Stefan Ayala 1e851ba3ea Feat set token limits based on model (#4498) ...

* feat: set max token limits for better user experience

* fix: use OPEN_AI_CHAT_MODELS max limits

* fix: use the old default of 8000

* fix: formatting so isort/black checks pass

* fix: avoid circular dependencies

* fix: use better to avoid circular imports

* feat: introduce soft limits and use them

* fix: circular import issue and missing field

* fix: move import to avoid overriding doc comment

* feat: DRY things up and set token limit for fast llm models too

* tests: make linter tests happy

* test: use the max token limits in config.py test

* fix: remove fast token limit from config

* feat: remove smart token limit from config

* fix: remove unused soft_token_limit var

* fix: remove unneeded tests, settings aren't in config anymore

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>

2023-06-07 10:16:53 +02:00

..

Auto-GPT-test-cassettes @ dbea803947

Update cassette submodule & fix current_score.json generation (#4601)

2023-06-06 23:46:41 +02:00

challenges

Update challenge scores

2023-06-06 21:48:57 +00:00

integration

Improve logic and error messages for file reading and writing with Python code (#4567)

2023-06-07 02:54:02 +02:00

mocks

Pass Configs to Commands and remove CFG = Config() in the commands/ folder (#4328)

2023-05-26 08:39:25 -07:00

unit

Feat set token limits based on model (#4498)

2023-06-07 10:16:53 +02:00

vcr

Rearrange tests & fix CI (#4596)

2023-06-06 10:48:49 -07:00

__init__.py

refactor: Refactor imports to be compatible with unit tests

2023-04-12 10:16:00 +02:00

conftest.py

Rearrange tests & fix CI (#4596)

2023-06-06 10:48:49 -07:00

context.py

Add function and class descriptions to tests (#2715)

2023-04-24 14:55:49 +02:00

utils.py

Feature/basic proxy (#4164)

2023-05-14 11:07:37 +12:00