Mixedbread

Question Answering

Get AI-powered answers to questions about your vector store content. The system searches through your documents, retrieves the most relevant chunks, and generates context-aware responses with source file metadata for transparency. Perfect for building Q&A systems and knowledge bases from your document collections.

Command

mxbai vs qa <name-or-id> <question> [options]

Options

  • --top-k <n> - Number of context chunks to use (default: 10)
  • --threshold <score> - Minimum relevance score for context chunks
  • --return-metadata - Include source file metadata in the response

Note: Default values for --top-k can be configured using mxbai config. See the for details.

Examples

# Ask a basic question
mxbai vs qa "My Documents" "How do I configure authentication?"

# Ask for more results
mxbai vs qa "My Documents" "What are the deployment steps?" --top-k 15

# Ask with relevance threshold
mxbai vs qa "My Documents" "What is the API rate limit?" --threshold 0.8

# Ask and include metadata in results
mxbai vs qa "My Documents" "How to handle errors?" --return-metadata

# Combine options
mxbai vs qa "My Documents" "Best practices for security" --top-k 20 --return-metadata
Search
Search through vector store content using natural language queries.
Sync
Sync files with intelligent change detection using Git-based analysis.

Last updated: July 5, 2025