Add CSV-Files to the knowledge base

Besides PDF, URL, Documents and Question-Answer-Pairs, CSV-Files can be added as resources to the knowledge base.

A CSV file describes a table that has a fixed structure. The title line describes the information/data contained in the individual columns. It is mandatory and it is recommended to name the columns as precisely as possible. 

The title of a column must be unique to enable correct assignments.

When importing the CSV file, it is possible to define which column titles are to be imported. By default, the entire table is imported. By deselecting the unimportant titles, parts of the table are excluded. 

The title columns describe the part that users are most likely to ask about. The columns to be imported describe the data columns that the AI accesses in order to answer queries. 
The greater the number of imported columns, the greater the potential for inaccurate or incorrect answers. 
It is recommended to use CSV files in specific intents and not just in the general knowledge base. Experience shows that the potential for errors is lower when included in specific intents, recognition is increased and the general quality of the answers is higher.

The usage of the semicolon (;) as a separator is recommended. 

Further sources for errors regarding the CSV-Import may be: 

• To many rows are imported or the text within the columns is to long: A great amount of imported rows or very long texts within the individual columns may lead to an incomplete import of the rows information. To add longer informational texts into the Knowledgebase Websites or articles should be used.
• Separator could not be recognized: If the separator used cannot be clearly identified, this can cause the import to fail. We therefore recommend using the semicolon (;) as a separator to avoid potential problems. 
• CSV is not well formed: The CSV file must be formatted correctly, i.e. each row should contain the same number of columns. Inconsistent line lengths can lead to the import not being carried out correctly.
• Separator not properly escaped: If the separator occurs within a column (e.g. in a text field), it must be properly escaped. Otherwise, incorrect column structures may occur that hinder the import.