Pinecone (beta)

What is Pinecone?

Pinecone makes it easy to provide long-term memory for high-performance AI applications. It’s a managed, cloud-native vector database with a simple API and no infrastructure hassles. Pinecone serves fresh, filtered query results with low latency at the scale of billions of vectors.

Why Connect Pinecone to Monte Carlo?

Connecting Pinecone to Monte Carlo allows for monitoring the most critical component of your AI pipelines. We've brought Monte Carlo's data anomaly detection to Pinecone by observing patterns in Vector Count by Index and Index Namespace.

As soon as you connect Pinecone, hourly tracking of Vector Count by each Index and Index Namespace will be cataloged to be view and actively monitored by Monte Carlo's machine learning - no other setup necessary. You can see the expected Thresholds of Vector Count highlighted on the chart as well.

More monitors for your Pinecone assets are coming soon.

Integration Setup

1. Create a Pinecone API Key

Pinecone API keys are configured per Project, so you will need to create an integration in Monte Carlo per Pinecone Project.

  1. In Pinecone, select the Project you would like to monitor in Monte Carlo.
  2. Navigate to the API Keys pane.
  3. Use the Create API Key button.
  4. Enter a Key Name, like monte_carlo and click Create Key.
  5. Save this API Key for using with Monte Carlo. Note the Environment here for your API key as well as the Project ID listed in the URL of this page. For example, this is the structure of the Pinecone URL: projects/<environment>:<project-id>/keys

2. Create the Integration in Monte Carlo

  1. Navigate to the Settings -> Integrations page in Monte Carlo.
  2. Under Data Lake and Warehouses, click Create, and click Pinecone.
    If you are not using a recent Data Collector, you will be warned here and need to go to the Settings -> Collectors page and upgrade.
  3. For the Integration Name, it is recommended to suffix with a project identifier, like Pinecone-my-project.
  4. The Environment, Project ID, and API Key are what you noted above in Step 1.5. Examples:
    Environment: us-east-1-aws, eastus-azure, or eu-west4-gcp.
    Project ID: asd8fgh
  5. Click Create in the bottom left. A validation to test connectivity will be run. If the connection fails, you can double-check your credentials, Skip validation to proceed, and contact Monte Carlo Support.