self-operating-computer

OthersideAI/self-operating-computer

Fork 0

mirror of https://github.com/OthersideAI/self-operating-computer.git synced 2026-03-29 05:07:04 +00:00

Commit Graph

Select branches

Hide Pull Requests

add-agent-1

add-ocr

dev

gpt-4-turbo

gpt-4o

main

refactor

#1

#10

#100

#105

#107

#108

#11

#110

#111

#112

#113

#114

#119

#121

#125

#126

#126

#129

#13

#134

#135

#136

#141

#143

#144

#145

#152

#154

#154

#157

#157

#16

#161

#162

#163

#172

#180

#185

#188

#19

#191

#191

#192

#192

#206

#224

#224

#226

#226

#227

#227

#229

#229

#230

#232

#232

#233

#236

#236

#237

#237

#238

#239

#241

#242

#247

#247

#249

#249

#250

#250

#252

#252

#255

#255

#256

#256

#257

#257

#258

#258

#260

#260

#264

#264

#265

#265

#268

#28

#34

#40

#41

#43

#44

#45

#47

#48

#49

#50

#51

#52

#54

#55

#57

#59

#61

#62

#63

#68

#70

#71

#75

#76

#8

#81

#82

#83

#89

#91

#96

#97

#97

#98

1.0.4

v1.0.1

v1.0.2

v1.0.3

v1.0.5

v1.0.6

v1.0.7

v1.0.8

v1.0.9

v1.1.0

v1.1.1

v1.1.2

v1.2.0

v1.2.1

v1.2.2

v1.2.3

v1.2.4

v1.2.5

v1.2.6

v1.2.7

v1.2.8

v1.2.9

v1.3.0

v1.3.1

v1.3.2

v1.4.0

v1.4.1

v1.4.2

v1.4.5

v1.4.6

v1.5.0

v1.5.1

v1.5.5

v1.5.6

v1.5.7

v1.5.8

10bb8bf3b6 remove extra space in print Josh Bickett 2024-02-02 14:57:50 -08:00
c80d502fe3 Update to version="1.2.9" v1.2.9 Josh Bickett 2024-02-02 14:46:27 -08:00
bc3e8276d4 SYSTEM_PROMPT_OCR_MAC improvements Josh Bickett 2024-02-02 14:46:13 -08:00
628c2f4a02 Iterate SYSTEM_PROMPT_OCR_MAC Josh Bickett 2024-02-02 14:16:00 -08:00
d144ac95f9 Some changes to VERBOSE prints Josh Bickett 2024-02-02 13:59:54 -08:00
02772a9ff0 Improve app prints in error handling and improve prompts Josh Bickett 2024-02-02 13:55:00 -08:00
4554bf50ff Remove ## Current Challenges since it was improved Josh Bickett 2024-01-26 08:57:05 -08:00
ef8f47d4f9 Update to version="1.2.8" v1.2.8 Josh Bickett 2024-01-25 08:30:05 -08:00
2e3eb0643f Improve OPERATE_FIRST_MESSAGE_PROMPT Josh Bickett 2024-01-25 08:29:43 -08:00
83d22fdfcb Add more cleaning to content Josh Bickett 2024-01-25 08:29:30 -08:00
8494e39e4b Improvements to SYSTEM_PROMPT_OCR_MAC Josh Bickett 2024-01-25 08:13:37 -08:00
283ccbf212 Improve if VERBOSE log and prompt Josh Bickett 2024-01-25 06:34:05 -08:00
5f2d7176a2 Turn off verbose True Josh Bickett 2024-01-25 06:08:22 -08:00
ba08bc4c3a Update gpt_4_fallback Josh Bickett 2024-01-24 09:31:45 -08:00
798a9f6126 Only show traceback.print_exc during debug mode Josh Bickett 2024-01-24 09:30:01 -08:00
345eb9d04b Update to version="1.2.7", bug fix v1.2.7 Josh Bickett 2024-01-24 09:01:40 -08:00
f494f226eb Add new mode to require_api_key Josh Bickett 2024-01-24 09:01:23 -08:00
1fe0b1ad15 New version="1.2.6" v1.2.6 Josh Bickett 2024-01-24 08:49:18 -08:00
fd0b8b3660 Merge pull request #145 from OthersideAI/add-ocr Josh Bickett 2024-01-24 08:45:21 -08:00
b1cc4faab5 Update readme.md add-ocr Josh Bickett 2024-01-24 08:41:53 -08:00
24e688432b Add ### Optical Character Recognition Mode -m gpt-4-with-ocr`` Josh Bickett 2024-01-24 08:40:11 -08:00
e8ffbb5edb Default to gpt-4-with-ocr since it performs best Josh Bickett 2024-01-24 08:29:12 -08:00
39ddc45dd6 Add missing if self.verbose: Josh Bickett 2024-01-24 08:27:04 -08:00
e1fa95374d Turn off verbose Josh Bickett 2024-01-24 08:24:30 -08:00
