You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Have run the package from main branch and created a bot with PDF documents. There are three nodes shown as references for the answers but they are empty and not showing the part of PDF as source/reference (Screenshot attached)
The text was updated successfully, but these errors were encountered:
Thanks @mohdamir. This should only happen if you're using a Typescript backend, but not with Python. The reason is that Typescript is not adding any file metadata; I added a patch for this (run-llama/LlamaIndexTS#758), which will be released with the next LlamaIndexTS version.
Meanwhile, if you're using a Typescript backend, I filter out source nodes without metadata, see 8b81b17
Have run the package from main branch and created a bot with PDF documents. There are three nodes shown as references for the answers but they are empty and not showing the part of PDF as source/reference (Screenshot attached)
The text was updated successfully, but these errors were encountered: