Exclude the ".txt" extension while adding text to vector DB via create_by_text API #6954
Closed
5 tasks done
Labels
📚 feat:datasource
Data sources like web, Notion, Logseq, Lark, Docs
Self Checks
1. Is this request related to a challenge you're experiencing? Tell me about your story.
While adding text to a vector DB via create_by_text API, the file name of document is suffixed with the .txt extension even though the document is comprised of text extracted from web or YouTube's transcrips. For example, a YouTube URL is referenced as "https://youtu.be/Xkm3-thqgXc.txt". Since the file name is used in "Citations and Attributions", showing "https://youtu.be/Xkm3-thqgXc.txt" does not make sense. It should be referenced as "https://youtu.be/Xkm3-thqgXc" without the extension.
2. Additional context or comments
No response
3. Can you help us with this feature?
The text was updated successfully, but these errors were encountered: