You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I see that you have downgraded the version of numpy, which actually benefits me as I was having incompatibility versions between pipecat and langchain.
However, I wonder if there was any compromise in performance by doing that...
Also, as I have noted here in langchain: langchain-ai/langchain#29319
They have included in their imports by some reason two constraints to numpy, where one of them restricts the lib to be under version 2 and the other allows it. This was what was causing my issue.
Not sure why was the reason for the downgrade of the numpy, but thought it would be good to share this piece with you.
Thanks!
The text was updated successfully, but these errors were encountered:
I was having incompatibility versions between pipecat and langchain.
Many people were having issues like this, with langchain and other services. It seems that support for numpy >2 is not broad enough to warrant an upgrade. That's the reason.
You can see some discussion in these issues: #913, #914. There was more discussion about this in Discord.
Hi,
I see that you have downgraded the version of numpy, which actually benefits me as I was having incompatibility versions between pipecat and langchain.
However, I wonder if there was any compromise in performance by doing that...
Also, as I have noted here in langchain: langchain-ai/langchain#29319
They have included in their imports by some reason two constraints to numpy, where one of them restricts the lib to be under version 2 and the other allows it. This was what was causing my issue.
Not sure why was the reason for the downgrade of the numpy, but thought it would be good to share this piece with you.
Thanks!
The text was updated successfully, but these errors were encountered: