Pinecone

The Pinecone Vector Database Connector allows you to integrate Pinecone as a vector database for storing and retrieving vectorized data in your pipelines. This guide explains the configuration options available when setting up a Pinecone vector database connector.

Configuration Fields

Field Summary

Finding Required Information in Pinecone

API Key

To find your Pinecone API Key:

  1. Log in to your Pinecone Console

  2. Navigate to the API Keys section

  3. Copy your API key or generate a new one if needed

Configuring the Integration

  1. From the main menu, click on Vector Databases

  2. Click New Vector Database Integration

  3. Select the Pinecone card

  4. Fill in the required fields:

    • Enter a descriptive name for the connector

    • Paste your Pinecone API Key

    • Enter your Pinecone endpoint URL

  5. Click Create Pinecone Integration to test and save your configuration

Usage in Pipelines

When configuring a pipeline, you can select this Pinecone integration as the vector database output. Vectorize will then write the vectorized data to your specified Pinecone instance.

Troubleshooting

If you encounter issues while creating the integration:

  • Verify that your API Key is correct and has the necessary permissions

  • Ensure that your endpoint URL is accurate and does not include any object names

  • Check that your Pinecone index is properly configured and accessible

For further assistance, please refer to the Pinecone documentation or contact Vectorize support.

Last updated