Adding a DOCX file to be extracted into chunks and added to the vector database, like the PDF's fails

shubham0204 / Android-Document-QA

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

Apache License 2.0

56 stars 6 forks source link

Adding a DOCX file to be extracted into chunks and added to the vector database, like the PDF's fails #14

Open dcrowleyMunster opened 6 days ago

dcrowleyMunster commented 6 days ago

Good afternoon,

Adding a PDF and asking questions of the PDF works very nicely, however when adding a DOCX (Word files), the UI seems to add the file however when a question is asked that includes text within the word file, the chatbot crashes

shubham0204 commented 5 days ago

@dcrowleyMunster I am not able to reproduce the issue with the steps you mentioned. It would be great if you can provide the crash logs from the 'Logcat' of Android Studio, if the test device is accessible to you.

dcrowleyMunster commented 5 days ago

Good Afternoon,

I was testing on the device itself with no connection to Android Studio. Later today I'll hook the device up to Android studio and run in debug mode and see what happens. If its the same behavior occurs I'll send the log files and whatever else I can find. If I can find the time I will just fix the issue, send the updated code for review and send an update.