Skip to Content
Get StartedOverview

Endee Vector Database Documentation

Endee is a high-performance vector database designed for speed and efficiency. It enables rapid Approximate Nearest Neighbor (ANN) searches for applications requiring robust vector search capabilities with advanced filtering and metadata support.

Key Features

  • Fast ANN Searches: Efficient similarity searches on vector data using HNSW algorithm
  • Multiple Distance Metrics: Support for cosine, L2, and inner product distance metrics
  • Metadata Support: Attach and search with metadata and filters
  • Advanced Filtering: Powerful query filtering with operators like $eq, $in, and $range
  • High Performance: Optimized for speed and efficiency
  • Scalable: Handle millions of vectors with ease
  • Memory Optimization: Optional half-precision (FP16) storage for reduced memory footprint

Use Cases

  • Semantic Search: Build intelligent search systems that understand meaning, not just keywords
  • Recommendation Systems: Power personalized recommendations based on similarity matching
  • RAG Applications: Enhance LLM applications with relevant context retrieval for Retrieval-Augmented Generation
  • Image and Video Search: Find similar images and videos using visual embeddings

Workflow

Here’s how to use Endee Vector Database in your applications:

1. Generate Vectors

Use an external embedding model to convert your data into dense vectors. Popular options include OpenAI embeddings, Sentence Transformers, or any embedding model of your choice.

2. Create Index

Create an index using our SDKs to store and organize your vectors efficiently.

3. Upsert Vectors

Upsert vectors with unique IDs, metadata, and filters. Each vector can have associated metadata for filtering during search.

4. Search with a Vector

Use the same embedding model to convert your query text into a vector, then search the index to find the most similar results. Apply filters for more precise searches.

Get Started with SDKs

Ready to start building? Choose your preferred SDK:

Quick Start