Add html parser for RAG and some improvements

[thinkall]

Why are these changes needed?

• Added a html parser to retrieve_utils (borrowed from browser_utils)
• Better handle save_path in get_file_from_url, won't break when save_path is a directory
• Better usage of get_file_from_url, won't break if url is a broken one
• Enable overlap in split_text_to_chunks, not exposed to RAG agent yet

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 53.84615% with 30 lines in your changes are missing coverage. Please review.

Project coverage is 50.06%. Comparing base (0d99d45) to head (97c42a6).

Files	Patch %	Lines
autogen/retrieve_utils.py	53.84%	24 Missing and 6 partials ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #2271       +/-   ##
===========================================
+ Coverage   38.39%   50.06%   +11.67%     
===========================================
  Files          78       78               
  Lines        7808     7859       +51     
  Branches     1669     1818      +149     
===========================================
+ Hits         2998     3935      +937     
+ Misses       4560     3593      -967     
- Partials      250      331       +81     

Flag	Coverage Δ
unittest	14.22% <0.00%> (?)
unittests	49.03% <53.84%> (+10.65%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[ekzhu]

In the future, I think we should consider sharing these utility functions across the core library rather than exclusively used by retrieval. For example, the parse HTML web pages can be built into a regular tool or user-defined function to be used by any ConversableAgent.

cc @gagb @jackgerrits