mem0 icon indicating copy to clipboard operation
mem0 copied to clipboard

[Bug]: docx loader erroring out when trying to add docx files

Open legaltextai opened this issue 2 years ago • 2 comments

🐛 Describe the bug

    333 app_id = self.config.id if self.config is not None else None
    335 # Create chunks
--> 336 embeddings_data = chunker.create_chunks(loader, src, app_id=app_id)
    337 # spread chunking results
    338 documents = embeddings_data["documents"]

File [~/Downloads/autogen/lib/python3.11/site-packages/embedchain/chunkers/base_chunker.py:26](https://file+.vscode-resource.vscode-cdn.net/Users/home/Downloads/~/Downloads/autogen/lib/python3.11/site-packages/embedchain/chunkers/base_chunker.py:26), in BaseChunker.create_chunks(self, loader, src, app_id)
     24 chunk_ids = []
...
-> 1369     raise BadZipFile("File is not a zip file")
   1370 if self.debug > 1:
   1371     print(endrec)

BadZipFile: File is not a zip file```

legaltextai avatar Oct 23 '23 13:10 legaltextai

@legaltextai Can you provide more information? What is the line of code that is throwing the error, what are you trying to achieve and the source url you are trying to add (if possible)?

deven298 avatar Oct 25 '23 15:10 deven298

Can confirm this issue. I was able to reproduce this on my side.

deshraj avatar Oct 25 '23 17:10 deshraj