[BUG] Cannot Join Iterable

[GoudaCouda]

Describe the bug I am getting the error "TypeError: can only join an iterable" when trying to create an article

To Reproduce

I ran the recomended Ollama Wiki example script.

Environment:

• I am on Windows using Bing Search API. I am using a secondary computer with ollama serve which used the model Macro-o1.

1. Input Topic: The effects of technology on children under the age of 5

Out Put Files

The Folder was just empty

Errors I am also getting these error but not sure if they are an issue

trafilatura.utils : ERROR : parsed tree length: 1, wrong data type or not valid HTML trafilatura.core : ERROR : empty HTML tree: None trafilatura.core : WARNING : discarding data: None trafilatura.utils : ERROR : parsed tree length: 1, wrong data type or not valid HTML trafilatura.core : ERROR : empty HTML tree: None trafilatura.core : WARNING : discarding data: None Error while requesting URL('https://community.thriveglobal.com/parenting-and-technology-how-to-raise-kids-in-the-digital-era/') - HTTPStatusError("Client error '403 Forbidden' for url 'https://community.thriveglobal.com/parenting-and-technology-how-to-raise-kids-in-the-digital-era/'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") Error while requesting URL('https://academic.oup.com/pch/article/28/3/184/7163632') - HTTPStatusError("Client error '403 Forbidden' for url 'https://academic.oup.com/pch/article/28/3/184/7163632'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") Error while requesting URL('https://pmc.ncbi.nlm.nih.gov/articles/PMC6326346/') - HTTPStatusError("Client error '403 Forbidden' for url 'https://pmc.ncbi.nlm.nih.gov/articles/PMC6326346/'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") Error while requesting URL('https://pmc.ncbi.nlm.nih.gov/articles/PMC10353947/') - HTTPStatusError("Client error '403 Forbidden' for url 'https://pmc.ncbi.nlm.nih.gov/articles/PMC10353947/'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") Error while requesting URL('https://pmc.ncbi.nlm.nih.gov/articles/PMC8078852/') - HTTPStatusError("Client error '403 Forbidden' for url 'https://pmc.ncbi.nlm.nih.gov/articles/PMC8078852/'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") Error while requesting URL('https://www.jpedhc.org/article/S0891-5245(21)00126-7/fulltext') - HTTPStatusError("Client error '403 Forbidden' for url 'https://www.jpedhc.org/article/S0891-5245(21)00126-7/fulltext'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403") trafilatura.utils : ERROR : parsed tree length: 1, wrong data type or not valid HTML trafilatura.core : ERROR : empty HTML tree: None trafilatura.core : WARNING : discarding data: None trafilatura.utils : ERROR : parsed tree length: 1, wrong data type or not valid HTML trafilatura.core : ERROR : empty HTML tree: None

[Yucheng-Jiang]

I am also getting these error but not sure if they are an issue these are issues of retrievers, not fatal errors

I would recommend add printing and assertion here to make sure inputs are all of str type.

[MrAnayDongre]

@GoudaCouda Just before the line that's causing the error you could add print(f"Debug: text variable: {text}, type: {type(text)}")

Additionally, check Ollama logs for any error messages or warnings.