feat: implement ProjectAI MVP automation pipeline#1
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| @classmethod | ||
| def from_dict(cls, data: Dict[str, Iterable[str]]) -> "FeishuSourceConfig": | ||
| return cls( | ||
| documents=[Path(path) for path in data.get("documents", [])], | ||
| sheets=[Path(path) for path in data.get("sheets", [])], | ||
| messages=[Path(path) for path in data.get("messages", [])], |
There was a problem hiding this comment.
Relative paths from the config are converted to Path objects as-is, so they are interpreted relative to the process working directory. If the CLI is executed outside the repository (e.g. python run.py run --config /tmp/sample_config.json), the ingestion step fails with FileNotFoundError: data/document_tasks.json because the paths aren’t anchored to the config file’s location. Consider joining each path with the directory that contains the config before building FeishuSourceConfig, so configs work regardless of where the command is launched.
Useful? React with 👍 / 👎.
1 participant
Summary
Testing
https://chatgpt.com/codex/tasks/task_e_68f4fede5638832297790849ad35b599