OMGeeky/gpt-pilot
1
0
Fork 0
mirror of https://github.com/OMGeeky/gpt-pilot.git synced 2025-12-31 08:30:03 +01:00
Code Issues Packages Projects Releases Wiki Activity
389 Commits 1 Branch 0 Tags
623908d09331f865d004c530088cd4e57d20cdfe
Commit Graph

64 Commits

Author SHA1 Message Date
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
Zvonimir Sabljic
9a7c15e0c5 Merge branch 'ipc' into debugging_ipc 2023-09-14 09:40:36 +02:00
Zvonimir Sabljic
0619b53d18 Necessary flag so 33c38985bf works 2023-09-12 21:35:07 +02:00
Zvonimir Sabljic
151aa051e2 Improved debugging process and enabled splitting of app development into tasks and then into steps 
- split step implementation into different functions
- standardized the return value in the implementation process - { "success": True }
- added propagation of errors back to the recursion level 0 with TooDeepRecursionError and TokenLimitError
- created new class Debugger and moved debugging in it
 2023-09-12 21:32:56 +02:00
Zvonimir Sabljic
19ac692509 Don't send max_tokens to openai api so we can use as much context as possible 2023-09-12 21:28:01 +02:00
LeonOstrez
80914f0722 Merge pull request #81 from nalbion/feature/should_execute_step 
Refactored `execute_step()` as per #80
 2023-09-12 12:57:52 +02:00
LeonOstrez
b023205a53 Merge pull request #85 from alter123/patch-1 
Add check when the response is empty
 2023-09-12 08:40:07 +02:00
LeonOstrez
9ffcdf79bb Merge pull request #82 from nalbion/feature/test_CodeMonkey 
Feature/test code monkey
 2023-09-12 08:09:12 +02:00
Jay
74cbe33421 Add check when the response is empty 
{
  "id": "",
  "object": "",
  "created": 0,
  "model": "",
  "prompt_annotations": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "hate": { "filtered": false, "severity": "safe" },
        "self_harm": { "filtered": false, "severity": "safe" },
        "sexual": { "filtered": false, "severity": "safe" },
        "violence": { "filtered": false, "severity": "safe" }
      }
    }
  ],
  "choices": [],
  "usage": null
}


In newer versions of models, at times choices array can be empty
 2023-09-12 00:01:13 +05:30
Nicholas Albion
a94cbf9209 added documentation 2023-09-11 22:15:26 +10:00
Nicholas Albion
5b7b621832 Refactored execute_step() as per #80 2023-09-11 14:09:16 +10:00
Goon
3b207987aa Merge remote-tracking branch 'upstream/main' 2023-09-11 10:26:05 +07:00
Goon
c39346868a fix(gitignore): rm cache 2023-09-11 10:08:57 +07:00
Goon
367caa1797 fix(gitignore): rm pilot-env and cache 2023-09-11 10:08:42 +07:00
Nicholas Albion
f2187b5a04 fixed tests for CI 2023-09-09 12:02:22 +10:00
Nicholas Albion
a38c7c4f6d linting 2023-09-09 11:54:16 +10:00
Nicholas Albion
4b64631bec linting 2023-09-09 11:50:55 +10:00
Nicholas Albion
8cec113df9 test_username_to_uuid() 2023-09-09 10:54:33 +10:00
Nicholas Albion
831e6a4265 Merge remote-tracking branch 'origin/main' into feature/get_email-from-gitconfig 
# Conflicts:
#	pilot/utils/arguments.py
 2023-09-09 10:54:02 +10:00
Zvonimir Sabljic
6a46851b20 Added catching and retrying when there is an error with Token limit 2023-09-08 18:03:54 +02:00
LeonOstrez
fd1fae8c43 Merge branch 'main' into feature/user_id-from-getpass_getuser 2023-09-08 14:46:04 +02:00
Goon
02623b6353 fix(llm connection): add openrouter api endpoint 2023-09-08 15:52:29 +07:00
Nicholas Albion
95c6e26665 removed commented-out code 2023-09-08 15:20:32 +10:00
Nicholas Albion
e33616450d BaseModel.id is a UUIDField, create UUID from username 2023-09-08 15:19:47 +10:00
Nicholas Albion
891d153a2b BaseModel.id is a UUIDField, create UUID from username 2023-09-08 15:14:49 +10:00
Nicholas Albion
ee77f1ffac get_app_by_user_workspace(user_id, workspace) 2023-09-08 15:13:37 +10:00
Nicholas Albion
0ec6da74ab workspace path can be specified in CLI args 2023-09-08 06:29:46 +10:00
Nicholas Albion
720fa26bcf user_id defaults to OS username 2023-09-08 04:05:26 +10:00
Nicholas Albion
c4af2750ac user_id defaults to OS username 2023-09-08 04:01:46 +10:00
Zvonimir Sabljic
d52c674cf0 Fix 2023-09-07 19:47:05 +02:00
Nicholas Albion
48edfae03c handle rate_limit_exceeded error 2023-09-08 03:05:26 +10:00
Nicholas Albion
69eeae5606 attempt to get email from ~/.gitconfig 2023-09-08 03:03:38 +10:00
LeonOstrez
44a05b49b5 collect telemetry and ask user for feedback 2023-09-07 13:01:44 +02:00
LeonOstrez
83378033be remove checking for tokens before openai api request and handle too many tokens in response 2023-09-06 16:46:08 +02:00