> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agenticenv.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Retrieval (RAG)

> Ground agent responses with Weaviate or pgvector using agentic, prefetch, or hybrid retriever modes

Grounds agent responses with `WithRetrievers`. Pick **one backend** per run.

| Backend               | Entrypoint                               |
| --------------------- | ---------------------------------------- |
| Weaviate              | `go run ./agent_with_retriever/weaviate` |
| PostgreSQL + pgvector | `go run ./agent_with_retriever/pgvector` |

Sample KB documents are seeded by Task infra. Edit `docker/weaviate/sample-documents.json` or `docker/pgvector/sample-documents.json` and re-run `up` to change corpus content.

Source: [`examples/agent_with_retriever/`](https://github.com/agenticenv/agent-sdk-go/tree/main/examples/agent_with_retriever)

## Retriever modes

Set `RETRIEVER_MODE` in `.env` (default `agentic`):

| Mode       | Behavior                                                                        |
| ---------- | ------------------------------------------------------------------------------- |
| `agentic`  | Retriever exposed as a tool; LLM decides when to search                         |
| `prefetch` | Search runs once before the first LLM call; context injected into system prompt |
| `hybrid`   | Prefetch and retriever tools                                                    |

Prefetch/hybrid embed your **exact user message** — use concrete questions aligned with the sample KB (returns, shipping, warranty, etc.).

## Setup

From `examples/`:

```bash theme={null}
task infra:status
```

**Weaviate:**

```bash theme={null}
task infra:weaviate:up
go run ./agent_with_retriever/weaviate "What is the return policy?"
task infra:weaviate:down
```

**pgvector:**

```bash theme={null}
task infra:pgvector:up
go run ./agent_with_retriever/pgvector "What is the return policy?"
task infra:pgvector:down
```

## Run examples

```bash theme={null}
# Agentic (default)
go run ./agent_with_retriever/weaviate "What is the return policy?"

# Prefetch — search before first LLM call
RETRIEVER_MODE=prefetch go run ./agent_with_retriever/weaviate "What are the return and shipping rules?"

# Hybrid
RETRIEVER_MODE=hybrid go run ./agent_with_retriever/pgvector "Summarize warranty coverage."
```

Use `SHOW_TELEMETRY=true` to compare prefetch vs agentic search counts.

## Expected output

```
Our return policy allows returns within 30 days of purchase with a receipt.
Items must be in their original condition. Sale items are final sale.
```

The response is grounded in the sample KB documents seeded by `task infra:weaviate:up` / `task infra:pgvector:up`. With `SHOW_TELEMETRY=true` in agentic mode you'll see `total_retriever_searches: 1`.

## Learn more

<CardGroup cols={2}>
  <Card title="Retrieval" icon="book-open" href="/features/retrieval">
    Retriever modes and backends
  </Card>

  <Card title="Memory" icon="brain" href="/examples/memory">
    Long-term memory on same infra
  </Card>
</CardGroup>