Answer Questions from Documents with RAG Using Supabase, OpenAI, & Cohere Reranker - n8n Workflow | Neura Market
Answer Questions from Documents with RAG Using Supabase, OpenAI, & Cohere Reranker
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
This comprehensive RAG workflow enables your AI agents to answer user questions with contextual knowledge pulled from your own documents, using metadata-rich embeddings stored in Supabase.
**Key Features:**
- RAG Agents powered by GP-4.5 or GP-3.5 via OpenRouter or OpenAI.
- Supabase Vector Store to store and retrieve document embeddings.
- Cohere Reranker to improve response relevance and quality.
- Metadata Agent to enrich vectorized data before ingestion.
- PDF Extraction Flow to automatically parse and upload documents with metadata.
**Setup Steps:**
1. Connect your Supabase Vector Store.
2. Use OpenAI Embeddings (e.g., text-embedding-3-small).
3. Add API keys for OpenAI and/or OpenRouter.
4. Connect a reranker like Cohere.
5. Process documents with metadata before embedding.
6. Start chatting - your AI agent now returns context-rich answers from your own knowledge base!
Perfect for building AI assistants that can reason, search, and answer based on internal company data, academic papers, support docs, or personal notes.
Platform
n8n
Category
AI
Price
Free
Creator
Luan Correia
code
stickyNote
googleDrive
manualTrigger
agent
extractFromFile
chatTrigger
rerankerCohere
embeddingsOpenAi
lmChatOpenRouter
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.