Key Features

What you can do

Multi-Provider LLM Support

Supports multiple LLM providers such as HuggingFace, Ollama, and OpenAI-compatible APIs for text generation and embeddings.

Adaptive Search Pipeline

Combines coarse-grained filtering with accurate retrieval to optimize search efficiency and performance.

Performance Optimizations

Includes GPU batching, ZMQ-based distance communication, CPU/GPU overlapping, and selective caching of high-degree nodes.

CLI Tool for Quick Setup

Provides a command-line interface for easy installation, setup, and querying of private data sources like Slack.

Local, Privacy-Focused Deployment

Enables zero cloud dependency by running entirely on local machines, supporting privacy-sensitive use cases.