Roo-Code/reranker-service/docker-compose.yml
Abinand Nallathambi 6fe86f074f feat: Add code search reranking support via external services
- Implement pluggable reranker architecture with HTTP API communication
- Add LocalReranker implementation for self-hosted reranking services
- Include reference Python reranker service with Docker support
- Add comprehensive UI configuration options in settings
- Implement proper error handling and fallback mechanisms
- Add extensive test coverage for all reranking functionality
- Support internationalization for all 18 languages
- Update documentation with feature overview and usage instructions

The extension now supports optional reranking of code search results
through external services, improving search relevance while maintaining
user privacy and control.
2025-08-02 15:43:50 -04:00

65 lines
No EOL
1.4 KiB
YAML

version: '3.8'
services:
reranker:
build:
context: .
dockerfile: Dockerfile
container_name: code-reranker
ports:
- "8080:8080"
environment:
# Model configuration
- MODEL_NAME=cross-encoder/ms-marco-MiniLM-L-6-v2
- MODEL_CACHE_DIR=/app/.cache/models
# API configuration
- API_HOST=0.0.0.0
- API_PORT=8080
- API_WORKERS=1
# Performance configuration
- REQUEST_TIMEOUT=30
- BATCH_SIZE=32
# Logging
- LOG_LEVEL=INFO
# CORS configuration
- CORS_ORIGINS=http://localhost:*,http://127.0.0.1:*
# Device configuration (set to true to force CPU usage)
- FORCE_CPU=false
# Model warmup
- WARMUP_ON_START=true
volumes:
# Mount model cache to persist downloaded models
- model-cache:/app/.cache/models
# For development: mount source code
- ./app.py:/app/app.py:ro
- ./models:/app/models:ro
- ./config.py:/app/config.py:ro
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 40s
restart: unless-stopped
# Resource limits
deploy:
resources:
limits:
memory: 2G
reservations:
memory: 1G
volumes:
model-cache:
driver: local