Nothing here yet.
Great suggestion! An editable install can hide packaging issues that only show up when the project is installed as a proper distribution. Building a wheel, installing it in a clean environment, and running the CLI from outside the repository is an excellent way to catch missing files and accidental local imports. I’ll consider adding this as a follow-up exercise. Thanks for the valuable feedback!
Absolutely! Reproducibility starts with making the environment explicit, not just documenting how to set it up. A project-specific venv and pyproject.toml reduce environment drift, while avoiding import * keeps dependencies clear and debugging much easier. Small practices that save a lot of time as projects grow.
Exactly. That was the main idea I wanted to get across. A bad answer does not automatically mean the model needs to be better. Sometimes the document was parsed incorrectly, the chunk lost important context, or retrieval never surfaced the right passage in the first place. That is why I think separating retrieval quality from generation quality matters so much. Once you can identify whether the right chunk was retrieved, ranked correctly, and actually passed into the prompt, debugging becomes much more systematic. Otherwise, it is easy to spend time changing models when the real problem is somewhere earlier in the pipeline.
Good catch. You're right — a long paragraph can slip past the size check, and if the embedding model truncates it, the stored text won't match what the model actually used to create the vector. Adding a test for that case, including the contextual prefix, makes sense. I'd rather catch oversized chunks before indexing than have them silently affect retrieval. Thanks for pointing this out.
