Fix AI test failures & do not run graphqlmaster tests

[hmstepanek]

Overview

Fix the following AI test failures:

• Bedrock changed the order of payload assertions in commit: boto/botocore@db41663 which resulted in the expected error being different due to the validator order change.
• Langchain added metadata to Document interface so update expected events with this field.
• pydantic ValidationError moved locations so adjust the path to the error in the tests.
• Langchain doesn't list support for Python3.8 so do not test it on Python3.8.
• Graphql main tests are failing so comment these out for now.

[github-actions]

🦙 MegaLinter status: ✅ SUCCESS

Descriptor	Linter	Files	Fixed	Errors	Elapsed time
✅ PYTHON	black	3	0	0	1.22s
✅ PYTHON	flake8	3		0	0.51s
✅ PYTHON	isort	3	0	0	0.22s
✅ PYTHON	pylint	3		0	4.23s

See detailed report in MegaLinter reports
Set VALIDATE_ALL_CODEBASE: true in mega-linter.yml to validate all sources, not only the diff

MegaLinter is graciously provided by

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 81.59%. Comparing base (d642980) to head (7e19ad8).

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1211      +/-   ##
==========================================
+ Coverage   80.05%   81.59%   +1.54%     
==========================================
  Files         197      197              
  Lines       21803    21803              
  Branches     3807     3807              
==========================================
+ Hits        17454    17790     +336     
+ Misses       3239     2897     -342     
- Partials     1110     1116       +6     

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

[umaannamalai]

Approving - independent of LangChain test failures

[hmstepanek]

@umaannamalai Would you mind giving this another review? I've added a couple additional fixes for langchain and graphql tests.