vector-db-launchlisted

## Dependencies This skill requires **Python 3.8+** and standard library only. No external packages needed. **To install this skill's dependencies:** ```bash pip-compile ./requirements.in pip install -r ./requirements.txt ``` See `./requirements.txt` for the dependency lockfile (currently empty — standard library only). --- # Vector DB Launch (Python Native Server) ChromaDB provides the vector database backend for semantic search. If configured for Option C (Native Server) in `vector_profiles.json`, the database must be running as a background HTTP service to be accessed by `operations.py`. ## When You Need This - **RAG ingest fails** with connection refused to `127.0.0.1:8110` - **Semantic search** hangs or fails to connect - The user has explicitly selected **Option 2 (Python Native Server)** during `vector-db-init` ## Pre-Flight Check ```bash # Check if ChromaDB is already running curl -sf http://127.0.0.1:8110/api/v1/heartbeat > /dev/null && echo "✅ ChromaDB running" || echo "❌ ChromaDB not running" ``` If it prints "✅ ChromaDB running", you're done. If not, proceed. ## Security: Localhost-Only Binding (Hard Rule) ChromaDB has multiple unpatched, unfixed CVEs as of 2026-08-27 (CVE-2026-45829: pre-auth code injection, CVSS 10.0; CVE-2026-45830/45831: authorization provider doesn't scope tenant/database/ collection permissions) — see `plugins/agent-memory/requirements.in` for full detail. **Never bind the server to `0.0.0.0` or any publicly routable interface**