Fix: Make OpenAIEmbedding work when token usage info is not set

[aniketmaurya]

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?

What does this PR do?

OpenAIEmbeddingSpec requires to set token usage in the context otherwise it fails with the following example. This PR, makes it work and set usage to 0 when not provided.

Error

  File "/Users/aniket/Projects/github/LitServe/src/litserve/api.py", line 90, in encode_response
    return self._spec.encode_response(output, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/aniket/Projects/github/LitServe/src/litserve/specs/openai_embedding.py", line 128, in encode_response
    "prompt_tokens": context_kwargs.get("prompt_tokens", 0),
                     ^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'get'

Code

import litserve as ls
from sentence_transformers import SentenceTransformer

class EmbeddingsAPI(ls.LitAPI):
    def setup(self, device):
        self.model = SentenceTransformer('all-MiniLM-L6-v2', device=device)

    def predict(self, inputs):
        embeddings = self.model.encode(inputs)
        return embeddings

if __name__ == "__main__":
    api = EmbeddingsAPI()
    server = ls.LitServer(api, spec=ls.OpenAIEmbeddingSpec())
    server.run(port=8000)

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 2 lines in your changes missing coverage. Please review.

Project coverage is 94%. Comparing base (771a1c9) to head (d1f56ed).
Report is 1 commits behind head on main.

Additional details and impacted files

@@         Coverage Diff         @@
##           main   #369   +/-   ##
===================================
- Coverage    94%    94%   -0%     
===================================
  Files        25     25           
  Lines      1563   1564    +1     
===================================
  Hits       1465   1465           
- Misses       98     99    +1