1. Data feed description
Easily import your useful content using a CSV file.
This format, structured in two columns:
-
question: a question or topic -
answer: the answer, the associated content
A sample CSV file is available from this link.
You can choose to import a local file or specify a URL to retrieve data online, facilitating regular updates. When using a URL, an automatic daily update is scheduled at 3:00 AM GMT.
NB: When importing your CSV file (via URL or local file), a preliminary check is now performed on the first 10,000 rows of the file.
This allows potential errors to be detected immediately before starting the full ingestion. This change makes the process smoother, especially for large files.
2. Assistance in creating the knowledge source
To import your data efficiently
- Start by specifying a clear name for your knowledge source to facilitate its management.
- Ensure that your file is accessible online via a URL or available locally on your device. If the URL requires authentication, add the necessary information in the headers.
- If your file does not follow the standard CSV format, adjust the field separator (comma, semicolon, etc.). Labels that comply with standard conventions enable automatic field mapping.
- Make sure to fill in the mandatory columns to ensure the correct creation of your catalog.
- Once the content is verified and the fields are configured, confirm the settings and save to start the import process.
3. Error management
In case of an error, an explanatory message will indicate the cause of the issue.
The most common errors are as follows:
- Incorrect separator: The specified separator does not match the file format.
- CSV format not followed: Some rows do not have the same number of columns. Each row must include a fixed number of columns, even if some are empty.
- Non-compliant encoding: The file is not encoded in UTF-8.
⚠ Make sure to check these points to avoid any issues during the import process!