849cc7efba update get_system_prompt Josh Bickett 2024-01-23 19:12:39 -08:00
135b3ea6e4 New click prompt 'no button' approach for SYSTEM_PROMPT_OCR_MAC Josh Bickett 2024-01-22 07:33:53 -08:00
ff35f17a9b Create gpt_4_fallback method Josh Bickett 2024-01-22 07:33:33 -08:00
817d137eed Update SYSTEM_PROMPT_OCR_WIN_LINUX Josh Bickett 2024-01-21 13:24:50 -08:00
2716b92172 Add easyocr to `requirements.txt Josh Bickett 2024-01-21 13:24:38 -08:00
14f3a8a255 Adjust SYSTEM_PROMPT_OCR_MAC Josh Bickett 2024-01-21 13:19:51 -08:00
df1cbd2455 add content_str for proper message structure Josh Bickett 2024-01-21 13:12:49 -08:00
3281fac9fb iterate get text function Josh Bickett 2024-01-21 12:58:47 -08:00
4790a4fa46 Fix get_text_coordinates Josh Bickett 2024-01-21 12:30:09 -08:00
5f5ed69f33 Iterate get_text_coordinates Josh Bickett 2024-01-21 12:16:52 -08:00
ff7a716dfa Change dir to labeled_images_dir Josh Bickett 2024-01-21 12:16:26 -08:00
c90ce67029 Add get_text_coordinates Josh Bickett 2024-01-21 09:20:41 -08:00
f6b61c6341 Experimental prompt fixes Josh Bickett 2024-01-21 09:13:22 -08:00
a156a48a5d Bug fixes Josh Bickett 2024-01-21 09:13:06 -08:00
8f7765c5be Iterate ocr method with get_text_element Josh Bickett 2024-01-21 09:03:05 -08:00
4bca53e856 Add SYSTEM_PROMPT_OCR_MAC and SYSTEM_PROMPT_OCR_WIN_LINUX Josh Bickett 2024-01-21 08:42:03 -08:00
b2299236c7 Add initial ocr approach with call_gpt_4_vision_preview_ocr Josh Bickett 2024-01-21 07:57:56 -08:00
d0a972fd46 pass api_key to genai.configure Josh Bickett 2024-01-19 14:31:38 -08:00
b62cbfbabf Updating to version="1.2.5" v1.2.5 Josh Bickett 2024-01-19 13:51:10 -08:00
18757556f2 Was missing "thought" key Josh Bickett 2024-01-19 13:49:18 -08:00
657059f5c5 Consolidate into only one click fucntion add-agent-1 Josh Bickett 2024-01-19 13:10:38 -08:00
75db780bc7 Merge branch 'main' into add-agent-1 Josh Bickett 2024-01-19 12:55:42 -08:00
5b94e8cbd7 update to version="1.2.4" v1.2.4 Josh Bickett 2024-01-19 12:44:43 -08:00
94c59e71dc Fix OpenAI() instantiation bug Josh Bickett 2024-01-19 12:40:44 -08:00
439d09da5c Add new version="1.2.3" v1.2.3 Josh Bickett 2024-01-19 11:52:08 -08:00
d7b9a5c356 .example.env no longer needed for new readme.md approach Josh Bickett 2024-01-19 11:47:05 -08:00
99f902dc2e Add new self.openai_api_key approach Josh Bickett 2024-01-19 11:46:46 -08:00
fd6d493367 fix verbose assignment Josh Bickett 2024-01-19 11:38:59 -08:00
9d1d433d22 Create Singleton Pattern for Config Josh Bickett 2024-01-19 11:27:32 -08:00
721fdd2177 Add pkg_resources for yolo model Josh Bickett 2024-01-19 10:34:10 -08:00
c590889035 remove print Josh Bickett 2024-01-19 10:24:14 -08:00
303cb61d16 Add condition for require_api_key Josh Bickett 2024-01-19 10:22:11 -08:00
33cafdc570 Fix ### Voice Mode --voice`` Josh Bickett 2024-01-19 09:33:17 -08:00
c3a0c50f34 Iterate operate -m gemini-pro-vision instructions in readme.md Josh Bickett 2024-01-19 09:28:58 -08:00
510f562f44 Merge branch 'main' of https://github.com/OthersideAI/self-operating-computer v1.2.2 Josh Bickett 2024-01-19 09:25:45 -08:00
59ff55c3d5 Iterate verions to v1.2.1 for easy install Josh Bickett 2024-01-19 09:25:43 -08:00
209e7449ca Merge pull request #144 from OthersideAI/update-readme Josh Bickett 2024-01-19 09:24:57 -08:00
