# Loading Prodigy output back into Prodigy **URL:** \ **Category:** Uncategorized\ **Tags:** ner\ **Created:** [May 17, 2023, 6:33pm UTC](https://support.prodi.gy/t/loading-prodigy-output-back-into-prodigy/6551 "2023-05-17T18:33:05Z")\ **Posts on this page:** 1\ **Showing post:** 4
**Author:** ![ryanwesslen](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ryanwesslen/32/2969_2.png) [@ryanwesslen](https://support.prodi.gy/u/ryanwesslen)\ **Post date:** [May 17, 2023, 9:15pm UTC](https://support.prodi.gy/t/loading-prodigy-output-back-into-prodigy/6551/4 "2023-05-17T21:15:07Z")
Hm... that's weird. Typically, that error has sometimes been a formatting or something that needed restart: > [@Testing add\_tokens](https://support.prodi.gy/t/testing-add-tokens/628/3): > > Thanks! I copied the code exactly from [here](https://support.prodi.gy/t/valueerror-mismatched-tokenization-in-ner-make-gold/292), but adding the brackets solved it! > [@Uploading a dataset of images](https://support.prodi.gy/t/uploading-a-dataset-of-images/1685/6): > > Thanks! And I think I found the problem: Before you’re returning pic\_json, you’re calling json.dumps on it, which turns it into a string. However, examples added to the database are expected to be just a regular list of dictionaries. So you can drop that line slightly_smiling_face I also just noticed that add\_examples currently expects the examples to already have hashes set (an "\_input\_hash" representing the input data, e.g. the image, and a "\_task\_hash" representing the specific question, … > [@Spancat training from db-in'd dataset not working](https://support.prodi.gy/t/spancat-training-from-db-ind-dataset-not-working/5530/9): > > Sorry for the delay - just coming back to this project. For some reason this is working now. I can only think that for some reason restarting my machine since I was last trying this has made a difference. Sorry I can't find a better explanation sweat_smile Thanks for your help, really appreciated pray I'm a bit surprised that you saw the same issue with `dataset:`. I'd suggest to run that process on (say) the first 10 records. Does it run? If so, then this makes it seem like it's not a systematic issue and instead only affects a few records. If it doesn't run, then perhaps try the last 10 records or randomly take a few rows. Sorry this is a bit of a trial-and-error but the goal is to figure out if this is an issue with all of the records or only some/certain records. I've done this in the past where I didn't realize there was some a minor data issue with a few sparsely populated records. If you do find it's with only some records, then try to find an example of it and understand why. This is a bit of a challenge without a fully reproducible example (completely understand you can't provide due to data privacy). If possible, if you could create 1 similar dummy, ready-to-go `.jsonl` that will help me a ton because then I can reproduce it. Also, provide what are the exact commands if possible. --- _[View the full topic](https://support.prodi.gy/t/loading-prodigy-output-back-into-prodigy/6551)._