OMGeeky/gpt-pilot
1
0
Fork 0
mirror of https://github.com/OMGeeky/gpt-pilot.git synced 2025-12-30 16:13:32 +01:00
Code Issues Packages Projects Releases Wiki Activity
523 Commits 1 Branch 0 Tags
2d867eb5a233fa2abbf8926430c9a2e4581ee484
Commit Graph

109 Commits

Author SHA1 Message Date
Nicholas Albion
908fec154e tidy up 2023-10-04 16:18:05 +11:00
Nicholas Albion
c1e47ceb8b testing new ApiKeyNotDefinedError in CI 2023-10-04 16:06:47 +11:00
Nicholas Albion
9251c1831e model = os.getenv('MODEL_NAME', 'gpt-4') - which makes sense as CI doesn't have my env 2023-10-04 15:50:45 +11:00
Nicholas Albion
366e88dc4d more debug 2023-10-04 15:47:47 +11:00
Nicholas Albion
11da00605a more logging 2023-10-04 15:42:50 +11:00
Nicholas Albion
8914bb438e added debuggin logs for CI 2023-10-04 15:39:11 +11:00
Nicholas Albion
cbac991bd9 avoid getting stuck in a loop if LLM can't conform to schema. 2023-10-04 15:23:36 +11:00
Nicholas Albion
0d8a4c7fee try without logger.error(str, e) 2023-10-04 14:56:16 +11:00
Nicholas Albion
a63aedb2b1 fix for #130 2023-10-04 14:53:22 +11:00
Nicholas Albion
8c26ce7674 logger.warn() is deprecated 2023-10-04 13:17:21 +11:00
Nicholas Albion
f446c0f028 fixed some unit tests 2023-10-03 19:04:17 +11:00
LeonOstrez
d6a677c35a enable retrying request for extension if API call fails 2023-10-02 18:28:13 +01:00
Nicholas Albion
1376c11647 added logging 2023-10-02 20:08:15 +11:00
Nicholas Albion
5fdc853768 GPT4 responded with a JSON object != schema. 
Retry the request, advising what the issue was
 2023-10-02 18:59:38 +11:00
LeonOstrez
4713a68040 fix updating of app status 2023-10-01 02:46:45 +01:00
LeonOstrez
0cec2a45bf fix loading project steps 2023-09-30 21:36:22 +01:00
LeonOstrez
f5feb6274d fixes 2023-09-29 22:37:35 +01:00
LeonOstrez
4c1fe834a8 fix getting args.root, ask feedback only on success and keyboard interrupt (not on exceptions), fix terminal width and erasing old logs 2023-09-29 13:31:11 +01:00
Nicholas Albion
396cf2fcea log prompt name at INFO 2023-09-29 18:38:25 +10:00
Nicholas Albion
7bf5de8861 Improved logging 2023-09-29 18:18:55 +10:00
pavel-pythagora
103b920cb7 Add arguments for extension 2023-09-28 13:29:21 +03:00
Nicholas Albion
2aaa914c26 Merge branch 'main' into debugging_ipc 
# Conflicts:
#	README.md
#	pilot/helpers/agents/CodeMonkey.py
#	pilot/helpers/agents/Developer.py
#	pilot/prompts/system_messages/architect.prompt
#	pilot/utils/arguments.py
#	pilot/utils/llm_connection.py
#	pilot/utils/utils.py
 2023-09-28 13:53:49 +10:00
Nicholas Albion
108271f28a ignore ': OPENROUTER PROCESSING' 2023-09-27 13:10:52 +10:00
Nicholas Albion
b0fea79c7b fixed test for CI 2023-09-27 12:45:20 +10:00
Nicholas Albion
8cfc7500b6 Merge branch 'debugging_ipc' into feature/99-remove-function-calling 2023-09-27 11:50:10 +10:00
Nicholas Albion
af75e8ebdc switched to colorama which works on Windows and in VS Code 2023-09-27 11:37:15 +10:00
Nicholas Albion
6dd5a032fa Improved JSON prompting for GPT-4 and recover incomplete JSON responses from Code Llama 2023-09-27 10:53:44 +10:00
LeonOstrez
459f9380a7 update code to support python <3.10, update requirements, fix readme issues 2023-09-26 17:13:15 +01:00
Nicholas Albion
cf97a1be5e removed TODOs 2023-09-26 19:44:52 +10:00
Nicholas Albion
e5e0f56d2e JSON validation working 2023-09-26 19:38:24 +10:00
Nicholas Albion
8a024c2ff2 rejecting responses that are not JSON. 
Need to fix prompts for GPT-4
 2023-09-26 17:27:54 +10:00
Nicholas Albion
b8965f527d notes and testing 2023-09-25 10:36:37 +10:00
Nicholas Albion
dd10b4ad24 removed local_llm_function_calling 2023-09-23 20:20:58 +10:00
Nicholas Albion
623908d093 fixed tests 2023-09-23 17:08:22 +10:00
Nicholas Albion
b317f58550 clean up 2023-09-23 16:27:02 +10:00
Nicholas Albion
f4789538a3 6 models returning JSON as per ARCHITECTURE function_calls schema 2023-09-23 14:52:57 +10:00
Nicholas Albion
18aec507e8 anthropic/claude-2 returns JSON 
gpt-3_5 returns technologies such as "Backend: Node.js with Mongo database (Mongoose)"
codellama throws an error due to missing `choices`
 2023-09-23 14:34:36 +10:00
Nicholas Albion
156b361263 function_call-style JSON response from gpt-4, gpt-3_5, codellama, palm-2-chat-bison 2023-09-23 00:45:23 +10:00
Nicholas Albion
575c25902e Refactored AgentConvo.postprecess_response() into function_calling.process_json_response() 2023-09-22 22:41:38 +10:00
Nicholas Albion
4d91f381c1 Tested Developer.install_technology before refactoring without function_calling 2023-09-22 19:11:50 +10:00
Nicholas Albion
d4879a04b7 ARCHITECTURE function_calls works on meta-llama/codellama-34b-instruct 2023-09-21 23:05:37 +10:00
Nicholas Albion
714658a0c8 tidy up tests 2023-09-21 00:25:25 +10:00
Nicholas Albion
2b4186a4f8 test_chat_completion_Architect passes 2023-09-20 23:15:37 +10:00
Nicholas Albion
82690b2a17 added test_end_to_end() and llm_connection test 2023-09-20 22:20:05 +10:00
Nicholas Albion
4b7aa2df22 get_prompt() moved from llm_connection to utils and works from unit tests 2023-09-20 22:17:37 +10:00
Nicholas Albion
0660244017 fabulous does not work on Windows 2023-09-20 22:14:59 +10:00
Zvonimir Sabljic
ffe4fbeba9 Enabled catching of max token limit errors from OpenAI's response 2023-09-18 19:18:54 -07:00
LeonOstrez
67209b5b27 merge master into debugging_ipc branch 2023-09-18 19:09:37 -07:00
Zvonimir Sabljic
0dd6b6d996 Changed development_steps, command_runs, and user_inputs models - we don't need to hash any data - we can just use it as is 2023-09-15 17:51:24 +02:00
Zvonimir Sabljic
65135344ab Converted colored leftovers 2023-09-15 09:43:30 +02:00