Monitoring
Pinecone generates time-series performance metrics for each Pinecone index. You can monitor these metrics directly in the Pinecone console, or you can pull them into Prometheus or Prometheus- and OpenMetrics-compatible tools, such as Datadog.
Monitor in the Pinecone Console
To view performance metrics in the Pinesone console:
- Open the Pinecone console.
- Select the index that you want to monitor.
- Go to the Metrics tab.
Monitor with Prometheus
This feature is available only for pod-based indexes on Enterprise or Enterprise Dedicated plans. Serverless indexes do not currently support Prometheus monitoring.
Pinecone metrics are available at the following URL:
https://metrics.YOUR_ENVIRONMENT.pinecone.io/metrics.
To monitor Pinecone with your own Prometheus instance, configure the prometheus.yml file to target the Pinecone metrics URL, using your API key for authorization:
scrape_configs:
- job_name: pinecone-job-1
authorization:
credentials: <api-key-here>
scheme: https
static_configs:
- targets: ['metrics.YOUR_ENVIRONMENT.pinecone.io/metrics']
Your API key must be passed via the Authorization header as a bearer token like Authorization: Bearer \<api-key\>. Also, note that only the metrics for the project associated with the API key will be ingested by Prometheus.
For more configuration details, see the Prometheus docs.
Example Prometheus queries
Return the average latency in seconds for all requests against the Pinecone index example-index:
avg by (request_type) (pinecone_request_latency_seconds{index_name="example-index"})
Return the vector count for the Pinecone index example-index:
sum ((avg by (app) (pinecone_vector_count{index_name="example-index"})))
Return the total number of requests against the Pinecone index example-index over one minute:
sum by (request_type)(increase(pinecone_request_count_total{index_name="example-index"}[60s]))
Return the total number of upsert requests against the Pinecone index example-index over one minute:
sum by (request_type)(increase(pinecone_request_count_total{index_name="example-index", request_type="upsert"}[60s]))
Return the total errors returned by the Pinecone index example-index over one minute:
sum by (request_type) (increase(pinecone_request_error_count{
index_name="example-index"}[60s]))
Return the index fullness metric for the Pinecone index example-index:
round(max (pinecone_index_fullness{index_name="example-index"} * 100))
Monitor with Datadog
To monitor Pinecone with Datadog, use Pinecone’s direct Datadog integration.
Available Metrics
The metrics available are as follows:
| Name | Type | Description | Labels |
|---|---|---|---|
| pinecone_vector_count | gauge | The number of records per pod in the index. | - pid: Process identifier - index_name: Name of the index - project_name: Pinecone project name |
| pinecone_request_count_total | counter | The number of data plane calls made by clients. | - pid: Process identifier - index_name: Name of the index - project_name: Pinecone project name - request_type: One of upsert, delete, fetch, query, describe_index_stats |
| pinecone_request_error_count_total | counter | The number of data plane calls made by clients that resulted in errors. | - pid: Process identifier - index_name: Name of the index - project_name: Pinecone project name - request_type: One of upsert, delete, fetch, query, describe_index_stats |
| pinecone_request_latency_seconds | histogram | The distribution of server-side processing latency for pinecone data plane calls. | - pid: Process identifier - index_name: Name of the index - project_name: Pinecone project name - request_type: One of upsert, delete, fetch, query, describe_index_stats |
| pinecone_index_fullness | gauge | The fullness of the index on a scale of 0 to 1. | - pid: Process identifier - index_name: Name of the index - project_name: Pinecone project name |
Was this page helpful?