Skip to main content
Pinecone is a vector database designed for AI and machine learning applications. It provides tools for storing, searching, and managing vector embeddings, enabling semantic search, recommendation systems, and other AI-powered features that require similarity matching and vector operations.

​
1. Add your Pinecone access

  1. In the Destinations tab, click on the “Add destination” button located on the top right of your screen. Then, select the Pinecone option from the list of connectors.
  2. Click Next and you’ll be prompted to add your access:
  • API Key: Your Pinecone API key, generated on the Pinecone platform.
  • Index name: The Pinecone index where your data will be written. Your index is created on the Pinecone platform, and its dimension must match the embed model you select below (each model option indicates its dimension). For more details, refer to Pinecone’s documentation.
  • Mode: The sync mode to use when writing data:
    • Append: Adds the incoming records to the existing data in the namespace.
    • Overwrite: Clears the namespace before loading, so it will contain only the incoming records after the run.
  • Embed model: The model used to generate the vector embeddings. You can choose between Pinecone-hosted models (e.g., llama-text-embed-v2, the default, and multilingual-e5-large), OpenAI models (e.g., text-embedding-3-small, text-embedding-3-large), and open-source models (e.g., BAAI/bge-small-en-v1.5, sentence-transformers/all-MiniLM-L6-v2). Each option indicates the embedding dimension it produces, which must match your index’s dimension.
  • OpenAI API key: Required only if you select an OpenAI embed model. This key is used to generate the embeddings on OpenAI’s API.
  1. Click Next.
Records are written to a namespace named after the input table, inside the index you configured.

​
2. Select your data to send

  1. The next step is letting us know which data you want to send to Pinecone. Select the tables or even entire layers, sources or transformations to send more than one table.
Tip: The resource can be found more easily by typing its name.
  1. Click Next.

​
3. Map your data fields

Configure how the fields from your source table should be mapped to the Pinecone record fields: Once you are done configuring, click Next.

​
4. Configure your Pinecone data destination

  1. Describe your destination for easy identification within your workspace. You can inform things like what data it sends, to which team it belongs, etc.
  2. To define your Trigger, consider how often you want data to be sent to this destination. This decision usually depends on how frequently you need the new table data updated (every day, once a week, only at specific times, etc.).
  3. Click Done.

​
Check your new destination!

  1. Once completed, you’ll receive confirmation that your new destination is set up!
  2. You can view your new destination on the Destinations page. Now, for you to be able to see it on your Pinecone platform, you have to wait for the pipeline to run. You can monitor it on the Destinations page to see its execution and completion. If needed, manually trigger the pipeline by clicking on the refresh icon. Once executed, your data should be seen on Pinecone.
If you encounter any issues, reach out to us via Slack, and we’ll gladly assist you!