[Question]: Issue while using csv with 1000 rows and 12 columns

[saineshwar]

Describe your problem

Output

Data in .csv file

Download file to test - customers-1000.csv

[KevinHuSh]

And the issue is ...?

[saineshwar]

And the issue is ...?

1. It is showing headers of csv file in answer.
2. Data is not formatted

[yingfeng]

Choose Table as the parsing template, then I've got the above result. Forget about the Chinese characters got by LLMs.

One issue is that, the embedding process is pretty long. Since there are 1000 lines in the csv file, and each line will be sent to embedding model. We'll improve such strategy to enlarge the batch for Table like data.

[saineshwar]

Choose Table as the parsing template, then I've got the above result. Forget about the Chinese characters got by LLMs. One issue is that, the embedding process is pretty long. Since there are 1000 lines in the csv file, and each line will be sent to embedding model. We'll improve such strategy to enlarge the batch for Table like data.

Which embedding and LLM have you used for testing it.

[yingfeng]

It does not relate to the LLM/embedding closely. The key issue is you should choose Table instead of default General as the file parser template

[saineshwar]

It does not relate to the LLM/embedding closely. The key issue is you should choose Table instead of default General as the file parser template

Know i have chosen table only.

[yingfeng]

You could try to adjust the prompt. By default, demo adopts deepseek.

[saineshwar]

You could try to adjust the prompt. By default, demo adopts deepseek.

@yingfeng any example can you share please. I am using llama 3.1 as LLM