Originally created by @fbirlik on GitHub (Mar 3, 2024).
Bug Report
Description
Bug Summary:
Rag/Web requests (#url..) have empty User-Agent header causing some web sites denying the request
Expected Behavior:
Either a fix User-Agent or random User-Agent to imitate a real browser
Note
langchain_community.WebBaseLoader class used to fetch web pages has support for generating fake user agents using fake_useragent package in default use case. Installing this package is enough to start generating user agents.
Originally created by @fbirlik on GitHub (Mar 3, 2024).
# Bug Report
## Description
**Bug Summary:**
Rag/Web requests (#url..) have empty User-Agent header causing some web sites denying the request
**Expected Behavior:**
Either a fix User-Agent or random User-Agent to imitate a real browser
## Note
langchain_community.WebBaseLoader class used to fetch web pages has support for generating fake user agents using fake_useragent package in default use case. Installing this package is enough to start generating user agents.
<img width="651" alt="Screenshot 2024-03-03 at 2 15 18 PM" src="https://github.com/open-webui/open-webui/assets/31392854/0afb4965-06b8-4251-bde0-7f6d287a373b">
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 @fbirlik on GitHub (Mar 3, 2024).
Bug Report
Description
Bug Summary:
Rag/Web requests (#url..) have empty User-Agent header causing some web sites denying the request
Expected Behavior:
Either a fix User-Agent or random User-Agent to imitate a real browser
Note
langchain_community.WebBaseLoader class used to fetch web pages has support for generating fake user agents using fake_useragent package in default use case. Installing this package is enough to start generating user agents.
@fbirlik commented on GitHub (Mar 3, 2024):
Following PR adds necessary package to requirements.txt. Tested with docker image
#1023