Bump llama-cpp-python to version 0.2.47

[Dedalo314]

Updating llama-cpp-python allows using the latest models' architectures, such as Gemma by Google.

What does this PR do?

Updates llama-cpp-python to use the latest open source models, such as Gemma by Google. An unused env variable, CUSTOM_GPTSTONKS_QA, is also removed.

Before submitting

• Did you make sure title is self-explanatory and the description concisely explains the PR?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you list all the breaking changes introduced by this pull request?
• Did you test your PR locally with pytest command?
• Did you run pre-commit hooks with pre-commit run -a command?

Did you have fun?

Make sure you had fun coding 🙃