What is RAG?
RAG combines your custom knowledge with the AI’s general intelligence:- Upload documents (PDFs, text files, web pages, etc.)
- AI processes and indexes the content
- During calls, the AI searches your knowledge base
- Combines retrieved information with its response
How to Set Up RAG
Step 1: Prepare Your Content
Step 1: Prepare Your Content
Supported Formats:
- PDF documents
- Text files (.txt, .md)
- Web pages (URLs)
- Structured data (JSON, CSV)
- Keep documents focused and well-organized
- Use clear headings and sections
- Include FAQs, product info, policies, etc.
- Remove outdated or irrelevant information
Step 2: Upload to Your Assistant
Step 2: Upload to Your Assistant
- Go to your assistant’s RAG Configuration section
- Click “Upload Documents” or “Add Knowledge”
- Upload files or paste URLs
- Wait for processing (may take a few minutes)
- Test with sample questions
Step 3: Configure RAG Settings
Step 3: Configure RAG Settings
- Similarity Threshold: How closely questions must match content
- Max Results: Number of knowledge pieces to retrieve
- Context Window: How much text to include in responses
Use Cases
Customer Support
Customer Support
- Product manuals and troubleshooting guides
- Company policies and procedures
- FAQ documents
- Return/refund policies
Sales & Information
Sales & Information
- Product catalogs and specifications
- Pricing information
- Company background and history
- Service descriptions
Internal Knowledge
Internal Knowledge
- Employee handbooks
- Internal procedures
- Technical documentation
- Training materials
Best Practices
- Quality over quantity: Better to have fewer, high-quality documents than many poor ones
- Keep content updated: Regularly review and update your knowledge base
- Test thoroughly: Ask questions you expect callers to ask and verify accuracy
- Use clear language: Write content in plain language, avoiding jargon when possible
- Organize logically: Group related information together
Troubleshooting
Common RAG Issues
Common RAG Issues
- AI doesn’t find relevant info: Check similarity threshold, add more specific keywords
- Outdated information: Remove or update old documents
- Conflicting answers: Ensure documents don’t contradict each other
- Too much irrelevant content: Use more focused, specific documents