mirror of
https://github.com/aljazceru/gpt-engineer.git
synced 2025-12-17 04:35:17 +01:00
19a4c10b6e
* Added LangChain integration * Fixed issue created by git checkin process * Added ':' to characters to remove from end of file path * Tested initial migration to LangChain, removed comments and logging used for debugging * Tested initial migration to LangChain, removed comments and logging used for debugging * Converted camelCase to snake_case * Turns out we need the exception handling * Testing Hugging Face Integrations via LangChain * Added LangChain loadable models * Renames "qa" prompt to "clarify", since it's used in the "clarify" step, asking for clarification * Fixed loading model yaml files * Fixed streaming * Added modeldir cli option * Fixed typing * Fixed interaction with token logging * Fix spelling + dependency issues + typing * Fix spelling + tests * Removed unneeded logging which caused test to fail * Cleaned up code * Incorporated feedback - deleted unnecessary functions & logger.info - used LangChain ChatLLM instead of LLM to naturally communicate with gpt-4 - deleted loading model from yaml file, as LC doesn't offer this for ChatModels * Update gpt_engineer/steps.py Co-authored-by: Anton Osika <anton.osika@gmail.com> * Incorporated feedback - Fixed failing test - Removed parsing complexity by using # type: ignore - Replace every ocurence of ai.last_message_content with its content * Fixed test * Update gpt_engineer/steps.py --------- Co-authored-by: H <holden.robbins@gmail.com> Co-authored-by: Anton Osika <anton.osika@gmail.com>
43 lines
1.1 KiB
Python
43 lines
1.1 KiB
Python
import re
|
|
|
|
|
|
def parse_chat(chat): # -> List[Tuple[str, str]]:
|
|
# Get all ``` blocks and preceding filenames
|
|
regex = r"(\S+)\n\s*```[^\n]*\n(.+?)```"
|
|
matches = re.finditer(regex, chat, re.DOTALL)
|
|
|
|
files = []
|
|
for match in matches:
|
|
# Strip the filename of any non-allowed characters and convert / to \
|
|
path = re.sub(r'[\:<>"|?*]', "", match.group(1))
|
|
|
|
# Remove leading and trailing brackets
|
|
path = re.sub(r"^\[(.*)\]$", r"\1", path)
|
|
|
|
# Remove leading and trailing backticks
|
|
path = re.sub(r"^`(.*)`$", r"\1", path)
|
|
|
|
# Remove trailing ]
|
|
path = re.sub(r"[\]\:]$", "", path)
|
|
|
|
# Get the code
|
|
code = match.group(2)
|
|
|
|
# Add the file to the list
|
|
files.append((path, code))
|
|
|
|
# Get all the text before the first ``` block
|
|
readme = chat.split("```")[0]
|
|
files.append(("README.md", readme))
|
|
|
|
# Return the files
|
|
return files
|
|
|
|
|
|
def to_files(chat, workspace):
|
|
workspace["all_output.txt"] = chat
|
|
|
|
files = parse_chat(chat)
|
|
for file_name, file_content in files:
|
|
workspace[file_name] = file_content
|