aljaz/gpt-engineer
1
0
Fork 0
mirror of https://github.com/aljazceru/gpt-engineer.git synced 2025-12-18 13:15:00 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update respec

Browse Source
This commit is contained in:
Anton Osika
2023-06-19 23:38:38 +02:00
parent 851c6bc999
commit 808fc7242d
3 changed files with 11 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpt_engineer/steps.py
View File

@@ -70,7 +70,7 @@ def gen_spec(ai: AI, dbs: DBs):
def respec(ai: AI, dbs: DBs): def respec(ai: AI, dbs: DBs):
messages = dbs.logs[gen_spec.__name__] messages = json.loads(dbs.logs[gen_spec.__name__])
messages += [ai.fsystem(dbs.identity["respec"])] messages += [ai.fsystem(dbs.identity["respec"])]
messages = ai.next(messages) messages = ai.next(messages)

10
identity/generate
View File

@@ -7,12 +7,12 @@ You will first lay out the names of the core classes, functions, methods that wi
Then you will output the content of each file including ALL code. Then you will output the content of each file including ALL code.
Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that
[FILENAME] is the lowercase file name including the file extension, FILENAME is the lowercase file name including the file extension,
[LANG] is the markup code block language for the code's language, and [CODE] is the code: LANG is the markup code block language for the code's language, and CODE is the code:
[FILENAME] FILENAME
```[LANG] ```LANG
[CODE] CODE
``` ```
You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on. You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.

11
identity/use_qa
View File

@@ -5,13 +5,12 @@ First lay out the names of the core classes, functions, methods that will be nec
Then you will output the content of each file including ALL code. Then you will output the content of each file including ALL code.
Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that
[FILENAME] is the lowercase file name including the file extension, FILENAME is the lowercase file name including the file extension,
[LANG] is the markup code block language for the code's language, and [CODE] is the code: LANG is the markup code block language for the code's language, and CODE is the code:
Syntax: FILENAME
[FILENAME] ```LANG
```[LANG] CODE
[CODE]
``` ```
Please note that the code should be fully functional. No placeholders. Please note that the code should be fully functional. No placeholders.