Simple RAG Configuration

Simple RAG uses pure vector (embedding) similarity to find relevant document chunks. It's the fastest architecture to deploy and works well for simple Q&A over a single domain.

Configuration Flow

Recommended Settings

The following settings provide a solid baseline for Simple RAG. Adjust based on your evaluation results and specific use case requirements.

Step 1: Project Setup

Project setup defines the identity and purpose of your RAG system. For Simple RAG, keep the domain focused to maximize retrieval accuracy.

Step 2: Knowledge Sources

Add your documents through direct upload or from your Document Library. For Simple RAG, stick to a single domain and keep documents under 50 MB each for optimal processing.

Step 3: Document Processing

Document processing prepares your raw text for embedding. Simple RAG works best with straightforward preprocessing — clean the text, split into fixed-size chunks, and preserve sentence boundaries.

Step 5: Pipeline Configuration

Pipeline configuration controls how queries are processed and results are returned. Simple RAG uses pure vector search with no keyword matching or graph traversal, keeping latency low and deployment simple.

Step 6: API Setup

Once configured, generate your API key and integrate using REST API, Python SDK, or MCP Protocol. Test your endpoints before deploying to production.

When to Use Simple RAG

• Quick proof-of-concept or prototype
• Single-domain knowledge base
• Straightforward Q&A over documentation
• Limited compute resources
• < 1000 documents

When to Upgrade

Consider Hybrid RAG or Graph RAG when:

• Users search with exact keywords that vector search misses
• You need to answer relationship-based questions
• Your domain has complex entity relationships
• Retrieval accuracy plateaus with vector search alone