SerpKite/langchain-serpkite

LangChain integration for SerpKite, the Google search API built for AI
agents. The package gives you:
| Class | What it does |
| SerpKiteSearch | Tool (serpkitesearch) that returns Markdown, which uses few tokens, for agents |
| SerpKiteSearchResults | Tool (serpkitesearchresultsjson) that returns a list of result dicts (title, link, domain, snippet, …) |
| SerpKiteAnswer | Tool (serpkiteanswer) that returns a cited answer from live Google results, with the numbered sources |
| SerpKiteResearch | Tool (serpkiteresearch) that runs a deep-research task and returns its cited Markdown report |
| SerpKiteAssistant | Tool (serpkitechatgpt, serpkitegemini, …) that asks ChatGPT, Gemini, Copilot, Google AI Mode or Brave AI and returns its answer, sources, products and brand mentions |
| SerpKiteRetriever | Retriever that returns Google results as Documents, optionally with full page Markdown |
| SerpKiteWebpageLoader | Document loader that fetches any public URL as clean Markdown |
| SerpKiteAPIWrapper | Holds the API key and the sync and async SerpKite clients |
Every class supports both sync and async (invoke/ainvoke, load/alazyload).
## Install
bash
pip install -U langchain-serpkite
export SERPKITEAPIKEY=sktlive... # https://app.serpkite.com/keys
## Tools
python
from langchainserpkite import SerpKiteSearch, SerpKiteSearchResults
search = SerpKiteSearch() # optional: endpoint="news", country="de", num=20, apikey="..."
print(search.invoke({"query": "best espresso machine"})) # Markdown string
papers = SerpKiteSearch(endpoint="scholar") # or news, images, videos, maps, places,
# shopping, patents, autocomplete
rows = SerpKiteSearchResults(maxresults=5).invoke({"query": "langgraph checkpointer"})
# [{"position": 1, "title": "...", "link": "https://...", "domain": "...", "snippet": "..."}, ...]
The model can set query, num, country, language and time
(hour|day|week|month|year). Defaults set on the tool (country=, language=, location=,
num=) apply when the model leaves a field out. engine= is set on the tool only (see
Search engines & fallback).
## Cited answers and research
python
from langchainserpkite import SerpKiteAnswer, SerpKiteResearch
answer = SerpKiteAnswer(depth="fast") # "standard" (default) also reads the top numsources pages
print(answer.invoke({"query": "what is the latest stable rust version"}))
# The latest stable Rust release is … [1].
# Sources:
# [1] Rust blog - https://blog.rust-lang.org/...
research = SerpKiteResearch(effort="lite") # lite | standard (default) | deep
print(research.invoke({"query": "compare managed Postgres vector search options"}))
Both tools use responseformat="contentandartifact": called with a tool call, the
ToolMessage.artifact is the full serpkite.types.AnswerResponse / ResearchTask (citations,
sources, meta.credits, meta.llm).
SerpKiteAnswer takes depth, numsources (1-5), includedomains, excludedomains,
country, language and time on the tool; the model only sets query.
SerpKiteResearch starts the task and waits for the report (one to several minutes, up to
timeout=900 seconds). If the wait runs out it returns the task's state; the task keeps running
server-side. effort sets how much is searched and read.