Mixedbread
Search

Search

Search your Vector Store using natural language to find exactly what you need. Vector Stores understand the meaning behind your queries, not just keywords, making it perfect for conversational search and complex questions.

Search for chunks of content across your Vector Store:

When you search, Vector Stores understand your natural language query and find the most relevant content across all your files. Results are automatically ranked by relevance with confidence scores.

For complete details on chunk object structure including all content types and properties, see .

Search Options

Top-k Results

Control the number of results returned:

Optimization Tips:

  • Start with top_k=10 for most use cases
  • Increase for comprehensive searches
  • Decrease for faster response times

Filter

Filter search results to narrow down your search scope. Vector store search supports two types of filtering:

Filter by Metadata

Filter based on file metadata for precise targeting:

For complete metadata filtering capabilities and advanced patterns, see .

Filter by Files

Rerank

Improve search result quality by reranking results with specialized models:

Reranking applies a second-stage ranking model to improve relevance, especially useful for complex queries or when initial results need refinement. You can use simple boolean (True) or configure advanced options with model selection and metadata inclusion.

Learn more about for advanced reranking strategies and model options.

Search across multiple Vector Stores simultaneously:

Considerations:

  • Results are merged and re-ranked together
  • May need higher top_k for diverse results
  • Different Vector Stores may have different metadata schemas

Search for complete files rather than individual chunks:

File search is ideal for:

  • Document Discovery: Finding relevant files or documents
  • Content Exploration: Browsing collections by topic
  • Research: Locating papers or resources on specific subjects

File search returns complete file objects with relevance scores, giving you document-level context rather than fragmented chunks.

For complete details on file object structure and properties, see .

For detailed file search capabilities, configurations, and advanced patterns, see .

Next Steps

Now that you understand search basics, explore advanced capabilities:

Supported Metadata Types
Learn about supported metadata types and how to structure metadata for optimal search performance, filtering capabilities, and content organization in Mixedbread Vector Stores.
Metadata Filtering
Learn how to use metadata filtering syntax to narrow search results and find exactly what you're looking for in your Vector Stores.

Last updated: July 15, 2025