> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Traditional RAG with LanceDB

## Code

```python theme={null}
from agno.agent import Agent
from agno.embedder.openai import OpenAIEmbedder
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.models.openai import OpenAIChat
from agno.vectordb.lancedb import LanceDb, SearchType

# Create a knowledge base of PDFs from URLs
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    # Use LanceDB as the vector database and store embeddings in the `recipes` table
    vector_db=LanceDb(
        table_name="recipes",
        uri="tmp/lancedb",
        search_type=SearchType.vector,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)
# Load the knowledge base: Comment after first run as the knowledge base is already loaded
knowledge_base.load()

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    knowledge=knowledge_base,
    # Enable RAG by adding references from AgentKnowledge to the user prompt.
    add_references=True,
    # Set as False because Agents default to `search_knowledge=True`
    search_knowledge=False,
    show_tool_calls=True,
    markdown=True,
)
agent.print_response(
    "How do I make chicken and galangal in coconut milk soup", stream=True
)
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U openai lancedb tantivy pypdf sqlalchemy agno
    ```
  </Step>

  <Step title="Run Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/agent_concepts/rag/traditional_rag_lancedb.py
      ```

      ```bash Windows theme={null}
      python cookbook/agent_concepts/rag/traditional_rag_lancedb.py
      ```
    </CodeGroup>
  </Step>
</Steps>