Commit Graph

35 Commits

Author SHA1 Message Date
magmueller
ef6311b22c Merge remote-tracking branch 'origin/main' into output-history 2024-11-22 22:41:58 +01:00
magmueller
7fdf80deda Test for history output 2024-11-22 22:37:59 +01:00
Gregor Žunič
9255d37b0d default logging level is info 2024-11-22 21:46:56 +01:00
Gregor Žunič
6e9d6c07a9 formatting logging 2024-11-22 21:39:43 +01:00
Gregor Žunič
03b83d60a6 bumped up version 2024-11-22 21:36:03 +01:00
Gregor Žunič
b48f94e394 Merge pull request #40 from BedroomDev:main
ResultOnlyMode: Added logLevel.RESULT & env to filter the output
2024-11-22 17:20:44 +01:00
Gregor Žunič
0019105a49 fixed merge errors 2024-11-22 15:08:58 +01:00
Gregor Žunič
5941dd2752 Merge branch 'staging' into gregorzunic/bu-56-switch-from-selenium-to-playwright 2024-11-22 15:08:30 +01:00
Gregor Žunič
bb233e7868 fixed test_clicks 2024-11-22 14:36:11 +01:00
magmueller
e5d7dc2e3f Agent history tests included 2024-11-22 13:08:37 +01:00
Gregor Žunič
0000af0a11 fixed sync pydantic param registered functions 2024-11-22 12:51:30 +01:00
Jean Weatherwax
c73eca6991 Allow headless option when initializing controller 2024-11-21 12:44:20 -07:00
Marvin
7f7c9ee44c Added logLevel.RESULT and to filter the output, added new .env.example variable 2024-11-21 12:05:06 +01:00
Marvin
864483968c Added logLevel.RESULT and to filter the output 2024-11-21 12:01:27 +01:00
Gregor Žunič
57490c06f3 fixed num clicks type error 2024-11-21 10:37:35 +01:00
Gregor Žunič
c91c1782e8 decreased click wait timeouts 2024-11-20 17:49:29 +01:00
Gregor Žunič
b0c390f2c0 fixed multi tab management, clicking timeouts, general bugfixes 2024-11-20 17:33:49 +01:00
Gregor Žunič
f7148e3542 untested version of playwright (kinda works) 2024-11-19 18:32:31 +01:00
magmueller
3d33a4ff94 Example for system prompt change 2024-11-19 16:53:56 +01:00
magmueller
2bba5d4617 Option to set new tasks and to do custom system prompt 2024-11-19 16:25:06 +01:00
Magnus Müller
d5ebd652e2 Merge pull request #34 from gregpr07/access-browser-with-custom-actions
Access browser with custom actions
2024-11-18 23:52:26 +01:00
Gregor Žunič
155f49acc4 started the switch from selenium to playwright 2024-11-18 20:38:00 +01:00
magmueller
be31ac9359 Fix token calculation 2024-11-18 20:23:09 +01:00
magmueller
e78ecc6ff0 Simplify browser access 2024-11-18 19:45:28 +01:00
magmueller
0bb488a01a Extent description for extract page 2024-11-18 14:28:57 +01:00
magmueller
3b047656f0 Fixed bug for empty parameters 2024-11-18 14:28:37 +01:00
magmueller
beef18c597 Merge remote-tracking branch 'origin/main' into fix-href-cap 2024-11-18 13:49:18 +01:00
magmueller
add855e5ee Dont cap urls 2024-11-18 13:46:22 +01:00
magmueller
1e9dee081b Core function to scroll up and down on page 2024-11-17 16:43:54 +01:00
Gregor Žunič
4f74170685 Added anonymized posthog telemetry (#22)
* added anonymized telemetry

* collect data with posthog readme
2024-11-17 01:17:01 +01:00
Gregor Žunič
89c63fdd63 Added custom actions registry and fixed extraction layer (#20)
* Validator

* Test mind2web

* Cleaned up logger

* Pytest logger

* Cleaned up logger

* Disable flag for human input

* Multiple clicks per button

* Multiple clicks per button

* More structured system prompt

* Fields with description

* System prompt example

* One logger

* Cleaner logging

* Log step in step function

* Fix critical clicking error - wrong argument used

* Improved thought process of agent

* Improve system prompt

* Remove human input message

* Custome action registration

* Pydantic model for custom actions

* Pydantic model for custome output

* Runs through, model outputs functions, but not called yet

* Work in progress - description for custome actions

* Description works, but schema not yet

* Model can call the right action - but is not executed

* Seperate is_controller_action  and is_custom_action

* Works! Model can call custom function

* Use registry for action, but result is not feed back to model

* Include result in messages

* Works with custom function - but typing is not correct

* Renamed registry

* First test cases

* Captcha tests

* Pydantic for tests

* Improve prompts for multy step

* System prompt structure

* Handle errors like validation error

* Refactor error handling in agent

* Refactor error handling in agent

* Improved logging

* Update view

* Fix click parameter to index

* Simplify dynamic actions

* Use run instead of step

* Rename history

* Rename AgentService to Agent

* Rename ControllerService to Controller

* Pytest file

* Rename get state

* Rename BrowserService

* reversed dom extraction recursion to while

* Rename use_vision

* Rename use_vision

* reversed dom tree items and made browser less anoying

* Renaming and fixing type errors

* Renamed class names for agent

* updated requirements

* Update prompt

* Action registration works for user and controller

* Fix done call by returning ActionResult

* Fix if result is none

* Rename AgentOutput and ActionModel

* Improved prompt Passes 6/8 tests from test_agent_actions

* Calculate token cost

* Improve display

* Simplified logger

* Test function calling

* created super simple xpath extraction algo

* Tests logging

* tiny fixes to dom extraction

* Remove test

* Dont log number of clicks

* Pytest file

* merged per element js checks

* Check if driver is still open

* super fast processing

* fixed agent planning and stuff

* Fix example

* Fix example

* Improve error

* Improved error correction

* New line for step

* small type error fixes

* Test for pydantic

* Fix line

* Removed sample

* fixed readme and examples

---------

Co-authored-by: magmueller <mamagnus00@gmail.com>
2024-11-15 21:42:02 +01:00
Gregor Žunič
7729da6971 testig element highlighting 2024-11-13 13:52:28 +01:00
Gregor Žunič
f11c37388d added highlighting of items 2024-11-07 19:02:02 +01:00
Gregor Žunič
7c5bc97e15 preserve element structure in outputs 2024-11-07 17:35:02 +01:00
Gregor Žunič
68201df624 src -> browser_use 2024-11-06 18:18:00 +01:00