Actions2
Overview
This node performs AI-powered web search operations. It allows users to submit natural-language objectives or keyword queries to retrieve relevant web search results processed by an AI service. The node supports two processing modes: a standard "Base" processor and an advanced "Pro" processor, enabling different levels of search sophistication.
Common scenarios for this node include:
- Finding recent news or updates on specific topics.
- Gathering curated search results filtered by domain inclusion or exclusion.
- Extracting concise excerpts from multiple web sources for research or monitoring purposes.
For example, a user could input the objective "Find recent news about artificial intelligence developments" and receive a list of summarized search results limited to trusted domains like wikipedia.org and reuters.com.
Properties
| Name | Meaning |
|---|---|
| Objective | Natural-language description of what the web search is trying to find. |
| Processor | Search processing mode; options are: - Base: Standard search processing - Pro: Advanced search processing |
| Additional Fields | Collection of optional parameters: - Include Domains: Comma-separated list of domains to include in search results. - Exclude Domains: Comma-separated list of domains to exclude. - Max Results: Maximum number of search results to return (1-50). - Max Characters Per Result: Maximum characters to include in excerpts per result (100-10,000). - Search Queries: Comma-separated list of traditional keyword search queries. |
Output
The node outputs a JSON array where each item corresponds to one execution of the search operation. Each output item contains the search results returned by the external AI-powered web search API.
The exact structure of the json output depends on the API response but generally includes:
- A list of search results matching the objective or queries.
- Each result may contain fields such as title, URL, excerpt text limited by the max characters setting, and possibly metadata about the source.
No binary data output is produced by this node.
Dependencies
- Requires an API key credential for the external AI-powered web search service ("parallelApi").
- The node makes HTTP requests to
https://api.parallel.aiendpoints. - Proper configuration of the API authentication credential in n8n is necessary for successful operation.
Troubleshooting
- Timeouts: The node retries fetching results up to 15 times with a timeout of approximately 4 minutes per attempt. If the task execution times out, it throws an error indicating the maximum attempts were reached. To resolve, check network connectivity and API service status.
- Invalid JSON in Input: If the input or schema JSON is malformed, the node will throw an error specifying invalid JSON. Ensure all JSON inputs are correctly formatted.
- Authentication Errors: If the API key credential is missing or invalid, requests will fail. Verify that the API key is correctly set up in n8n credentials.
- Domain Filters: Incorrectly formatted domain lists (e.g., missing commas) may cause unexpected filtering behavior. Use comma-separated domain names without spaces.
Links and References
- Parallel AI Web Search API Documentation (hypothetical link based on context)
- n8n Documentation - Creating Custom Nodes