fix openai usage info for non-streaming response

[aniketmaurya]

What does this PR do?

Aggregate the usage_info for all the generations properly in case of non-streaming response.

In current main branch, UsageInfo for the following code will return completion tokens=1 which is incorrect and it should aggregate all the usage infos. This PR fixes that.

class OpenAIWithUsagePerToken(ls.LitAPI):
    def setup(self, device):
        self.model = None

    def predict(self, x):
        for i in range(1, 6):
            yield {
                "role": "assistant",
                "content": f"{i}",
                "prompt_tokens": 0,
                "completion_tokens": 1,
                "total_tokens": 1,
            }

Before submitting

• Was this discussed/agreed via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure to update the docs?
• Did you write any new necessary tests?

PR review

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in GitHub issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[codecov]

Codecov Report

Attention: Patch coverage is 50.00000% with 1 line in your changes missing coverage. Please review.

Project coverage is 92%. Comparing base (636c9fd) to head (af39d42).
Report is 1 commits behind head on main.

Additional details and impacted files

@@         Coverage Diff         @@
##           main   #399   +/-   ##
===================================
  Coverage    91%    92%           
===================================
  Files        25     25           
  Lines      1782   1783    +1     
===================================
+ Hits       1627   1632    +5     
+ Misses      155    151    -4