Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions app/spicedb/tutorials/agentic-rag/page.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

This guide shows how to add fine-grained authorization to a production-like RAG system using SpiceDB. Standard RAG pipelines follow a fixed `query -> retrieve -> generate` flow. This implementation adds a deterministic authorization step that agents cannot bypass. The example uses SpiceDB for authorization, [Weaviate](https://github.com/weaviate/weaviate) as the vector database, and the [LangChain-SpiceDB library](https://pypi.org/project/langchain-spicedb/).

The full code repository can be [found here](https://github.com/authzed/examples/tree/main/agentic-rag-authorization)
The full code repository can be [found here](https://github.com/authzed/examples/tree/weaviate/agentic-rag-authorization)

## Why Agentic RAG Needs Authorization

Expand Down Expand Up @@ -865,8 +865,8 @@ The `QueryRequest` Pydantic model enforces `max_attempts` between 1 and 5, preve

```bash
# 1. Clone the reference implementation
git clone https://github.com/authzed/agentic-rag-weaviate
cd agentic-rag-weaviate
git clone https://github.com/authzed/examples.git
cd agentic-rag-authorization

# 2. Start services (Weaviate + SpiceDB)
docker-compose up -d
Expand Down
Loading