aeb302c2ff Update README.md Josh Bickett 2024-01-19 09:23:44 -08:00
d84cc3db29 Include operate.models.weights as part of setup Josh Bickett 2024-01-19 09:22:11 -08:00
23dfbd63ae Update README.md Josh Bickett 2024-01-19 09:01:18 -08:00
fe8445244e Add key.png and **Enter your OpenAI Key** Josh Bickett 2024-01-19 08:58:47 -08:00
0105586983 Simplify pip install self-operating-computer install Josh Bickett 2024-01-19 08:53:21 -08:00
edc347cc5c Iteration version="1.2.1", fixing config.py v1.2.1 Josh Bickett 2024-01-19 08:41:08 -08:00
59d93dfcb6 Merge pull request #143 from OthersideAI/fix-config Josh Bickett 2024-01-19 08:35:17 -08:00
4c61db4653 Fix initialize_openai issue Josh Bickett 2024-01-19 08:25:25 -08:00
9ba17f4ba0 fix duplicate save_api_key_to_env call Josh Bickett 2024-01-19 08:11:31 -08:00
9c9842bfb6 Add initialize_google and fix require_api_key Josh Bickett 2024-01-19 08:08:29 -08:00
d0369f86fc No VERBOSE needed here Josh Bickett 2024-01-19 06:32:07 -08:00
bf0ca67f32 Update initialize_openai Josh Bickett 2024-01-19 06:03:46 -08:00
3470581c64 Merge pull request #141 from ubaiidullaah/main Josh Bickett 2024-01-19 06:02:51 -08:00
456c7f83cf Merge pull request #136 from michaelhhogue/update-evaluate Josh Bickett 2024-01-18 16:08:58 -08:00
4d5c706fd3 Add prints Josh Bickett 2024-01-18 13:22:35 -08:00
4dc961112c Handled error parsing JSON:'NoneType' object has no attribute Ubaidullahn 2024-01-19 01:10:25 +05:00
2d0043165d Add some traceback.print_exc Josh Bickett 2024-01-17 15:37:35 -08:00
00ac3307f7 Add AGENT_API_BASE_URL Josh Bickett 2024-01-17 15:21:47 -08:00
20c15f10c6 Merge branch 'main' into add-agent-1 Josh Bickett 2024-01-17 14:43:30 -08:00
593c66460c Add config Josh Bickett 2024-01-17 14:43:23 -08:00
106c69d70e Add double_click Josh Bickett 2024-01-17 14:42:42 -08:00
626d9c956e Oops, fix bug in "agent-1" condition Josh Bickett 2024-01-16 12:09:41 -08:00
3af20fb671 Add back call_agent_1 Josh Bickett 2024-01-16 11:55:28 -08:00
2dd9a3a7d1 Remove #Additional Thoughts from README.MD and small prompt fix Josh Bickett 2024-01-16 10:55:00 -08:00
791d9634d7 Update test result message format Michael Hogue 2024-01-16 10:18:22 -05:00
26c4295cd3 Update error message Michael Hogue 2024-01-16 09:56:03 -05:00
1827a6be06 Check for last screenshot instead of summary screenshot Michael Hogue 2024-01-16 09:53:18 -05:00
7ae2ed2c7e Update to version 1.2.0, with keycommands v1.2.0 Josh Bickett 2024-01-16 06:44:20 -08:00
74d187a66d Merge pull request #135 from OthersideAI/add-agent-1 Josh Bickett 2024-01-16 06:41:40 -08:00
01bd850490 Minor prompt improvements Josh Bickett 2024-01-16 06:36:30 -08:00
12b29d0667 Add another useful print Josh Bickett 2024-01-16 06:29:06 -08:00
d03805ab10 Merge branch 'main' into add-agent-1 Josh Bickett 2024-01-16 06:12:36 -08:00
e9bef10337 Switch back README.md for now Josh Bickett 2024-01-16 05:52:34 -08:00
47b058177f turn off verbose Josh Bickett 2024-01-15 11:22:13 -08:00
b16d21aa84 remove unused fetch_openai_response_async Josh Bickett 2024-01-15 11:17:06 -08:00
5bf795c701 add back clearing Josh Bickett 2024-01-15 11:16:38 -08:00
849ce90fbd remove print Josh Bickett 2024-01-15 11:13:33 -08:00
c010fc3ca8 Fix Config bug Josh Bickett 2024-01-15 10:50:28 -08:00
5b3c75ca6b move yolo_model to only be required if using that mode Josh Bickett 2024-01-15 10:08:16 -08:00

1 2 3 4 5 ...