You can upload new documents by clicking the Upload button and selecting files from your local system.
Maximum file size: 100 MB
Maximum text content: 2000000 characters
Direct upload: TXT, CSV
Other formats: BMP, DOC, DOCX, EML, EPUB, HEIC, HTML, JPEG, PNG, MD, MSG, ODT, ORG, P7S, PDF, PNG, PPT, PPTX, RST, RTF, TIFF, TSV, XLS, XLSX, XML
For unsupported formats, convert them to TXT or CSV using document processing tools before uploading.
After uploading, select the file(s) you want to analyze and click on the Analyze button. For the CSV file, a configuration window will appear with two steps:
Select ID column, which contains unique record identifiers.
Select the text column, which contains the content to be analyzed. The text content cannot exceed 20,100 characters.
Once your files are analyzed, you can build your RAG model.
Choose one or more analyzed files.
Click Build graph model to proceed.
Enter a model name in the dialog box and click Create.
Each file has a Status column to indicate processing progress:
Uploaded - the file is added but not analyzed yet.
Analyzed - the file has been processed and is ready to be used in RAG model creation.
Each file entry includes a three-dot menu (...) with additional options:
Analyze - re-runs analysis if needed (currently this option is disabled for already analyzed files).
Details - displays file metadata such as creation and analysis date, file size and content preview.
Delete - permanently removes the file.
Edit Tags - here you can assign or create tags to make file filtering easier (tags appear in the Tags column).
Smabbler Portal is integrated with for automatic document processing. If you upload a file that is not in TXT or CSV format, a pop-up window will appear where you can enter your Unstructured IO API key and URL. The system will then convert your file via API before processing.
Your model is now ready for activation in the tab.