RAG Reranking

# 🛠️ Setup Guide  
**Author:** [Nate Herk](https://www.youtube.com/@nateherk)

Follow the steps below to get your Retrieval-Augmented Generation (RAG) workflow up and running:

### ✅ Step 1: Connect Your [Supabase](https://supabase.com/) Vector Store  
Ensure your Supabase instance is ready and accessible. This will store your embedded documents with metadata.
Here is a [video tutorial](https://youtu.be/JjBofKJnYIU) on setting that up.

### ✅ Step 2: Connect Your [OpenAI](https://platform.openai.com/account/api-keys) Embeddings  
Use the `text-embedding-3-small` or similar model for embedding your documents. Make sure your API key is active.

### ✅ Step 3: Connect Your [OpenAI API Key](https://platform.openai.com/account/api-keys)  
This powers your embedding generation model. Add it via the HTTP Request node or a credential.

### ✅ Step 4: Add Your [OpenRouter](https://openrouter.ai/) API Key  
Use this for your main RAG agent—add your key via HTTP request or credential node.

### ✅ Step 5: Connect a [Cohere](https://dashboard.cohere.com/api-keys) Re-Ranker  
The re-ranker improves answer quality. Add your API key for better relevance ranking on retrieved documents.

### ✅ Step 6: Vectorize Documents with Metadata  
Ensure your data ingestion process tags documents with meaningful metadata before vectorization. This helps with structured retrieval.

### 💬 Final Step: Start Chatting  
Prompt your agent and test the RAG flow end-to-end—watch it pull context-rich answers from your vector store.