To link prompts to traces, you need to associate the prompt used in a generation with the corresponding trace. This process has been highlighted here.

​
Metrics and Analytics

After linking prompts to traces, you can access various metrics to evaluate performance:
  • Median Latency: Time taken for the model to generate a response
  • Median Input Tokens: Number of tokens in the input prompt
  • Median Output Tokens: Number of tokens in the generated response
  • Median Costs: Cost associated with the generation process
  • Traces Count: Total number of generations for a specific prompt
  • First and Last Generation Timestamp: Timeframe of the generations
These metrics are accessible by navigating to your prompt in the Future AGI dashboard and viewing the Metrics tab.