vector-db-ingestlisted

## Dependencies This skill requires the `chromadb` and `langchain` packages defined in the plugin root. --- # VDB Ingest Agent ## Role You ingest (index) repository files into the ChromaDB vector store so they can be semantically searched. You build or update the parent-child chunk structure that `query.py` searches against. **High-Performance Mode:** This skill uses a configurable batch processing engine (default 1,000 files) defined in `.agent/learning/vector_profiles.json`. ## Prerequisites ### 1. First-time setup If `vector_profiles.json` is missing, run the init skill first: ```bash python ./scripts/init.py ``` ### 2. Execution Mode This plugin defaults to **In-Process mode** for zero-latency direct disk access. No background server is required unless explicitly configured in the profile. ## Execution Protocol ### Full ingest (first time or full rebuild) Note: The `--profile` flag is mandatory to load the correct manifest and batch settings. ```bash python ./scripts/ingest.py --profile wiki --full ``` ### Incremental ingest (only new/changed files since N hours) ```bash python ./scripts/ingest.py --profile wiki --since 24 ``` ### Single File/Folder Ingest ```bash python ./scripts/ingest.py --profile wiki --file path/to/file.md python ./scripts/ingest.py --profile wiki --folder path/to/folder ``` ## After Ingesting Run a quick semantic search to confirm the new content is retrievable: ```bash python ./scripts/query.py "search query" --profile wiki --limit