steve
9aab79d49b
- Remove v1 Python CLI (src/kb_search/, tests/, root pyproject.toml, uv.lock, .venv) - Add Go client with cross-platform build (client/) - Add FastAPI engine with NVIDIA and multi-stage ROCm Dockerfiles (engine/) - Add VERSION files for client and engine, wired into builds - Add release.sh for automated build, tag, release, and Docker push - Update README with build/release docs and ROCm migration note - Clean up .gitignore for v2 project structure Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
25 lines
629 B
YAML
25 lines
629 B
YAML
services:
|
|
kb-engine:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.nvidia
|
|
runtime: nvidia
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
ports:
|
|
- "${KB_PORT:-8000}:8000"
|
|
volumes:
|
|
- ${KB_DATA_PATH:-./data}:/data
|
|
environment:
|
|
- KB_MODEL=${KB_MODEL:-all-MiniLM-L6-v2}
|
|
- KB_DEVICE=${KB_DEVICE:-auto}
|
|
- KB_INGEST_DEVICE=${KB_INGEST_DEVICE:-auto}
|
|
- KB_API_KEY=${KB_API_KEY:-}
|
|
- KB_SEARCH_THRESHOLD=${KB_SEARCH_THRESHOLD:-0.01}
|
|
restart: unless-stopped
|