Guides
Step-by-step guides organized by area. Each guide includes working code you can copy into your project.
Core
| Guide | Description |
| Pipeline | Steps, callbacks, decorators, and async execution |
| Retrieval | Dense, sparse, and hybrid retrieval with RRF |
| Advanced Retrieval | Rerankers, routers, and classification-based dispatch |
| Memory | Sliding window, summary buffer, and graph memory |
Data
| Guide | Description |
| Ingestion | Parsing documents, chunking strategies, and indexing |
| Storage | Context stores, vector stores, and backend configuration |
| Multi-modal | Working with images and tables alongside text |
Intelligence
| Guide | Description |
| Query Transform | HyDE, multi-query expansion, and query decomposition |
| Classifiers | Routing queries to the right retrieval path |
| Agent | Building agents with tools and skills |
Operations
| Guide | Description |
| Evaluation | Retrieval and RAG quality metrics |
| Observability | Tracing, cost tracking, and OpenTelemetry integration |
| Cache | Caching backends for retrieval and LLM calls |
| Formatters | Provider-specific formatting (Anthropic, OpenAI, generic) |