualizing the observability traces that Spice OSS generates.

The Observability tab shows the span tree for one ai_chat request. The ai_chat span contains two ai_completion spans and the list_datasets and document_similarity tool calls. Under document_similarity, a vector_search span contains a text_embed span and three sql_query spans. The detail pane shows the user message 'How do I set up a Spice application?', the JSON input, and the Markdown answer. A side panel shows the openai model and a duration of 6.456 seconds.

An observability trace for an AI chat completion in the Spice portal.