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

# Agent with Knowledge

> Ground an agent in documents using RAG.

Create an agent that retrieves relevant information from a knowledge base before answering.

<Steps>
  <Step title="Create the agent">
    ```python agent_knowledge.py theme={null}
    from definable.agent import Agent
    from definable.knowledge import Knowledge
    from definable.vectordb import InMemoryVectorDB

    knowledge = Knowledge(vector_db=InMemoryVectorDB())
    knowledge.add("Definable supports 10 LLM providers: OpenAI, Anthropic, Google, DeepSeek, Mistral, Moonshot, xAI, Perplexity, Ollama, and OpenRouter.")
    knowledge.add("Agents can use tools, knowledge, memory, middleware, and tracing.")
    knowledge.add("The @tool decorator converts Python functions into agent-callable tools.")

    agent = Agent(
        model="gpt-4o",
        knowledge=knowledge,
        instructions="Answer questions using the provided knowledge base. Cite specific facts.",
    )

    output = agent.run("What LLM providers does Definable support?")
    print(output.content)
    ```
  </Step>

  <Step title="Install dependencies">
    <Snippet file="install-definable.mdx" />
  </Step>

  <Step title="Export your API key">
    <Snippet file="export-openai-key.mdx" />
  </Step>

  <Step title="Run">
    ```bash theme={null}
    python agent_knowledge.py
    ```

    The agent retrieves the most relevant documents and uses them to answer accurately.
  </Step>
</Steps>

<Tip>
  You can also use path shorthand to load an entire directory:

  ```python theme={null}
  agent = Agent(model="gpt-4o", knowledge="./docs/")
  ```

  This auto-configures InMemoryVectorDB + OpenAIEmbedder + RecursiveChunker and loads all supported files from the directory.
</Tip>