> For the complete documentation index, see [llms.txt](https://doc.thordata.com/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.thordata.com/doc/scraping/serp-api/integration/sdk-integration/how-to-integrate-thordata-with-llamaindex.md).

# How to Integrate ThorData with LlamaIndex

Connect the ThorData SERP API to LlamaIndex, enabling your agents to perform real-time web search, image search, news search, and obtain structured search results. ThorData supports coverage across 190 countries/regions worldwide and is suitable for AI Agents, SEO tools, market research, and search-driven applications.

#### Get ThorData API Token

* Log in to your [ThorData ](https://dashboard.thordata.com/serp-api/get-started)[Dashboard](https://dashboard.talordata.com/).
* Go to [SERP API - API Token](https://dashboard.thordata.com/serp-api/get-started). If you have not yet generated an API Token, generate a new one.

#### Installation

Install the required package:

```
python -m pip install llama-index-tools-thordata-serp
```

#### Usage Example

The following example demonstrates how to use ThorData tools with LlamaIndex.

```
llm = OpenAI(model="gpt-4o", api_key="your-api-key")
​
thordata_tool = thordataToolSpec(api_key="your-api-key", zone="unlocker")
​
tool_list = thordata_tool.to_tool_list()
​
for tool in tool_list:
    tool.original_description = tool.metadata.description
    tool.metadata.description = "thordata web scraping tool"
​
agent = OpenAIAgent.from_tools(tools=tool_list, llm=llm)
​
query = (
    "Find and summarize the latest news about AI from major tech news sites"
)
tool_descriptions = "\n\n".join(
    [
        f"Tool Name: {tool.metadata.name}\nTool Description: {tool.original_description}"
        for tool in tool_list
    ]
)
​
query_with_descriptions = f"{tool_descriptions}\n\nQuery: {query}"
​
response = agent.chat(query_with_descriptions)
print(response)
```