We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hi I am running into this issue having updated to ollama 0.4.0
I fixed it by adding an escape_markdown func
def escape_markdown(text): escape_chars = r'_*~`>#+-=|{}.!' return re.sub(r'([%s])' % re.escape(escape_chars), r'\\1', text)
And then escaping all the MARKDOWN responses.
I also ensured the markdown responses are now: ParseMode.MARKDOWN_V2 instead of the deprecated MARKDOWN, I left the ParseMode.HTML alone.
I'm still testing the fixes if I can still reproduce the error, if I can't should I submit a PR for the fixes?
The text was updated successfully, but these errors were encountered:
+1 when responses has markdown in them...
Sorry, something went wrong.
No branches or pull requests
Hi I am running into this issue having updated to ollama 0.4.0
I fixed it by adding an escape_markdown func
def escape_markdown(text):
escape_chars = r'_*~`>#+-=|{}.!'
return re.sub(r'([%s])' % re.escape(escape_chars), r'\\1', text)
And then escaping all the MARKDOWN responses.
I also ensured the markdown responses are now: ParseMode.MARKDOWN_V2 instead of the deprecated MARKDOWN, I left the ParseMode.HTML alone.
I'm still testing the fixes if I can still reproduce the error, if I can't should I submit a PR for the fixes?
The text was updated successfully, but these errors were encountered: