RAG Knowledge Base
Upload documents and have AI-powered conversations with your own knowledge. HuluChat uses RAG (Retrieval-Augmented Generation) to provide accurate, context-aware responses.
What is RAG?
RAG (Retrieval-Augmented Generation) allows AI to answer questions based on your own documents. Instead of relying solely on the AI's training data, it searches through your uploaded files to find relevant information.
Upload
Add your documents
Search
AI finds relevant info
Chat
Get accurate answers
How to Use
- 1
Open the RAG Panel
Click the knowledge base icon (📚) in the sidebar or use the keyboard shortcut Ctrl + K
- 2
Upload Documents
Drag and drop files or click to browse. Supported formats include PDF, TXT, MD, DOCX, and more.
- 3
Wait for Processing
Documents are processed locally on your device. This may take a few seconds depending on file size.
- 4
Start Chatting
Ask questions about your documents. AI will search through your knowledge base and provide relevant answers.
Supported File Formats
PDF documents
TXT
Plain text files
MD
Markdown files
DOCX
Microsoft Word documents
CSV
Comma-separated values
JSON
JSON data files
🔒 Privacy First
Your documents are processed entirely on your device. No data is uploaded to any server. The knowledge base uses local vector storage (ChromaDB) for fast, private semantic search.
Tips for Best Results
📝 Use clear, well-formatted documents
Documents with clear headings and structure are easier for AI to search.
🎯 Be specific in your questions
Instead of "What's in the document?", ask "What are the key features mentioned in section 3?"
📚 Organize by topic
Create different chat sessions for different topics to keep your knowledge organized.