João Moura
0362449fe4
Adding new test for crew memory
2024-04-04 15:29:45 -03:00
João Moura
09c8193c8f
updating specs
2024-04-02 13:51:16 -03:00
João Moura
ddb84cc16d
Starting i18n language file support
2024-04-01 10:45:17 -03:00
João Moura
5b59e450f7
Adding long term, short term, entity and contextual memory
2024-04-01 10:45:17 -03:00
João Moura
5977c442b1
Adding custom caching
2024-04-01 10:43:05 -03:00
João Moura
721b27d222
Ability to disable cache at agent and crew level
2024-04-01 10:43:05 -03:00
João Moura
7259dba90d
fixing warnings
2024-04-01 10:43:05 -03:00
GabeKoga
bcf701b287
feature: human input per task ( #395 )
...
* feature: human input per task
* Update executor.py
* Update executor.py
* Update executor.py
* Update executor.py
* Update executor.py
* feat: change human input for unit testing
added documentation and unit test
* Create test_agent_human_input.yaml
add yaml for test
---------
Co-authored-by: João Moura <joaomdmoura@gmail.com >
2024-04-01 10:04:56 -03:00
Gui Vieira
128ce91951
Fix input interpolation bug ( #369 )
2024-03-22 03:08:54 -03:00
João Moura
35f8919e73
Preparing new version
2024-03-11 17:37:12 -03:00
João Moura
47b5cbd211
adding initial CLI support
2024-03-11 16:37:32 -03:00
João Moura
b856b21fc6
updating tests
2024-03-03 20:54:15 -03:00
João Moura
78bf008c36
cutting a new version addressin backward compatibility
2024-02-28 12:04:13 -03:00
João Moura
997c906b5f
adding support for input interpolation for tasks and agents
2024-02-28 03:44:23 -03:00
João Moura
2530196cf8
fixing tests
2024-02-28 03:44:23 -03:00
João Moura
340bea3271
Adding ability to track tools_errors and delegations
2024-02-28 03:44:23 -03:00
João Moura
a9863fe670
Adding overall usage_metrics to crew and not adding delegation tools if there no agents the allow delegation
2024-02-28 03:44:23 -03:00
João Moura
7b49b4e985
Adding initial formatting error counting and token counter
2024-02-28 03:44:23 -03:00
João Moura
1c7f9826b4
adding new converter logic
2024-02-22 15:16:17 -03:00
João Moura
0593d52b91
Improving inner prompts
2024-02-20 17:53:30 -03:00
João Moura
e9aa87f62b
Updating tests
2024-02-20 10:40:37 -03:00
João Moura
4c519d9d98
updating tests
2024-02-19 22:48:34 -03:00
João Moura
19b6c15fff
Cutting new version with tool ussage bug fix
2024-02-15 23:19:12 -03:00
João Moura
e55cee7372
adding function calling llm support
2024-02-13 02:57:12 -08:00
João Moura
b21191dd55
updating tests
2024-02-13 01:50:12 -08:00
João Moura
0076ea7bff
Adding ability to remember instruction after using too many tools
2024-02-10 12:53:02 -08:00
João Moura
e79da7bc05
refactoring task execution
2024-02-10 11:28:08 -08:00
João Moura
00206a62ab
Revamping tool usage
2024-02-10 10:36:34 -08:00
João Moura
d4c21a23f4
updating all cassettes
2024-02-10 00:55:40 -08:00
João Moura
a1e0596450
adding crew step_callback
2024-02-09 01:24:31 -08:00
João Moura
596e243374
adding support for step_callback
2024-02-08 23:56:13 -08:00
João Moura
326ad08ba2
adding support for full_ouput in crews
2024-02-08 23:23:34 -08:00
João Moura
a45c82c5f7
fixing RPM controlelr being set unencessarily
2024-02-07 23:09:36 -08:00
João Moura
09bec0e28b
adding manager_llm
2024-02-05 20:46:47 -08:00
João Moura
2f0bf3b325
updating readme
2024-02-04 13:13:42 -08:00
João Moura
05dda59cf6
Adding multi thread execution
2024-02-03 23:24:41 -08:00
João Moura
d712ee8451
adding ability to pass context to tasks
2024-02-02 23:17:02 -08:00
Gui Vieira
c78237cb86
Hierarchical process ( #206 )
...
* Hierarchical process + Docs
Co-authored-by: João Moura <joaomdmoura@gmail.com >
2024-02-02 13:56:35 -03:00
João Moura
8fc0f33dd5
adding task callback
2024-01-30 22:46:20 -03:00
Guilherme Vieira
29c31a2404
Fix static typing errors ( #187 )
...
Co-authored-by: João Moura <joaomdmoura@gmail.com >
2024-01-29 19:52:14 -03:00
João Moura
cd77981102
Adding support for expected output
2024-01-29 00:11:30 -03:00
João Moura
2bf924b732
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
53a32153a5
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
8e7772c9c3
Adding support for translations ( #120 )
...
Add translations support
2024-01-12 14:49:36 -03:00
João Moura
ea7759b322
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
8cc51d5e9e
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
João Moura
7954f6b51c
Reliability improvements ( #77 )
...
* fixing identation for AgentTools
* updating gitignore to exclude quick test script
* startingprompt translation
* supporting individual task output
* adding agent to task output
* cutting new version
* Updating README example
2024-01-07 12:43:23 -03:00
João Moura
234a2c72b0
Tools cache and delegation improvements ( #68 )
...
* Fixing repeated tool usage treatment
* Improving agent delegation prompt
2024-01-06 11:46:34 -03:00
João Moura
3f9c4df32d
Better agent execution error handling ( #54 )
...
A few quality of life improvements around cache handling and repeated tool usage
2024-01-05 11:04:59 -03:00
João Moura
6b054651a7
Refactoring task cache to be a tool ( #50 )
...
* Refactoring task cache to be a tool
The previous implementation of the task caching system was early exiting
the agent executor due to the fact it was returning an AgentFinish object.
This now refactors it to use a cache specific tool that is dynamically
added and forced into the agent in case of a task execution that was
already executed with the same input.
2024-01-04 21:29:42 -03:00
