URLs
Last updated
Last updated
URLs can be added to the group by selecting the "Upload new file" button and selecting "URLs" from the drop down menu.
After clicking on "URLs" you will have this screen with two choices.
If you click on the right button this brings up the "Crawl website sitemap" dialog box.
If you click on the left button this brings up the "Add individual URLs" dialog box.
You can assign the article to one or more groups by expanding the "Save to groups" dropdown and selecting the relevant vector group.
Chunking settings can be modified as required.
| Settings Name | Description |
|---|---|
Chunking Method | Specifies the strategy used to divide the dataset into smaller, manageable chunks or partitions. Available Options: - Letter - Word - Sentence - Passage |
Chunk Size | Specifies the chunk size when performing a semantic search. A larger chunk size can have more context, but then the tradeoff is loss of specificity in the answer. With larger chunks, you have less of them, and therefore less total database vectors to search and to score against your comparison input. Permitted Range: 0 - 4500 |
Chunk Overlap | Specifies the degree of redundancy or overlap between chunks of data stored within the vector database. A chunk in this context typically refers to a segment or partition of the overall dataset. Permitted Range: 0 - 4500 |
URLs can be uploaded manually or you can import from a templace file.
To upload a list of URLs click on
Download the URL template file by clicking on the "Template" button.
Open the file using any text editor of your choice.
Insert the desired URLs, each on a new line, without any additional text or characters and save the file. For example:
Click on the "Upload" button and select your saved file.
After selecting your saved file, you will see a new entry for each URL will be displayed.
URLs can be added manually by entering the URL in the edit field. If you need to enter more URLs then you can click the "Add another link" button.
