User Guide¶
This section provides comprehensive guides for using EmbedCache.
Overview¶
EmbedCache offers two modes of operation:
- Service Mode - Run as a REST API service
- Library Mode - Integrate directly into your Rust application
Topics¶
- Running as Service - Deploy and manage the EmbedCache service
- Library Usage - Use EmbedCache in your Rust applications
- Chunking Strategies - Understand and choose chunking methods
- Embedding Models - Available models and their characteristics
- Caching - How caching works and how to manage it
Quick Reference¶
Default Configuration¶
| Setting | Default Value |
|---|---|
| Chunking Type | words |
| Chunk Size | 512 |
| Embedding Model | BGESmallENV15 |
Available Chunking Types¶
| Type | Description |
|---|---|
words |
Split by whitespace into fixed-size chunks |
llm-concept |
LLM-based semantic concept chunking |
llm-introspection |
LLM-based analysis and chunking |