DocumentationWorkflowsApps and services
Web search node
Searches the web and returns the most relevant hits as a list, title, URL, snippet. Handy paired with the AI agent: feed the hits as context into the prompt to produce up-to-date answers. Learn how to configure it, map inputs and outputs, run a test and resolve common errors.
8 min readUpdated
What this node does
Searches the web and returns the most relevant hits as a list, title, URL, snippet. Handy paired with the AI agent: feed the hits as context into the prompt to produce up-to-date answers.
Use Web search as a clearly defined step in an anymize workflow.
- Processes one input.
- Provides one output for following steps.
- Runs as a regular step in the flow.
Set up the node
- 01Open a workflow and add Web search from the node catalog.
- 02Complete the required fields and map values from previous steps.
- 03Run the node with a small test record and inspect its output.
- 04Connect the successful output and activate the workflow after an end-to-end test.
Operations and modes
Web search has one focused purpose. Its available settings appear when you select the node.
Settings
| Field | Meaning | Area |
|---|---|---|
| Verify source links | Checks HTTP reachability and returns only reachable links. Up to three checks in parallel, eight seconds per link. Does not prove that a job listing is still active. | Standard |
| Search request | What to search for. Templates like {{ $json.topic }} are resolved at runtime. | Standard |
| Max. hits | How many hits come back (1,10). 5 is a good default. | Standard |
| Search depth | Basic is fast and cheap. Deep research searches more sources and makes a relevance pass, takes longer. | Standard |
| Generate short answer | When on, the web search also returns a 1-sentence answer. Only makes sense for factual questions. | Standard |
| Run once per item | Off (default): the node runs once for the whole input. On: if it receives several items (e.g. from Split Out), it runs once PER item, and {{ $json }} is that one item each time. This is how you work through a file list entry by entry. | Standard |
| If one item fails | "Skip" writes an `error` field for the failed item and keeps processing the rest, instead of losing the whole run to a single unreadable file. | Standard |
| Pause between items (milliseconds) | Wait before every run except the first. 1000 = 1 second per item. Useful when the other side would otherwise throttle you. Maximum 300000 (5 minutes). | Standard |
Inputs and outputs
| Input | Meaning | Type |
|---|---|---|
| query | Search request. Overrides the config field. | text |
| Output | Meaning | Type |
|---|---|---|
| results | List of hits. Each entry has title, url, snippet, score. | json |
| answer | Optional short answer, if the request was answerable as a fact. | text |
| total | Number of hits returned. | number |
| verification | Reachability evidence with HTTP status and check time. Includes unavailable sources so missing results are not mistaken for a complete search. | json |
This node can process lists item by item. Error handling and the delay between items are available in advanced settings.
Example and test run
Search current news: begin with a small, recognizable record. Inspect the output and only map fields that are present there.
Test-run example
{
"query": "DSGVO Update 2026 Newsletter Tracking"
}Access and security
Before activation, review which data enters this step and what its output contains.
Store keys and credentials in the protected connection manager. Never paste them into normal workflow fields, test data or descriptions.
Troubleshooting
- No output: inspect the latest run and confirm that the previous node returned the expected fields.
- Empty variable: open the previous step output and use a field name from the real test data.
- List processed once: enable per-item execution in advanced settings.