vector-db-initlisted

## Dependencies This skill requires **Python 3.8+** and standard library for initialization. Performance operations require `chromadb` and `langchain` as defined in the plugin root requirements. **To install this skill's dependencies:** ```bash python -m piptools compile requirements.in --output-file requirements.txt pip install -r requirements.txt ``` --- # Vector DB Initialization The `vector-db-init` skill is an interactive setup routine that prepares the environment for the Vector database. It follows the same pattern as `rlm-init` and `wiki-init` for a consistent experience across all three retrieval plugins. ## Profile Configuration Reference All operational settings live in `.agent/learning/vector_profiles.json`. These control performance and connection mode. | Parameter | Default | Purpose | |:-----|:--------|:--------| | `chroma_host` | `""` | Empty = In-Process (Direct Disk); IP = Server mode. | | `batch_size` | `1000` | Files processed per embedding batch. | | `embedding_model` | `nomic-ai/nomic-embed-text-v1.5` | Semantic model for indexing. | | `device` | `cpu` | Hardware: `cpu` or `cuda` (NVIDIA GPU). | | `parent_chunk_size` | `2000` | Parent chunk granularity. | | `child_chunk_size` | `400` | Child chunk granularity. | ## When to Use This - When a user first installs the `vector-db` plugin. - If the Vector DB profile is missing from `.agent/learning/vector_profiles.json`. - If you need to add a new manifest profile or update which folders are indexed.