extracting model response

[marshmellow77]

Fixes #72

[RajeshThallam]

@marshmellow77 Thanks for contributing. Can you please update/run integration tests?

[marshmellow77]

Integration test ran successfully:

(venv-lc-google) heikohotz-macbookpro:vertexai heikohotz$ pytest tests/integration_tests/test_model_garden.py
================================================================================================== test session starts ==================================================================================================
platform darwin -- Python 3.11.7, pytest-7.4.4, pluggy-1.4.0
rootdir: /Users/heikohotz/Documents/Projects/repos/langchain-google/libs/vertexai
configfile: pyproject.toml
plugins: syrupy-4.6.1, anyio-4.3.0, asyncio-0.21.1
asyncio: mode=Mode.AUTO
collected 6 items

tests/integration_tests/test_model_garden.py ...... [100%]

====================================================================================== warnings summary =======================================================================================
tests/integration_tests/test_model_garden.py::test_model_garden[FALCON_ENDPOINT_ID-generated_text]
/Users/heikohotz/.pyenv/versions/3.11.7/envs/venv-lc-google/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function __call__ was deprecated in LangChain 0.1.7 and will be removed in 0.2.0. Use invoke instead.
warn_deprecated(

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
===================================================================================== slowest 5 durations =====================================================================================
37.08s call tests/integration_tests/test_model_garden.py::test_model_garden[FALCON_ENDPOINT_ID-generated_text]
31.19s call tests/integration_tests/test_model_garden.py::test_model_garden_agenerate[FALCON_ENDPOINT_ID-generated_text]
29.70s call tests/integration_tests/test_model_garden.py::test_model_garden_generate[FALCON_ENDPOINT_ID-generated_text]
3.72s call tests/integration_tests/test_model_garden.py::test_model_garden_generate[LLAMA_ENDPOINT_ID-None]
2.75s call tests/integration_tests/test_model_garden.py::test_model_garden_agenerate[LLAMA_ENDPOINT_ID-None]
========================================================================== 6 passed, 1 warning in 107.34s (0:01:47) ===========================================================================

[lkuligin]

integration test should be updated accordingly (to test the changes).
could you work on this, please (and fix linting too).

[marshmellow77]

What is linting? And I don't want to publish my endpoint IDs to the repo - but then how will it know which endpoints to use?

I'm afraid I'm not familiar with integration testing tools (it was already a struggle to get pytest to run), so I'm not sure what needs to be done here :)

[marshmellow77]

can someone offer guidance on what needs to be done here?

[moizsajid]

@marshmellow77 firstly set up poetry with linting and testing like explained over here https://python.langchain.com/docs/contributing/code#local-development-dependencies

Then run from make lint and make format from the respective module directory i.e. libs/vertexai or libs/genai (in your case it would be libs/vertexai) after activating poetry shell. Please let me know if you need further help!

For running integration tests, the command would be make integration_tests