Maximum context length needs to be configurable

[evangineer]

When generating characters using gpt-3.5-turbo instead of gpt-4, I get the following error:

openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 4215 tokens. Please reduce the length of the messages.

[evangineer]

After a lot of pain, I solved the problem by switching to gpt-3.5-turbo-16k.

Clearly relates to #5 and having to work around the hardcoding of GPT-4 in parts.