openai:compatible with other llm usage meta data

[omgbbq]

• PR message:

  • Description: Compatible with other llm (eg: deepseek-chat, glm-4) usage meta data
  • Issue: N/A
  • Dependencies: no new dependencies added

• Add tests and docs:
  libs/partners/openai/tests/unit_tests/chat_models/test_base.py

cd libs/partners/openai
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_openai_astream
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_openai_stream
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_deepseek_astream
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_deepseek_stream
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_glm4_astream
poetry run pytest tests/unit_tests/chat_models/test_base.py::test_glm4_stream

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Aug 23, 2024 11:55pm

[efriis]

could you add a test case where both content and usage_metadata are returned? I'm pretty sure this has the exact same bug as #23704

I think this if/else block would need more substantial refactoring to work with this.

Will mark as draft for now - feel free to mark ready again when that's fixed!

[omgbbq]

could you add a test case where both content and usage_metadata are returned? I'm pretty sure this has the exact same bug as #23704

I think this if/else block would need more substantial refactoring to work with this.

Will mark as draft for now - feel free to mark ready again when that's fixed!

@efriis Yes, the same one. Based on the original, the return stream chunk message and unit tests of chatglm4, deepseek and gpt-3.5-turbo are added in libs/partners/openai/tests/unit_tests/chat_models/test_base.py.

[efriis]

Could you fix the lint errors in the new tests?