Jump to Content
Documentation
API Reference
Log In
Documentation
Log In
Documentation
API Reference
Search
Getting started
What is Not Diamond?
Demo quickstart
Chat with Not Diamond
API keys
LLM models
Model gateway
Pricing
Support
Open source
Core features
Training a custom router
Cost and latency tradeoffs
`model_select` vs. `create`
Function calling
Structured outputs
Joint prompt optimization
Preference IDs
Personalized routing with feedback
Reliability, fallbacks, and load-balancing
RAG Auto-Optimization
Introduction
Creating test data
Optimize retrieval pipelines
Evaluating RAG applications
Evaluation metrics
Embedding models
Tutorials and examples
Chat
Strong vs weak LLM routing
RAG workflows with LlamaIndex
Agent workflows
LLM evaluation tutorial
SAMMO tutorial
DSPy tutorial
Human-in-the-loop routing
Routing between RAG agents
Use cases
Customer support
Legal summarization
Code documentation
Clients and libraries
API reference
Node library
Python Modules
How Not Diamond works
How Not Diamond works
Benchmark performance
Privacy, security, and local deployments
Integrations
OpenAI integration
OpenRouter integration
LangChain integration
LiteLLM
Suggest
