Recombee RecommendNextItems
AI-generatedOverview
This node integrates with the Recombee recommendation service to fetch the next set of recommended items based on a previous recommendation ID. It is designed to handle batch processing and retries, making it suitable for workflows that require personalized item recommendations in bulk.
Common scenarios include:
- E-commerce platforms suggesting additional products after an initial recommendation.
- Content platforms recommending follow-up articles or videos.
- Any application needing to extend a recommendation chain dynamically.
For example, after receiving a list of recommended products from a prior step, this node can request the next set of recommendations tailored to each product, enabling deeper personalization.
Properties
| Name | Meaning |
|---|---|
| Recommendation ID | The ID of the previous recommendation to base the next recommendations on. |
| Count | The number of recommended items to return for each input item. |
| Timeout (Ms) | Request timeout in milliseconds for each API call to Recombee. |
| Max Retries | Number of retry attempts if a request to Recombee fails before throwing an error. |
Output
The node outputs an array of JSON objects, each corresponding to an input item processed. Each output object contains:
success: Boolean indicating if the recommendation request succeeded.recommId: The recommendation ID used for the request.count: The number of recommended items requested.data: The actual recommendation data returned by Recombee (structure depends on Recombee's API response).error(optional): Present only if the request failed, containing the error message.pairedItem(optional): Index of the input item related to the error when continuing on failure.
If the node encounters errors and is configured to continue on failure, it returns error details per item instead of stopping execution.
No binary data output is produced by this node.
Dependencies
- Requires an API key credential for authenticating with the Recombee service.
- Needs configuration of database ID, private token, and region for the Recombee API client.
- Uses the Recombee API client library bundled within the node.
Troubleshooting
- Timeouts: If requests take longer than expected, increase the "Timeout (Ms)" property or check network connectivity.
- Retries exhausted: If the node throws errors after retrying, verify the validity of credentials and the Recombee service status.
- Invalid Recommendation ID: Ensure the "Recommendation ID" corresponds to a valid previous recommendation; otherwise, the API may return errors.
- API quota limits: Excessive requests might be throttled by Recombee; consider reducing batch size or request frequency.
Common error messages will include the API error text. To resolve, check credentials, network access, and input parameters.