42 Commits

Author	SHA1	Message	Date
Jack Hayter	e307da43c5	Prevent duplicate TokenCalcHandler callbacks on Agent (#475)	2024-04-16 15:54:02 -03:00
João Moura	f7fc61f043	Increasing default max inter	2024-04-05 08:36:09 -03:00
João Moura	9b37aab61a	adding max execution time	2024-04-05 08:31:25 -03:00
João Moura	a0ba9a81b2	not overriding llm callbacks	2024-04-05 08:24:20 -03:00
João Moura	fd12609330	Adding new test for crew memory	2024-04-04 15:29:45 -03:00
João Moura	a1e1113101	Removing memory flag from agent in favor of crew memory	2024-04-04 15:29:45 -03:00
João Moura	f85bf00409	Adding long term, short term, entity and contextual memory	2024-04-01 10:45:17 -03:00
João Moura	d73dd08ef4	Adding custom caching	2024-04-01 10:43:05 -03:00
João Moura	81d5fe6fc6	Ability to disable cache at agent and crew level	2024-04-01 10:43:05 -03:00
Gui Vieira	27b3625cd1	Fix input interpolation bug (#369)	2024-03-22 03:08:54 -03:00
João Moura	5aa543f4d2	Preparing new version	2024-03-11 17:37:12 -03:00
Chris Pang	7ce89b8741	added langchain callback to agents (#333) ... Co-authored-by: Chris Pang <chris_pang@racv.com.au>	2024-03-11 16:40:10 -03:00
João Moura	631fce5b7c	Overridding classes __repr__	2024-03-05 10:12:49 -03:00
João Moura	ef9f85f5d2	adding support for agents and tasks to be defined of configs	2024-03-05 01:26:07 -03:00
João Moura	8468445e1d	Update inner tool usage logic to support both regular and function calling	2024-03-03 20:54:15 -03:00
João Moura	d2f8a30c96	cutting a new version addressin backward compatibility	2024-02-28 12:04:13 -03:00
João Moura	1b63f1a2ab	Fixing bug preparing new version	2024-02-28 09:09:37 -03:00
João Moura	6d23dc6ad7	removing necessary crewai-tools dependency	2024-02-28 03:44:23 -03:00
João Moura	38ceb9d409	adding support for input interpolation for tasks and agents	2024-02-28 03:44:23 -03:00
João Moura	b6badbaf54	changing method naming to increment	2024-02-28 03:44:23 -03:00
João Moura	5d682a5d6c	Adding initial formatting error counting and token counter	2024-02-28 03:44:23 -03:00
João Moura	1df621fad0	make agents not have a memory by default	2024-02-24 03:33:05 -03:00
João Moura	c5500987aa	Adding support for agents without tools	2024-02-24 01:39:29 -03:00
João Moura	c099776962	Improving inner prompts	2024-02-20 17:53:30 -03:00
João Moura	3cfc8dd4e0	Adding new tool usage and parsing logic	2024-02-19 22:43:10 -03:00
João Moura	55c0c186d1	adding function calling llm support	2024-02-13 02:57:12 -08:00
João Moura	830ddb18d9	allowing to set model naem through env var	2024-02-12 13:24:01 -08:00
João Moura	21d1168943	Adding ability to remember instruction after using too many tools	2024-02-10 12:53:02 -08:00
João Moura	bbbd976fe3	refactoring task execution	2024-02-10 11:28:08 -08:00
João Moura	5a102251cf	Revamping tool usage	2024-02-10 10:36:34 -08:00
João Moura	3613bbc9e8	recreating executor upon setting new step_callback	2024-02-09 01:52:28 -08:00
João Moura	c5839b215e	adding agent step callback	2024-02-08 23:01:30 -08:00
Gui Vieira	7efecd10ea	Hierarchical process (#206) ... * Hierarchical process + Docs Co-authored-by: João Moura <joaomdmoura@gmail.com>	2024-02-02 13:56:35 -03:00
Guilherme Vieira	e0d97b9916	Fix static typing errors (#187) ... Co-authored-by: João Moura <joaomdmoura@gmail.com>	2024-01-29 19:52:14 -03:00
scott------	5322cff6a9	Update agent.py (#161) ... adding tools to the list of attribute descriptions	2024-01-21 16:56:19 -03:00
Greyson LaLonde	e8a31da05d	Update some docstrings / typehints (#144)	2024-01-21 16:55:17 -03:00
João Moura	e27dd53c78	Add RPM control to both agents and crews (#133) ... * moving file into utilities * creating Logger and RPMController * Adding support for RPM to agents and crew	2024-01-14 00:22:11 -03:00
João Moura	1fc806161f	Adding support for Crew throttling using RPM (#124) ... * Add translations * fixing translations * Adding support for Crew throttling with RPM	2024-01-13 11:20:30 -03:00
João Moura	b487136878	Adding support for translations (#120) ... Add translations support	2024-01-12 14:49:36 -03:00
João Moura	70072b4e40	Revamp max iteration Logic (#111) ... This now will allow to add a max_inter option to agents while also making sure to force the agent to give it's best final answer before running out of it's max_inter.	2024-01-11 12:32:54 -03:00
Greyson LaLonde	0fde1f6258	Bump to langchain0.1.0 (#108) ... * Bump `langchain`, `openai`; add `langchain-openai` * Update imports to fix warnings	2024-01-11 09:33:43 -03:00
Greyson LaLonde	d122d90df0	Move to src dir usage (#99)	2024-01-10 11:39:36 -03:00