Installation
Install the integration package and configure your API key.
uv add llama-index-tools-quercleAvailable tools
All five Quercle endpoints are exposed as tools through this integration.
| Tool | Endpoint | Description |
|---|---|---|
QuercleToolSpec.fetch | Fetch | Fetch a URL and return an AI-synthesized answer based on page content and your prompt. |
QuercleToolSpec.search | Search | Search the web and return an AI-synthesized answer from the retrieved results. |
QuercleToolSpec.raw_fetch | Raw Fetch | Fetch a URL and return raw markdown or HTML. |
QuercleToolSpec.raw_search | Raw Search | Run web search and return raw results. |
QuercleToolSpec.extract | Extract | Fetch a URL and return chunks relevant to a query. |
Endpoint examples
Use the same endpoint methods directly through this integration.
from llama_index.tools.quercle import QuercleToolSpec
quercle = QuercleToolSpec(api_key="qk_your_api_key")
result = quercle.fetch(url="https://example.com", prompt="Summarize the main points")
print(result)Use in agents
Wire the integration into your agent orchestration loop.
import asyncio
from llama_index.tools.quercle import QuercleToolSpec
from llama_index.llms.openai import OpenAI
from llama_index.core.agent.workflow import FunctionAgent
async def main():
spec = QuercleToolSpec()
tools = spec.to_tool_list() # all 5 tools: fetch, search, raw_fetch, raw_search, extract
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt="You are a helpful research assistant.",
)
response = await agent.run(user_msg="Find trusted sources about prompt-injection defense")
print(response)
asyncio.run(main())