langchain/libs/partners/nvidia-ai-endpoints/tests
Vadim Kudlay 5f9ac6986e
nvidia-ai-endpoints[patch]: model arguments (e.g. temperature) on construction bug (#17290)
- **Issue:** Issue with model argument support (been there for a while
actually):
- Non-specially-handled arguments like temperature don't work when
passed through constructor.
- Such arguments DO work quite well with `bind`, but also do not abide
by field requirements.
- Since initial push, server-side error messages have gotten better and
v0.0.2 raises better exceptions. So maybe it's better to let server-side
handle such issues?
- **Description:**
- Removed ChatNVIDIA's argument fields in favor of
`model_kwargs`/`model_kws` arguments which aggregates constructor kwargs
(from constructor pathway) and merges them with call kwargs (bind
pathway).
- Shuffled a few functions from `_NVIDIAClient` to `ChatNVIDIA` to
streamline construction for future integrations.
- Minor/Optional: Old services didn't have stop support, so client-side
stopping was implemented. Now do both.
- **Any Breaking Changes:** Minor breaking changes if you strongly rely
on chat_model.temperature, etc. This is captured by
chat_model.model_kwargs.

PR passes tests and example notebooks and example testing. Still gonna
chat with some people, so leaving as draft for now.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-09 13:46:02 -08:00
..
integration_tests nvidia-ai-endpoints[patch]: model arguments (e.g. temperature) on construction bug (#17290) 2024-02-09 13:46:02 -08:00
unit_tests [Documentation] Updates to NVIDIA Playground/Foundation Model naming.… (#14770) 2023-12-15 12:21:59 -08:00
__init__.py [Documentation] Updates to NVIDIA Playground/Foundation Model naming.… (#14770) 2023-12-15 12:21:59 -08:00