🐛 [BUG] - LLM timeout causing Message passing to fail #35
Labels
bug
Something isn't working
gpt-engine
Everything about the GPTEngine
help wanted
Extra attention is needed
Description
In docFiller, we use API calls to interact with the language model (LLM). However, with web extensions using Manifest V3, direct API calls from content scripts are not allowed. Instead, content scripts need to communicate with a background service worker. The background worker listens for these messages, performs the API calls, and then sends the responses back to the content script.
A challenge arises when these API calls take a significant amount of time, especially with local Ollama models. This can result in errors due to message channels closing prematurely.
For more details on handling messaging between content scripts and background workers, see the Chrome documentation on content scripts, message passing, and background workers.
If you encounter issues with long-running tasks and message channels, check the Managing long-lived connections documentation.
Reproduction URL
https://github.com/rootCircle/docFiller
Reproduction steps
Screenshots
Logs
Browsers
Firefox
OS
Linux
The text was updated successfully, but these errors were encountered: