SerpAPI
SerpAPI node enables real-time web search, news, and job search capabilities within StackAI workflows, providing structured and actionable search results.
What is SerpAPI?
SerpAPI is a powerful node in StackAI that allows you to perform real-time web searches, news searches, job searches, and website to markdown directly within your workflow. It leverages the SerpAPI platform to fetch up-to-date information from the internet, making it ideal for research, content generation, and data enrichment tasks.
Example of Usage
Connect a Text Input node to SerpAPI.
Set the action to "Web Search".
Enter a search query like "latest AI trends".
The node returns a list of relevant web results, which can be displayed or processed further.
Available Actions
1. Web Search
Description: Performs a real-time search on the web and returns a list of relevant results.
Inputs:
Query (string, required): The search term or phrase to look up (e.g., "StackAI features").
Num (number, optional): Specify how many search results you want to retrieve (default: 5), needs to be at least 1.
Configurations:
Device (dropdown, optional): Choose whether to simulate search results as seen on desktop or mobile devices. Default is desktop.
CountryCode (dropdown, optional): Select which country's search engine to use for results.
LanguageCode (dropdown, optional): Choose the language for search results and interface.
Outputs:
Web Search Results (object_array): A collection of web search results containing URLs, titles, and content snippets.
Example: Input:
{
"query": "StackAI workflow automation"
}
Output:
{
"results": [
{
"title": "How to Automate Workflows with StackAI",
"link": "https://example.com/stackai-workflow",
"snippet": "Learn how to automate your business processes using StackAI..."
}
],
"metadata": {
"total_results": 100000,
"search_time": "0.45s"
}
}
2. News Search
Description: Fetches the latest news articles related to a specific query.
Inputs:
Query (string, required): The search term or phrase to look up (e.g., "AI news").
Configurations:
Device (dropdown, optional): Choose whether to simulate search results as seen on desktop or mobile devices. Default is desktop.
CountryCode (dropdown, optional): Select which country's search engine to use for results.
LanguageCode (dropdown, optional): Choose the language for search results and interface.
Outputs:
Result (string): The result of the news search
Example: Input:
{
"query": "AI breakthroughs"
}
Output:
{
"articles": [
{
"title": "Recent Breakthroughs in AI",
"link": "https://news.com/ai-breakthroughs",
"source": "Tech News",
"published_date": "2025-07-20"
}
],
"metadata": {
"total_articles": 50
}
}
3. Job Search
Description: Searches for job postings based on a given query and location.
Inputs:
Query (string, required): The search term or phrase to look up (e.g., "Data Scientist").
Num (number, optional): Specify how many search results you want to retrieve (default: 5), needs to be at least 1.
Configurations:
CountryCode (dropdown, optional): Select which country's search engine to use for results.
LanguageCode (dropdown, optional): Choose the language for search results and interface.
Outputs:
Jobs (string): List of jobs found.
Example: Input:
{
"query": "machine learning engineer",
"country_code": "UNITED_STATES"
}
Output:
{
"jobs": [
{
"title": "Machine Learning Engineer",
"company": "Tech Innovators",
"location": "San Francisco, CA",
"link": "https://jobs.com/ml-engineer"
}
],
"metadata": {
"total_jobs": 120
}
}
4. Website to Markdown
Description: This action takes a website URL and converts the entire page into a markdown-formatted document. It’s useful for extracting readable, structured content from any public web page.
Inputs:
Url (string, required): The URL of the website you want to convert to markdown.
Configurations:
Location (string, optional): The geographic location from which to perform the conversion (affects region-specific content). Default is US.
Outputs:
Markdown (string): The markdown representation of the website
Example: Input:
{
"url": "https://en.wikipedia.org/wiki/Markdown"
}
Output:
{
"markdown": "# Markdown\nMarkdown is a lightweight markup language..."
}
Last updated
Was this helpful?