SerpAPI Web Search

​

Node Details

• Name: serpApi
• Type: Document
• Category: Document Loaders
• Version: 1.0

​

Credentials

• Type: serpApi
• Fields:
  • serpApiKey: API key for accessing the SerpAPI service

​

Input Parameters

1. Query (required)

   • Type: string
   • Description: The search query to be sent to SerpAPI

2. Text Splitter (optional)

   • Type: TextSplitter
   • Description: A text splitter to break down large documents into smaller chunks

3. Additional Metadata (optional)

   • Type: JSON
   • Description: Additional metadata to be added to the extracted documents

4. Omit Metadata Keys (optional)

   • Type: string
   • Description: A comma-separated list of metadata keys to omit from the final documents. Use ’*’ to omit all default metadata keys except those specified in Additional Metadata.

​

Output

The node outputs an array of IDocument objects, each representing a search result with the following structure:

• pageContent: The main content of the search result
• metadata: Associated metadata, which can be customized or filtered based on input parameters

​

Functionality

1. Initializes the SerpAPILoader with the provided query and API key
2. Loads documents using the SerpAPILoader
3. If a text splitter is provided, splits the documents
4. Applies additional metadata if specified
5. Filters metadata based on the “Omit Metadata Keys” input
6. Returns the processed documents

​

Use Cases

• Web research automation
• Content aggregation from search results
• Data collection for analysis or training language models
• Integrating up-to-date web information into document processing workflows

​

Notes

• Requires a valid SerpAPI credential to function
• Can be combined with other document processing nodes for more complex workflows
• Useful for dynamically generating document collections based on search queries