Download
Engram is a high-performance embedding and similarity search library focused on making retrieval-augmented workflows efficient, scalable, and easy to adopt by developers building search, recommendation, or semantic matching systems. It provides utilities to generate embeddings from text or other structured data, index them using efficient approximate nearest neighbor algorithms, and perform real-time similarity queries even on large corpora. Engineered with speed and memory efficiency in mind, Engram supports batched indexing, incremental updates, and custom distance metrics so developers can tailor search behaviors to their domain’s needs. In addition to raw similarity search, the project includes tools for clustering, ranking, and filtering results, enabling richer user experiences like “related content”, semantic auto-completion, and contextual filtering.
Features
- Fast embedding generation pipeline for text and structured data
- Approximate nearest neighbor indexing for scalable similarity search
- Batched indexing and incremental updates
- Customizable distance metrics for domain-specific needs
- Clustering and ranking utilities for rich result sets
- Integration with ML frameworks and accelerators
Project Samples
