Evals

[Shuyib]

This pull request includes several changes to the Makefile, README.md, and new test files to improve the project's testing capabilities and documentation. The most important changes include the addition of test commands in the Makefile, updates to the README.md to include testing guidelines and responsible AI practices, and the creation of unit and integration test files.

Makefile updates:

• Added tests/*.py to the format target to ensure test files are also formatted.
• Added a command to remove the tests/__pycache__ directory in the clean target.
• Introduced a new test target to run tests using pytest.

Documentation updates:

• Added a description of the tests directory and its contents in the README.md.
• Included instructions for setting test-related environment variables in the README.md. [1] [2]
• Added sections on responsible AI practices and testing guidelines in the README.md. [1] [2]

New test files:

• Created tests/test_cases.py with unit tests for the function calling utilities, including tests for sending airtime, sending messages, and searching news.
• Created tests/test_run.py with integration tests for the function calling system, including various scenarios and edge cases.