User Guide Overview

Complete guide to using bruno-llm with bruno-core framework.

What is bruno-llm?

bruno-llm provides production-ready LLM and embedding provider implementations that integrate with the bruno-core framework. It enables you to:

• Use multiple LLM providers with a unified interface
• Generate embeddings for semantic search and RAG applications
• Switch between local and cloud models
• Leverage advanced features like caching, streaming, and cost tracking

Providers

• Ollama - Local LLM and embedding inference
• OpenAI - Cloud GPT models and embeddings

Advanced Features

• Embeddings - Semantic search and vector operations
• Response Caching - Cache LLM responses to reduce costs
• Context Management - Handle context window limits
• Streaming - Stream tokens as they're generated
• Cost Tracking - Track API costs per request
• Middleware - Add logging, validation, and custom processing

See Also

• API Reference
• Examples