6 Commits

Author	SHA1	Message	Date
Jack Gerrits	e35db7ef5f	Encapsulate colored into a module (#2057) ... * Encapsulate colored into a module * lint fix * add missing file * undo change * conform with original colored func * change import strategy --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>	2024-03-19 18:09:43 +00:00
Wael Karkoub	c5536ee92b	[Feature] Adds Image Generation Capability 2.0 (#1907) ... * adds image generation capability * add todo * readded cache * wip * fix content str bugs * removed todo: delete imshow * wip * fix circular imports * add notebook * improve prompt * improved text analyzer + notebook * notebook update * improve notebook * smaller notebook size * made changes to the wrong branch :( * resolve comments + 1 * adds doc strings * adds cache doc string * adds doc string to add_to_agent * adds doc string to ImageGeneration * instructions are not configurable * removed unnecessary imports * changed doc string location * more doc strings * improves testability * adds tests * adds cache test * added test to github workflow * compatible llm config format * configurable reply function position * skip_openai + better comments * fix test * fix test? * please fix test? * last fix test? * remove type hint * skip cache test * adds mock api key * dalle-2 test * fix dalle config * use apu key function --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com>	2024-03-15 22:11:53 +00:00
Chi Wang	cd3b5c6bbd	add doc about effects for capabilities (#1842) ... * add doc about effects for capabilities * remove unnecessary imports * improve doc * test * test location * polish * improve import of colored * termcolor * termcolor * use pull request for openai test	2024-03-03 23:15:52 +00:00
Gunnar Kudrjavets	b8ceb866e6	Add shebang functionality to tests (#1784) ... Tests that contain `if __name__ == "__main__":` now have a shebang line and execute permission.	2024-02-29 01:11:08 +00:00
dkirsche	a34e4cc515	Refactor transform_messages (#1631) ... * refactored code to simplify * optimize function. Instead of iterating over each character, guess at size and then iterate by token. * adding tests * Add missing tests * minor test fix * simplified token truncation by using tiktoken to encode and decode * updated truncated notification message * Fix llm_config spec to use os.environ * Add test case and fix bug in loop --------- Co-authored-by: gagb <gagb@users.noreply.github.com>	2024-02-20 22:53:05 +00:00
gagb	47d6c7567e	Proxy PR for Long Context Capability 1513 (#1591) ... * Add new capability to handle long context * Make print conditional * Remove superfluous comment * Fix msg order * Allow user to specify max_tokens * Add ability to specify max_tokens per message; improve name * Improve doc and readability * Add tests * Improve documentation and add tests per Erik and Chi's feedback * Update notebook * Update doc string of add to agents * Improve doc string * improve notebook * Update github workflows for context handling * Update docstring * update notebook to use raw config list. * Update contrib-openai.yml remove _target * Fix code formatting * Fix workflow file * Update .github/workflows/contrib-openai.yml --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>	2024-02-08 18:26:00 +00:00