RAG with Pinecone AI Agent > Using the RAG with Pinecone AI Agent recipe > Step 4. Configure the Pinecone Retriever tool connection
  

Step 4. Configure the Pinecone Retriever tool connection

Use the Pinecone Retriever tool to enhance search and retrieval tasks by efficiently locating semantically similar items within large datasets using vector similarity techniques. Configure the index name, API key, model, and text key to access the Pinecone database.
  1. 1Open the Pinecone_Retriever tool connection.
  2. 2In the Connection Details, enter values for the following properties:
    3. Property
    Description
    Index Name
    Name of the specific vector index within Pinecone that contains your document embeddings for search.
    API Key
    Authentication token that grants access to your Pinecone account and services.
    Model
    AI or embedding model used to convert input queries and documents into vector embeddings that Pinecone can index and search against.
    Different models can vary in retrieval accuracy, relevance, and performance.
    Text Key
    Optional. Name of the document field that contains the textual content to be retrieved and displayed when a vector search returns matching documents.
  3. 3Save the connection.