AlessandroSpallina / ccat-dietician

Prevent multiple unnecessary ingestions of the same file if it's unchanged. Support declarative memory update when a document changes; simply re-upload the document. Dietician is your friend!

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

KeyError 'source' when uploading a .csv

AlessandroSpallina opened this issue · comments

Describe the bug
When uploading a CSV file I see the following logs:

cheshire_cat_core           | [2024-01-23 09:24:08.862] ERROR  cat.mad_hatter.mad_hatter.MadHatter.execute_hook::263 => 'Error in plugin ccat_dietician::before_rabbithole_splits_text'
cheshire_cat_core           | [2024-01-23 09:24:08.869] ERROR  cat.mad_hatter.mad_hatter.MadHatter.execute_hook::264 => KeyError('source')
cheshire_cat_core           | [2024-01-23 09:24:08.877] WARNING cat.mad_hatter.mad_hatter.MadHatter.execute_hook::266 => ('To resolve any problem related to Dietician plugin, contact the creator '
cheshire_cat_core           | [2024-01-23 09:24:08.877] WARNING cat.mad_hatter.mad_hatter.MadHatter.execute_hook::266 => 'using github issue at the link '
cheshire_cat_core           | [2024-01-23 09:24:08.877] WARNING cat.mad_hatter.mad_hatter.MadHatter.execute_hook::266 => 'https://github.com/AlessandroSpallina/ccat-dietician')
cheshire_cat_core           | Traceback (most recent call last):
cheshire_cat_core           |   File "/app/cat/mad_hatter/mad_hatter.py", line 254, in execute_hook
cheshire_cat_core           |     tea_spoon = hook.function(
cheshire_cat_core           |   File "/app/cat/plugins/ccat_dietician/dietician.py", line 66, in before_rabbithole_splits_text
cheshire_cat_core           |     'name': doc[0].metadata['source'],
cheshire_cat_core           | KeyError: 'source'

Activated Plugins

  • Ingest Anything
  • Dietician