openai-vectorstore

n8n community node to manage OpenAI Vector Stores - Create, search, and manage vector stores for semantic search and RAG applications

Package Information

Downloads: 5 weekly / 19 monthly
Latest Version: 1.0.1
Author: Radse

Available Nodes

OpenAI Vector Store icon
OpenAI Vector Store
Manage OpenAI Vector Stores for semantic search and RAG applications

Documentation

n8n-nodes-openai-vectorstore

n8n.io - Workflow Automation
npm
License

This is an n8n community node to manage OpenAI Vector Stores for semantic search and RAG (Retrieval-Augmented Generation) applications.

n8n is a fair-code licensed workflow automation platform.

Features

Full implementation of OpenAI Vector Stores API:

🗃️ Vector Store

Operation Description
Create Create a new vector store with custom chunking strategy
Get Retrieve vector store details
Get Many List all vector stores with pagination
Update Modify name, description, expiration policies
Delete Remove a vector store
Search Semantic search with filters, ranking, and score threshold

📄 Vector Store Files

Operation Description
Create Add a file with custom attributes for filtering
Get Retrieve file information
Get Content Get parsed content of a file
Get Many List files with status filter
Update Update file attributes/metadata
Delete Remove file from vector store

📦 File Batches

Operation Description
Create Add multiple files in batch
Get Check batch status
Cancel Cancel batch operation
List Files List files in a batch

Installation

Community Nodes (Recommended)

  1. Go to Settings > Community Nodes
  2. Select Install
  3. Enter n8n-nodes-openai-vectorstore
  4. Click Install

Manual Installation

# In your n8n installation directory
npm install n8n-nodes-openai-vectorstore

Credentials

You need an OpenAI API key:

  1. Go to OpenAI API Keys
  2. Create a new API key
  3. In n8n, create new credentials for "OpenAI Vector Store API"
  4. Enter your API key

Usage Examples

Create a Vector Store

{
  "resource": "vectorStore",
  "operation": "create",
  "name": "Knowledge Base",
  "additionalFields": {
    "description": "Support documentation",
    "expiresAfterDays": 30
  }
}

Semantic Search

{
  "resource": "vectorStore",
  "operation": "search",
  "vectorStoreId": "vs_abc123",
  "query": "How to reset password?",
  "searchOptions": {
    "max_num_results": 5,
    "score_threshold": 0.7,
    "rewrite_query": true
  }
}

Add File with Attributes

{
  "resource": "vectorStoreFile",
  "operation": "create",
  "vectorStoreId": "vs_abc123",
  "fileId": "file-xyz789",
  "additionalFields": {
    "attributes": {
      "category": "support",
      "language": "en"
    }
  }
}

Search with Filters

{
  "searchOptions": {
    "filters": {
      "type": "eq",
      "key": "category",
      "value": "support"
    }
  }
}

Use Cases

  • RAG Chatbots: Provide relevant context to AI assistants
  • Support Systems: Search documentation with natural language
  • Knowledge Management: Build enterprise knowledge bases
  • Document Analysis: Extract information from large document sets

Example Workflow

[Webhook] → [Vector Store: Search] → [OpenAI: Chat] → [Respond]
  1. Receive user question
  2. Search for relevant documents
  3. Generate response with context
  4. Send answer

Resources

License

MIT

Discussion