Actions31
- Account Actions
- Agent Actions
- Browser Actions
- Crawling Actions
- Extract (Legacy) Actions
- Interact Actions
- Map & Search Actions
- Scraping Actions
Agent → Agent (Async) - Returns job ID for manual polling
AI-generatedOverview
This node interacts with the Firecrawl API to perform asynchronous data extraction tasks using an agent. It allows users to specify a natural language prompt describing the data to extract, optionally focus the agent on specific URLs, and define the expected data schema either by example or manually. The node returns a job ID that can be used for manual polling of the extraction results, making it suitable for scenarios where data extraction might take time and needs to be tracked asynchronously.
Use Case Examples
- Extract pricing information from multiple product pages by specifying URLs and a prompt.
- Find the founders of a company and their roles by providing a natural language prompt and a JSON schema example.
- Use a custom JSON body to define complex extraction tasks and receive a job ID for later retrieval.
Properties
| Name | Meaning |
|---|---|
| Prompt | Natural language description of the data to extract, guiding the agent on what information to find. |
| Specify URLs | Boolean flag to indicate whether to focus the agent on specific URLs or let it autonomously search the web. |
| URLs | List of URLs to focus the agent on, supporting multiple formats like comma-separated, newline-separated, or JSON array. |
| Schema Type | Defines how the output data schema is determined: none, generated from a JSON example, or manually defined. |
| JSON Example | Example JSON object used to automatically generate the output schema when 'Generate From JSON Example' is selected. |
| Schema | Manually defined JSON Schema specifying the structure of the extracted data. |
| Use Custom Body | Flag to indicate if a custom JSON body should be sent to the API instead of using the standard parameters. |
| Custom Body | Custom JSON body to send to the Agent Async endpoint, allowing full control over the request payload. |
| Request Options | Settings for batching, SSL validation, proxy, and timeout to control request behavior. |
Output
JSON
jobId- The ID of the job created for asynchronous processing, used for manual polling of results.
Dependencies
- Firecrawl API key credential
Troubleshooting
- Ensure the Firecrawl API key credential is correctly configured and has necessary permissions.
- If the job ID is not returned, verify that the prompt and URLs (if specified) are correctly formatted and valid.
- Timeout errors can occur if the API server is slow or unreachable; adjust the timeout setting in Request Options accordingly.
- If using a custom body, ensure the JSON is valid and matches the API's expected format.