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

# LlamaIndex

> LlamaIndex is a framework for building LLM-powered applications that use your own data.

## Prerequisites

Before you can configure and use LlamaIndex with Connect AI, you must do the following:

* [OAuth JWT bearer token](/ja/API/Authentication-Embedded) を生成します。PAT をコピーし、認証時にパスワードとして使用します。
* Obtain an OpenAI API key: [https://platform.openai.com](https://platform.openai.com/).
* Make sure you have Python >= 3.10 in order to install the LlamaIndex packages.

## Create the Python Files

<Steps>
  <Step>
    Create a folder for LlamaIndex MCP.
  </Step>

  <Step>
    Create a Python file within the folder called `llamaindex.py`.
  </Step>

  <Step>
    In `llamaindex.py`, set up your MCP server and MCP client to call the tools and prompts. The `Authorization` is `Bearer` and the JWT bearer token from the prerequisites.

    ```python expandable theme={null}
    from llama_index.llms.openai import OpenAI
    from llama_index.tools.mcp import BasicMCPClient, aget_tools_from_mcp_url
    from llama_index.core.agent import ReActAgent
    import asyncio

    client = BasicMCPClient(
        "https://mcp.cloud.cdata.com/mcp",
        headers={"Authorization": "Bearer OAUTH_JWT_TOKEN"}
    )

    async def main():
        # List available tools
        tools = await aget_tools_from_mcp_url("https://mcp.cloud.cdata.com/mcp", client=client)
       
        llm = OpenAI(model="gpt-4o", api_key="YOUR_OPENAI_KEY")   
        # Create ReActAgent
        agent = ReActAgent(tools=tools, llm=llm, verbose=True)
        # # Run a query
        response = await agent.run("List all the catalogs for me please")
        print(response)

    asyncio.run(main())
    ```
  </Step>
</Steps>

## Install the LlamaIndex Packages

Run the following command in your project terminal:

```bash theme={null}
pip install llama-index llama-index-llms-openai llama-index-tools-mcp
```

## Run the Python Script

<Steps>
  <Step>
    When the installation finishes, run the following command to execute the script:

    ```bash theme={null}
    python llamaindex.py
    ```
  </Step>

  <Step>
    The script discovers the Connect AI MCP tools needed for the LLM to query the connected data.
  </Step>

  <Step>
    Supply a prompt for the agent. The agent provides a response.

    <Frame>
      <img src="https://mintcdn.com/cdata/tJfdD354GT5ojxph/ja/images/llamaindex_client_terminal.png?fit=max&auto=format&n=tJfdD354GT5ojxph&q=85&s=676046d379b5c17a96096b7b143e506e" alt="LlamaIndex Client Terminal" width="1191" height="715" data-path="ja/images/llamaindex_client_terminal.png" />
    </Frame>
  </Step>
</Steps>