Pinecone Vector Store

​

Node Details

• Name: Pinecone_VectorStores
• Type: Pinecone
• Version: 5.0
• Category: Vector Stores

​

Base Classes

• Pinecone
• VectorStoreRetriever
• BaseRetriever

​

Credentials

• Type: pineconeApi
• Required Fields:
  • pineconeApiKey

​

Input Parameters

1. Document (optional, list)
   • Type: Document
   • Description: List of documents to be embedded and stored
2. Embeddings (required)
   • Type: Embeddings
   • Description: Embedding model to use for vectorizing documents
3. Record Manager (optional)
   • Type: RecordManager
   • Description: Keeps track of records to prevent duplication
4. Pinecone Index (required)
   • Type: string
   • Description: Name of the Pinecone index to use
5. Pinecone Namespace (optional)
   • Type: string
   • Description: Namespace within the Pinecone index
6. File Upload (optional)
   • Type: boolean
   • Description: Enables file upload functionality in the chat
7. Pinecone Text Key (optional)
   • Type: string
   • Default: “text”
   • Description: Key in the metadata for storing text
8. Pinecone Metadata Filter (optional)
   • Type: json
   • Description: Filter to apply on metadata during queries
9. Top K (optional)
   • Type: number
   • Default: 4
   • Description: Number of top results to fetch
10. MMR Parameters (optional)
    • Various parameters for Maximal Marginal Relevance search

​

Outputs

1. Pinecone Retriever
   • Type: Retriever
   • Description: A retriever object for querying the Pinecone vector store
2. Pinecone Vector Store
   • Type: VectorStore
   • Description: The Pinecone vector store object

​

Functionality

​

Upsert Method

• Adds or updates documents in the Pinecone index
• Handles file upload and chat ID association if enabled
• Supports record management to prevent duplication

​

Delete Method

• Removes documents from the Pinecone index based on provided IDs
• Supports deletion through record manager or direct ID-based deletion

​

Init Method

• Initializes the Pinecone vector store with the provided configuration
• Sets up metadata filters, including chat ID filtering if file upload is enabled
• Returns either a vector store or a retriever based on the node configuration

​

Use Cases

• Semantic search applications
• Question-answering systems
• Document retrieval systems
• Recommendation engines
• Any application requiring efficient similarity search on vector data

​

Notes

• This node integrates closely with LangChain’s implementation of Pinecone
• It supports advanced features like MMR search and metadata filtering
• The node is designed to work within a larger workflow, potentially connecting with other nodes for complex AI and ML tasks