Mixedbread

Search

Perform semantic search that understands meaning rather than just keywords. Uses advanced multimodal embedding models to find relevant content based on context and intent with sub-second response times. Search across text chunks within vector stores using natural language queries like "comfortable running shoes" to find "cushioned athletic sneakers".

Command

mxbai vs search <name-or-id> <query> [options]

Options

  • --top-k <n> - Number of results to return (default: 10, range: 1 - 100)
  • --threshold <score> - Minimum similarity score (range: 0.0 - 1.0)
  • --return-metadata - Include file metadata in results
  • --rerank - Enable result reranking for better relevance (default: false)
  • --file-search - Search files instead of chunks

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

Examples

# Basic search
mxbai vs search "My Documents" "how to get started"

# Search with more results
mxbai vs search "My Documents" "authentication" --top-k 20

# Search with similarity threshold
mxbai vs search "My Documents" "configuration" --threshold 0.8

# Search and include metadata in results
mxbai vs search "My Documents" "deployment" --return-metadata

# Search and rerank results
mxbai vs search "My Documents" "best practices" --rerank

# Search showing text chunks
mxbai vs search "My Documents" "error handling" --file-search

# Combine multiple options
mxbai vs search "My Documents" "API usage" --top-k 15 --rerank --return-metadata
File Management
Upload files and manage files within vector stores.
Question Answering
Ask questions about content in your vector stores and get AI-powered answers.

Last updated: July 5, 2025