Originally created by @tth37 on GitHub (Apr 11, 2025).
Check Existing Issues
I have searched the existing issues and discussions.
Problem Description
Currently, users can configure the RAG_WEB_SEARCH_ENGINE (e.g., DuckDuckGo, Google) directly from the Open WebUI frontend settings. However, the related configuration RAG_WEB_LOADER_ENGINE, which controls the method used to fetch and parse web page content for RAG, appears to only be configurable via environment variables or backend configuration (on latest main branch). This makes it less convenient to switch or experiment with different loading mechanisms compared to the search engine setting.
Desired Solution you'd like
I propose adding a setting in the Open WebUI frontend (perhaps in the "Settings" -> "Web Search" section, near the Web Search Engine selector) that allows users to select the desired RAG_WEB_LOADER_ENGINE. This could be a dropdown menu listing the available loader engines supported by the backend.
Alternatives Considered
No response
Additional Context
No response
Originally created by @tth37 on GitHub (Apr 11, 2025).
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
Currently, users can configure the `RAG_WEB_SEARCH_ENGINE` (e.g., DuckDuckGo, Google) directly from the Open WebUI frontend settings. However, the related configuration `RAG_WEB_LOADER_ENGINE`, which controls the method used to fetch and parse web page content for RAG, appears to only be configurable via environment variables or backend configuration (on latest main branch). This makes it less convenient to switch or experiment with different loading mechanisms compared to the search engine setting.
### Desired Solution you'd like
I propose adding a setting in the Open WebUI frontend (perhaps in the "Settings" -> "Web Search" section, near the Web Search Engine selector) that allows users to select the desired `RAG_WEB_LOADER_ENGINE`. This could be a dropdown menu listing the available loader engines supported by the backend.
### Alternatives Considered
_No response_
### Additional Context
_No response_
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @tth37 on GitHub (Apr 11, 2025).
Check Existing Issues
Problem Description
Currently, users can configure the
RAG_WEB_SEARCH_ENGINE(e.g., DuckDuckGo, Google) directly from the Open WebUI frontend settings. However, the related configurationRAG_WEB_LOADER_ENGINE, which controls the method used to fetch and parse web page content for RAG, appears to only be configurable via environment variables or backend configuration (on latest main branch). This makes it less convenient to switch or experiment with different loading mechanisms compared to the search engine setting.Desired Solution you'd like
I propose adding a setting in the Open WebUI frontend (perhaps in the "Settings" -> "Web Search" section, near the Web Search Engine selector) that allows users to select the desired
RAG_WEB_LOADER_ENGINE. This could be a dropdown menu listing the available loader engines supported by the backend.Alternatives Considered
No response
Additional Context
No response