Hello!
I seem to have a problem and I don't know where is the problem...
When I run the readme everything checks out, the pdf of naval is readed and chunked... however whenever I use one of my pdfs it seems I get this error saying that there is no data
The pdf is here https://evi.ams3.cdn.digitaloceanspaces.com/CHATPOC/job_example.pdf
It is a pdf that I created from a google docs file so I know for a fact that is not an scanned copy or whatever, it should be able to read...
Can you post the exact error?
Yes, here it is...
File "C:\MAMP\htdocs\embedchain\index.py", line 9, in
chat_poc.add("pdf_file", "https://evi.ams3.cdn.digitaloceanspaces.com/CHATPOC/job_example.pdf")
File "C:\Users\mocte\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\embedchain\embedchain.py", line 94, in add
self.load_and_embed(loader, chunker, url)
File "C:\Users\mocte\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\embedchain\embedchain.py", line 118, in load_and_embed
embeddings_data = chunker.create_chunks(loader, url)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mocte\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\embedchain\chunkers\base_chunker.py", line 11, in create_chunks
datas = loader.load_data(url)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mocte\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\embedchain\loaders\pdf_file.py", line 13, in load_data
raise ValueError("No data found")
ValueError: No data found
What I can tell from the error is that it seems that is unable to load the document and therefore unable to load any data... which is odd since I can access the pdf file no problem
Checked this issue now. Its still occuring.
Hi @kpatron Can you share the PDF link again, the previously shared URL is not working anymore.
ya. i tested cant read too