Fix packaging metadata and add a non-embedding recall path#1
Open
0xCyberBerserker wants to merge 1 commit intoSabaTech-dev:mainfrom
Open
Fix packaging metadata and add a non-embedding recall path#10xCyberBerserker wants to merge 1 commit intoSabaTech-dev:mainfrom
0xCyberBerserker wants to merge 1 commit intoSabaTech-dev:mainfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This fixes a couple of rough edges in the current package layout and recall flow.
pyproject.tomland Pydantic modelsMemoryBank.recall()when no query embedding is providedWhy
At the moment the project fails to install through
pip install .because setuptools sees bothsqlandxmemoryat the top level and refuses automatic discovery.Also,
recall()only returns results when embeddings are passed in, which makes the basic API harder to use during early integration or local testing. A simple text/context fallback keeps the method useful before an embedding pipeline is wired in.The README also had a few examples that no longer match the constructor or the stats model fields.
Validation
python -m pytest -qCurrent result locally:
3 passed, 14 skipped