Pinecone generates time-series performance metrics for your assistants, such as number of requests, error counts, chat/context latency, and file processing time. You can monitor these metrics directly in the Pinecone console.Documentation Index
Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt
Use this file to discover all available pages before exploring further.
- Open the Pinecone console.
- Select the project containing the assistant(s) you want to monitor.
- Go to Assistant > Metrics.