richfrem Vector DB Audit
Systematically audits the Vector Database to identify gaps between the project manifest and the actual document chunks stored in ChromaDB.
Capabilities
- Coverage Analysis: Calculates the exact percentage of project documentation currently vectorized.
- Gap Identification: Detects files that are included in the manifest but missing from the ChromaDB collection.
- Exporting: Generates CSV lists of missing files for targeted batch ingestion.
- Dynamic Configuration: Loads connection and collection settings directly from the selected profile.
Usage
Run the audit for a specific profile (e.g., wiki) to generate a coverage report and a CSV of gaps:
python scripts/audit_vector.py --profile wiki --report vector_audit.txt --csv missing_vector.csv
Protocol
- Identify: Run this skill to find missing content.
- Review: Check
missing_vector.csv. - Ingest: Use
vector-db-ingest --profile wiki --file [path]to fill specific gaps.
Related
- vector-db-ingest: Use to fill the gaps identified by this audit.
- vector-db-cleanup: Use to remove orphaned chunks from the index.