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

# Agent with Knowledge

> Attach a PgVector knowledge base to an AwsBedrock agent.

## Code

```python knowledge.py theme={null}
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.models.aws import AwsBedrock
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

knowledge_base = Knowledge(
    vector_db=PgVector(table_name="recipes", db_url=db_url),
)
knowledge_base.insert(
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
)

agent = Agent(
    model=AwsBedrock(id="mistral.mistral-large-2402-v1:0"),
    knowledge=knowledge_base,
)
agent.print_response("How to make Thai curry?", markdown=True)
```

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Set your API keys**

```bash theme={null}
export AWS_ACCESS_KEY_ID=***
export AWS_SECRET_ACCESS_KEY=***
export AWS_REGION=***
export OPENAI_API_KEY=***  # Used by the default OpenAIEmbedder
```

**2. Install dependencies**

```bash theme={null}
uv pip install -U boto3 sqlalchemy pgvector pypdf openai psycopg agno
```

**3. Run PgVector**

```bash theme={null}
docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:18
```

**4. Run Agent**

```bash theme={null}
python knowledge.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.