Runnable LlamaIndex FunctionAgent examples powered directly by capsolver-agent.
Examples only: no
llamaindex-capsolverPyPI package, duplicated SDK, or independent release lifecycle.
The demo converts ordinary async Python functions into LlamaIndex tools. Those functions delegate every operation to the shared CapSolver executor, keeping schemas, solving behavior, error handling, and browser support centralized.
git clone https://github.com/capsolver-ai/llamaindex-capsolver.git
cd llamaindex-capsolver
python -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txtExport the keys in .env.example, then run python examples/quickstart.py.
from capsolver_agent import create_executor
from llama_index.core.agent.workflow import FunctionAgent
capsolver = create_executor()
async def get_capsolver_balance() -> str:
return str(await capsolver.execute("get_balance", {}))
agent = FunctionAgent(tools=[get_capsolver_balance], llm=llm)See examples/quickstart.py for solving and balance tools.
examples/quickstart.py LlamaIndex FunctionAgent demo
requirements.txt Shared SDK repositories and LlamaIndex
tests/test_demo.py Offline validation
.github/workflows/ci.yml Demo checks
Use the example only for lawful, user-authorized workflows that respect target-site terms. Never commit secrets or private target data.
See CONTRIBUTING.md, SUPPORT.md, and SECURITY.md. Licensed under the ISC License.
LlamaIndex is a third-party project. This repository is maintained by CapSolver and is not affiliated with or endorsed by LlamaIndex.