fix: "Failed to stream message: p is not a function" with custom OpenAI-compatible provider#3313
Open
entrusc wants to merge 2 commits into
Open
fix: "Failed to stream message: p is not a function" with custom OpenAI-compatible provider#3313entrusc wants to merge 2 commits into
entrusc wants to merge 2 commits into
Conversation
entrusc
force-pushed
the
FIX/p-not-a-function
branch
from
a791497 to
80c33fe
Compare
entrusc
changed the title
…sing custom provider in web mode
…rovider is selected
entrusc
force-pushed
the
FIX/p-not-a-function
branch
from
80c33fe to
6763460
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I ran into an issue with the docker version of Mux and custom OpenAI-compatible providers (in my case LiteLLM). Instead of any response from the LLM I got "Failed to stream message: p is not a function". After some AI assisted investigation I was able to get the issue fixed.
Apparently the problem is a library that gets only loaded on demand but that is not bundled in the minified version. I included it statically and added a script that collects all transitive dependencies and copies them to the production build. I also fixed a small issue with name generation for a workspace - that also did not work as expected with custom providers.