# Knowledge (/examples/models/anthropic/knowledge)



<Warning>
  Anthropic retired the source's dated Sonnet 4 and Opus 4 models on June 15, 2026. Before running your saved copy, replace `claude-sonnet-4-20250514` or `claude-opus-4-20250514` with the active `claude-sonnet-4-6` model. See [model lifecycle status](https://platform.claude.com/docs/en/about-claude/model-deprecations).
</Warning>

```python title="knowledge.py"
"""Run `uv pip install ddgs sqlalchemy pgvector pypdf anthropic openai` to install dependencies."""

from agno.agent import Agent
from agno.knowledge.embedder.azure_openai import AzureOpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.anthropic import Claude
from agno.vectordb.pgvector import PgVector

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

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

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="recipes",
        db_url=db_url,
        embedder=AzureOpenAIEmbedder(),
    ),
)
# Add content to the knowledge
knowledge.insert(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf")

agent = Agent(
    model=Claude(id="claude-sonnet-4-20250514"),
    knowledge=knowledge,
)
agent.print_response("How to make Thai curry?", markdown=True)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno "psycopg[binary]" anthropic beautifulsoup4 openai pgvector pypdf sqlalchemy
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
        export AZURE_EMBEDDER_OPENAI_API_KEY="your_azure_embedder_openai_api_key_here"
        export AZURE_EMBEDDER_OPENAI_ENDPOINT="your_azure_embedder_openai_endpoint_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```powershell
        $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
        $Env:AZURE_EMBEDDER_OPENAI_API_KEY="your_azure_embedder_openai_api_key_here"
        $Env:AZURE_EMBEDDER_OPENAI_ENDPOINT="your_azure_embedder_openai_endpoint_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

    <Step title="Run PgVector">
      <CodeBlockTabs defaultValue="macOS / Linux">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="macOS / Linux">
            macOS / Linux
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="macOS / Linux">
          ```bash
          docker run -d \
            -e POSTGRES_DB=ai \
            -e POSTGRES_USER=ai \
            -e POSTGRES_PASSWORD=ai \
            -e PGDATA=/var/lib/postgresql \
            -v pgvolume:/var/lib/postgresql \
            -p 5532:5432 \
            --name pgvector \
            agnohq/pgvector:18
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```powershell
          docker run -d `
            -e POSTGRES_DB=ai `
            -e POSTGRES_USER=ai `
            -e POSTGRES_PASSWORD=ai `
            -e PGDATA=/var/lib/postgresql `
            -v pgvolume:/var/lib/postgresql `
            -p 5532:5432 `
            --name pgvector `
            agnohq/pgvector:18
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Update the source model">
    In your saved copy, replace `claude-sonnet-4-20250514` or `claude-opus-4-20250514` with `claude-sonnet-4-6`. Keep the other model settings.
  </Step>

  <Step title="Select the Azure embedding deployment">
    Your Azure resource must already have a `text-embedding-3-small` deployment. If its deployment name is not `text-embedding-3-small`, export its actual name before starting Python:

    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export AZURE_EMBEDDER_DEPLOYMENT="your_embedding_deployment_name"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```powershell
        $Env:AZURE_EMBEDDER_DEPLOYMENT="your_embedding_deployment_name"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>

    The endpoint and key must belong to that resource. These variables select an existing deployment; they do not create one.
  </Step>

  <Step title="Run the example">
    Save the code above as `knowledge.py`, then run:

    ```bash
    python knowledge.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/anthropic/knowledge.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/90_models/anthropic/knowledge.py)
