Chatbot Data Source

The Data Source is the centralised hub of information that empowers your Virtual Assistant to provide precise and valuable information to your visitors. The virtual assistant can deliver accurate responses and offer relevant suggestions by uploading your data.

📘

Reminder of Roles & Permissions

Only an Aministrator or any custom role with permission of Manage Destination is allowed to add, view, edit, download and delete the data source.

Add Data Source

To add a data source:

• Navigate to Administration > Tools & Settings > Data Source.
• Click the Add Data Source button at the top right-hand corner of the Data Source page.

 

• Enter the name of the data source you are creating into the panel on the right-hand side of the page.
• Enter the data source instruction.

📘

The Data Source Name must be unique.

You can select one of the data source types: CSV, PDF, URL or Markdown File.

 

CSV

• Select CSV as the data source type.
• Upload the CSV file to CINNOX by dragging and dropping it or by clicking Browse to search for the CSV file.
• Click Re-upload to re-upload an updated CSV file.

Here is the sample CSV file (Table 1) with not less than 20 MB using 1 language; all text is readable and not encrypted, fewer than 20,000 rows, and each column has a title.

In this sample data source:

• ProductID is a unique identifier for each product.
• ProductName provides the name of the product.
• Category specifies the category to which the product belongs (e.g., Electronics, Fashion, Home & Kitchen).
• Description offers a brief description of the product.
• Price is the price of the produce.
• Brand is the brand or manufacturer of the product.
• Rating represents the product's average user rating on a scale of 1 to 5.

📘

CSV File Data Source Reminder

• The maximum file size is 20 MB.
• Using UTF-8 as a file format for CSV is recommended.
• CSV files are limited to 20,000 rows. Scrapping will fail if it exceeds this limit.
• One language per data source is recommended.
• Images or multiple text columns won't be scraped.
• Encryption or password-protected files are not supported.
• For accurate parsing, provide a title for each column in the CSV file.
• Actual file size may vary slightly due to calculations.

 

PDF

• Select PDF as the data source type.
• Upload the PDF file to CINNOX by dragging and dropping it or by clicking Browse to search for the PDF file.
• You can click Re-upload to re-upload the updated PDF file.

📘

PDF File Data Source Reminder

• The maximum file size is 20 MB.
• One language per data source is recommended.
• Images or multiple text columns won't be scraped.
• Encryption or password-protected files are not supported.
• Actual file size may vary slightly due to calculations.

 

URL

• Select URL as the data source type.
• Enter the URL.

📘

URL Data Source Reminder

• Include the protocol, domain, and path (if applicable) for the URL format. To effectively narrow down the data scope, it is recommended to specify the path in the following format: https://docs.example.com/docs.
• The data source will include only the data under this specific domain and path. The data from other domains or different paths will be excluded.
• One language per data source is recommended.
• Images or multiple text columns won't be scraped.
• Use a valid public URL. For private sites, export to PDF or MD files instead.
• A server error or anti-crawling may lead to a failed status during data processing.

 

Markdown File

• Select Markdown File as the data source type.
• Upload the Markdown file to CINNOX by dragging and dropping it or by clicking Browse to search for the Markdown file.
• You can click Re-upload to re-upload the updated Markdown file.

📘

Markdown Data Source Reminder

• You can create a markdown file using any text editor or Notepad and save it with a .md extension.
• The maximum file size is 20 MB.
• One language per data source is recommended.
• Images or multiple text columns won't be scraped.
• Actual file size may vary slightly due to calculations.
• Encryption or password-protected files are not supported.

 

• Click Confirm at the bottom right-hand side of the panel.
• Once you successfully upload the source file or enter the URL, the list shows you the processing status of the uploaded data source. If it is ready, you can use it as the data source.
• CINNOX Q&A Bot is one of our tools required to use the uploaded Data Source. Please refer to the CINNOX Q&A Bot page for details on using the Data Source.

 

Data Source Status

The table below shows the status and descriptions of the uploaded data source.

📘

• You can only use a data source for your chatbot with a status = "Ready".
• When the data source is successfully processed or failed to process, you will receive a notification message from the CINNOX Bot.
• If the data source status is "Failed", agents should review the reason for the failure and edit the data source file accordingly.

 

View Data Source Details

• Click More(...) at the right-hand side of the data source.
• Select View.

• You can check the Source Name, Instruction and AI Engine on the panel at the right-hand side of the page.
• You can click Edit

 

Edit Data Source

• Click More(...) at the right-hand side of the data source.
• Select Edit.

 

• Edit the Source Name or the Description.
• Click OK.

 

Download Data Source

• Click More(...) at the right-hand side of the data source.
• Select Download. The data source file is downloaded and saved on your local device.

📘

Reminder

Only PDF, CSV, and Markdown file types of data sources are downloadable in any status.

 

Delete Data Source

• Click More(...) at the right-hand side of the data source required to delete.
• Select Delete.

 

• Click Delete.
• The required data source is deleted, and the list no longer shows this deleted data source.

📘

You cannot delete a data source if your chatbot is using it. Remove it from the chatbot - data source first, then try again.

 

Creating Q&A Bot

📘

Please refer to CINNOX Q&A Bot Configuration for the Detailed Guide of Q&A Bot creation.