Bedrijfsdata icon

Bedrijfsdata

Get data from the Bedrijfsdata API.

Actions30

Overview

The "Live Web RAG" resource with the "Get RAG Search" operation allows users to perform search queries on popular search engines and retrieve relevant snippets of information. This node is useful for scenarios where you want to gather summarized content or search results related to a specific query, such as market research, competitive analysis, or content aggregation.

For example, you can enter a search query like "latest electric cars 2024" and get back concise snippets from various web sources, optionally including cleaned HTML, markdown, or raw content formats. This helps automate the process of collecting and summarizing web search data within an n8n workflow.

Properties

Name Meaning
Search Query (Required) The main search query string to look up in popular search engines.
Search Options Optional parameters to refine the search:
- Country (ISO 639-1): Country code to localize search results (e.g., US, NL).
- Language (ISO 3166-1 Alpha-2): Language code for the search (e.g., us, nl).
- Limit: Maximum number of results to return (minimum 1).
- Timeout: Time allocated for content retrieval; higher values yield more complete summaries but take longer.
Output Options Options to customize the output format:
- Add Cleaned HTML: Include cleaned HTML content (Enable/Disable).
- Add Markdown: Include markdown content with options for CommonMark or cleaned markdown without images/links.
- Add Raw Content: Include raw text content (Enable/Disable).
- Add Raw HTML: Include raw HTML content (Enable/Disable).
- Max. Snippets Length: Limit length of snippets; if >0, unique sentences are added to the result.

Output

The node outputs JSON data containing search results with snippets from popular search engines based on the query and options provided. The structure typically includes:

  • A list of search result items.
  • Each item may contain:
    • Snippets of text summarizing the content.
    • Optionally cleaned HTML or markdown versions of the content.
    • Raw content or raw HTML if requested.
    • Metadata about each snippet or source.

If binary data is included (not explicitly shown here), it would represent content such as downloaded HTML or other media related to the search results.

Dependencies

  • Requires an API key credential for accessing the Bedrijfsdata API service.
  • The node makes HTTP GET requests to the /rag_search endpoint of the Bedrijfsdata API.
  • No additional environment variables are explicitly required beyond the API authentication.

Troubleshooting

  • Missing or invalid API key: Ensure that the API key credential is correctly configured in n8n; otherwise, the request will fail authentication.
  • Empty or invalid search query: The "Search Query" property is required. Providing an empty string or invalid input will cause the node to error out or return no results.
  • Timeout issues: Setting a very low timeout might result in incomplete summaries. Increase the timeout value to allow more thorough content retrieval.
  • Invalid country or language codes: Use valid ISO codes to avoid unexpected API errors or empty results.
  • API rate limits: If many requests are made in a short time, the API might throttle or reject calls. Implement retry logic or reduce request frequency.

Common error messages will relate to network issues, invalid parameters, or authentication failures. Review the error details returned by the node and verify all inputs and credentials.

Links and References

Discussion