llama-index-tools-serpdive 0.1.0

LlamaIndex tool for SERPdive, the AI Search API and Tavily alternative: answer-ready web content for agents, same speed, 20.2% fewer tokens, higher answer quality (60.7% of decided duels) on a public benchmark

llama-index-tools-serpdive

The official LlamaIndex tool for SERPdive, the AI Search API: your agent asks a question, the tool returns Documents whose text is answer-ready web content, extracted, cleaned, and sized for an LLM. On a public, replayable 1,000-question benchmark, SERPdive runs at the same speed as Tavily, feeds your LLM 20.2% fewer tokens, and wins 60.7% of decided quality duels.

Install

pip install llama-index-tools-serpdive

Get a free API key (no card required) at serpdive.com/dashboard/keys and set it:

export SERPDIVE_API_KEY="sd_live_..."

Use directly

from llama_index_tools_serpdive import SerpdiveToolSpec

spec = SerpdiveToolSpec()
documents = spec.serpdive_search("latest developments in solid state batteries")
# each Document: text = extracted page content; metadata = {url, title, date}

Use in an agent

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.anthropic import Anthropic
from llama_index_tools_serpdive import SerpdiveToolSpec

agent = FunctionAgent(
    tools=SerpdiveToolSpec().to_tool_list(),
    llm=Anthropic(model="claude-sonnet-5"),
)
await agent.run("What changed in the EU AI Act this month?")

Options

SerpdiveToolSpec(
    model="moby",     # "mako" (default): key sentences, fast. "moby": full page text, deep research
    max_results=5,    # hard cap on delivered results, 1-10
    api_key="sd_live_...",  # defaults to SERPDIVE_API_KEY
)

Localization is automatic: the language of the query picks where we search. Failed searches are never billed.

Links

• API reference
• Public benchmark (replayable end to end)
• Python SDK (this package is a thin layer over it)
• MCP server for Claude, Cursor and other MCP clients

License

MIT