Azure Document Loader

Facilitates access to and analysis of documents stored in Azure.

Detailed Explanation

1. Name:

   • This field allows you to assign a specific name to your document source, helping you identify it in your project.

   • Example: You might name it "Monthly Report" if the documents you're loading pertain to monthly performance reports.

2. File(s):

   • This section allows you to select one or more files from your local system. It supports various file types including:

     • PDF

     • JPEG, JPG, PNG, BMP

     • TIFF, HEIF

     • DOCX, XLSX, PPTX

     • HTML

   • Example: If you have a report in PDF format and an Excel spreadsheet, you can upload both by dragging them into this area.

3. Chunk Size:

   • This field specifies the number of tokens or characters in each chunk of data. The default is 1024, but it can be adjusted to suit your needs. This is particularly useful for managing large documents during processing.

   • Example: If you're working with a very large PDF document, you might set the chunk size to 512 for easier handling.

4. Cost Information:

   • The connector provides information regarding the cost associated with importing words from the specified documents.

   • Example: If it states "Cost per words: 7 tokens" and "Remaining words: 6399701 Words", this indicates how many tokens will be charged for each word processed and the number of words remaining for processing.