> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge

> Examples for retrieval-augmented generation, knowledge filters, and custom retrievers.

| Example                                                                             | Description                                                                                                   |
| ----------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
| [Agentic RAG](/examples/agents/knowledge/agentic-rag)                               | Agentic RAG with PgVector hybrid search: the agent queries a recipe knowledge base on demand.                 |
| [Agentic RAG With Reasoning](/examples/agents/knowledge/agentic-rag-with-reasoning) | Demonstrates agentic RAG with reranking and explicit reasoning tools.                                         |
| [Agentic RAG With Reranking](/examples/agents/knowledge/agentic-rag-with-reranking) | Agentic RAG over LanceDB with hybrid search and a Cohere reranker ordering results.                           |
| [Custom Retriever](/examples/agents/knowledge/custom-retriever)                     | Use knowledge\_retriever to provide a custom retrieval function.                                              |
| [Knowledge Filters](/examples/agents/knowledge/knowledge-filters)                   | Filter knowledge base searches using static filters or agentic filters.                                       |
| [RAG Custom Embeddings](/examples/agents/knowledge/rag-custom-embeddings)           | This cookbook is an implementation of Agentic RAG using Sentence Transformer Reranker with multilingual data. |
| [References Format](/examples/agents/knowledge/references-format)                   | Control how knowledge base references are formatted for the agent.                                            |
| [Traditional RAG](/examples/agents/knowledge/traditional-rag)                       | Traditional RAG that injects PgVector search results into the prompt instead of using a search tool.          |