LlamaIndex

pip install llama-index-tools-seltz llama-index

import os
from llama_index.tools.seltz import SeltzToolSpec

os.environ["SELTZ_API_KEY"] = "your-api-key"

# Initialize the tool
seltz_tool = SeltzToolSpec(api_key=os.environ["SELTZ_API_KEY"])

# List available tools
tool_list = seltz_tool.to_tool_list()
for tool in tool_list:
    print(tool.metadata.name)

# Search the web
results = seltz_tool.search("What is LlamaIndex?", max_documents=3)

for doc in results:
    print(f"URL: {doc.metadata['url']}")
    print(f"Content: {doc.text[:200]}...")

import os
import asyncio
from llama_index.tools.seltz import SeltzToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["SELTZ_API_KEY"] = "your-api-key"

# Create the tool spec
seltz_tool = SeltzToolSpec(api_key=os.environ["SELTZ_API_KEY"])
tool_list = seltz_tool.to_tool_list()

# Create an agent with Seltz tools
agent = FunctionAgent(
    tools=tool_list,
    llm=OpenAI(model="gpt-5.2"),
)

# Query the agent
async def main():
    response = await agent.run(
        "What are the latest developments in AI reasoning?"
    )
    print(response)

asyncio.run(main())

from llama_index.core import VectorStoreIndex
from llama_index.tools.seltz import SeltzToolSpec

# Fetch documents from the web
seltz_tool = SeltzToolSpec(api_key="your-api-key")
documents = seltz_tool.search("Python best practices 2025", max_documents=5)

# Build an index from the documents
index = VectorStoreIndex.from_documents(documents)

# Query the index
query_engine = index.as_query_engine()
response = query_engine.query("What are the recommended Python coding standards?")
print(response)