New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]: Knowledge base addition does not work. #2411
Comments
Hey there @aomeng1219! 👋 I'm Dosu, your friendly neighborhood bot here to lend a hand with bugs, answer your queries, and help you dive into contributing while we wait for a human maintainer to swing by. I'll be taking a look at your issue about PDF files not adding to the knowledge base in quivr and get back to you with a full answer shortly. Hang tight! 🚀 |
Did PDF fail to produce text vector during import? |
Based on the information you've provided and the similar issues I found, it seems like the problem might be related to the state of the One possible cause could be a race condition where the question is asked before the document content is fully processed and stored. This could explain why the second question can get a normal response, as by that time the processing might have completed. To debug this, you could add some logging in the def upload_file_storage(file, file_identifier: str):
supabase_client: Client = get_supabase_client()
response = supabase_client.storage.from_("quivr").upload(file_identifier, file)
print(f"Upload response: {response}") # Add logging
return response
class DocumentSerializable(Document):
page_content: str
metadata: dict = Field(default_factory=dict)
def to_json(self) -> str:
return json.dumps({"page_content": self.page_content, "metadata": self.metadata})
@classmethod
def from_json(cls, json_str: str):
data = json.loads(json_str)
print(f"Data from JSON: {data}") # Add logging
return cls(page_content=data["page_content"], metadata=data["metadata"]) This should give you more information about what's happening when the document content is being processed. If the issue persists, it would be helpful to know the exact version of Quivr you're using, as well as any error messages you're seeing in the console or logs. This will help narrow down the possible causes of the issue. Regarding your question about the PDF files failing to produce a text vector during the import process, yes, this could indeed be the cause. The To resolve this issue, you could:
I hope this helps! If you have any other questions or need further clarification, please let me know. Sources
|
"Error loading punkt: <urlopen error [Errno 99] Cannot",I found the above error |
What happened?
Running process, and uploading PDF files are errors, but when looking for the contents of these files, the reply is always unknown. It seems that nothing has been added to the knowledge base.
Relevant log output
No response
Twitter / LinkedIn details
No response
The text was updated successfully, but these errors were encountered: