Issue with Ingesting/Upserting CSV File in opengpts-backend
thierryteisseire opened this issue · comments
Running last version clean from git pull on Ubuntu 20.
![Screenshot 2024-04-16 184003](https://private-user-images.githubusercontent.com/77529835/322929755-143670f9-de82-4bb5-8e53-1a811fc204c4.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.CwiecNqNp1xR8J2liLzUmUFEwS1yx3xfAutDkE6sXao)
Description:
I am currently running the latest version of opengpts-backend after a clean git pull on Ubuntu 20. However, I am encountering an issue where I am unable to ingest/upsert a CSV file. The error message I am receiving is as follows:
File "/backend/app/ingest.py", line 45, in ingest_blob
for document in parser.lazy_parse(blob):
File "/usr/local/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/generic.py", line 70, in lazy_parse
raise ValueError(f"Unsupported mime type: {mimetype}")
ValueError: Unsupported mime type: text/csv
I have attached a screenshot for reference: Screenshot
I am seeking assistance in understanding why CSV files are not allowed for ingestion in opengpts-backend. Any insights or guidance on resolving this issue would be greatly appreciated.
I realised we do not cover csv upserting.