feat: +Reverse engineering related logic #800
Conversation
feat: +retry
fixbug: method type, feat: add compotition&aggregation
fixbug: IndexableDocument.from_path error
feat: ver+
fixbug: llm not answering the question
fixbug: add METAGPT model calc usage logic
fixbug: METAGPT model is None
| from metagpt.utils.di_graph_repository import DiGraphRepository | ||
| from metagpt.utils.graph_repository import GraphKeyword, GraphRepository | ||
|
|
||
|
|
||
| class RebuildClassView(Action): | ||
| """ | ||
| Reconstructs a graph repository about class diagram from a source code project. |
There was a problem hiding this comment.
We need more explicit functional description and design. Its function description is vague. The run interface has no real input parameters, and all input and output parameters are implicit.
| Reconstructs a graph repository about class diagram from a source code project. | ||
|
|
||
| Attributes: | ||
| graph_db (Optional[GraphRepository]): The optional graph repository. |
There was a problem hiding this comment.
It's a simple duplication of variables, and since this class is actually pydantic.BaseModel, I don't think the annotation here is needed and should be explained by the fields themselves.
| async def run(self, with_messages=None, format=config.prompt_schema): | ||
| """ | ||
| Implementation of `Action`'s `run` method. |
There was a problem hiding this comment.
Class is not a current specification and is recommended to be removed
| Implementation of `Action`'s `run` method. | ||
|
|
||
| Args: | ||
| with_messages (Optional[Type]): An optional argument specifying messages to react to. |
There was a problem hiding this comment.
This value requires appropriate type annotation and comments, rather than LLM generating text with no additional information
| # - gpt-4-turbo-vision: "gpt-4-vision-preview" | ||
| # - gpt-4 8k: "gpt-4" | ||
| # See for more: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/ | ||
| # pricing_plan: "gpt-4-turbo-preview" |
There was a problem hiding this comment.
It requires very clear annotations to explain its use and scenarios to reduce the cost of understanding.
| None | ||
|
|
||
| Raises: | ||
| SomeException: Describe any exceptions that might be raised during the saving process. |
There was a problem hiding this comment.
These comments, if they have no actual meaning, should be deleted. Please check other sections
| Note: | ||
| The JSON file should contain node-link data compatible with the format produced by the 'json' method. | ||
|
|
||
| """ | ||
| data = await aread(filename=pathname, encoding="utf-8") | ||
| m = json.loads(data) | ||
| self._repo = networkx.node_link_graph(m) | ||
|
|
||
| @staticmethod | ||
| async def load_from(pathname: str | Path) -> GraphRepository: |
There was a problem hiding this comment.
Generally speaking, this is more appropriately named from_json_file
| # Retrieves the root directory path for the graph repository files. | ||
|
|
||
| Note: | ||
| This property provides the directory path where graph repository files are saved or loaded. |
There was a problem hiding this comment.
251-263 seems to be reduced to one or three lines.
| Note: | ||
| This property provides the full path, including the filename, to the graph repository file. | ||
|
|
||
| """ |
There was a problem hiding this comment.
268-280 seems to be reduced to one or three lines.
| Note: | ||
| This property provides direct access to the networkx.DiGraph instance used by the graph repository. | ||
|
|
||
| """ |
There was a problem hiding this comment.
285-298 seems to be reduced to one or three lines.
Features