I need to extract only the table from the following format invoice (JPG, JPEG, PNG, and PDF).
The columns are different for each file; I need to extract them dynamically.
Please suggest whether I can train the document in the AI center and what Extract I need to use for this scenario
Thanks in advance
Anil_G
(Anil Gorthi)
September 3, 2024, 7:24am
2
@Rudhresh_tamil
If you know all formats then you can train in ai center for each format and extract
else given an option better to go with generative extractor which can work with different types of formats
also there is a new docpath llm model which is better for table extractions can try that as well
Rudhresh_tamil:
I need to extract only the table from the following format invoice (JPG, JPEG, PNG, and PDF).
The columns are different for each file; I need to extract them dynamically.
Please suggest whether I can train the document in the AI center and what Extract I need to use for this scenario
Thanks in advance
@Rudhresh_tamil I agree with @Anil_G You can use UiPath AI Center to train a model for extracting tables dynamically, you can also try using OCR activities to extract text from images.