koko210Serve
14e1a8df51
Key changes:
- CatAdapter (bot/utils/cat_client.py): WebSocket /ws/{user_id} for chat
queries instead of HTTP POST (fixes per-user memory isolation when no
API keys are configured — HTTP defaults all users to user_id='user')
- Memory management API: 8 endpoints for status, stats, facts, episodic
memories, consolidation trigger, multi-step delete with confirmation
- Web UI: Memory tab (tab9) with collection stats, fact/episodic browser,
manual consolidation trigger, and 3-step delete flow requiring exact
confirmation string
- Bot integration: Cat-first response path with query_llama fallback for
both text and embed responses, server mood detection
- Discord bridge plugin: fixed .pop() to .get() (UserMessage is a Pydantic
BaseModelDict, not a raw dict), metadata extraction via extra attributes
- Unified docker-compose: Cat + Qdrant services merged into main compose,
bot depends_on Cat healthcheck
- All plugins (discord_bridge, memory_consolidation, miku_personality)
consolidated into cat-plugins/ for volume mount
- query_llama deprecated but functional for compatibility
200 lines
6.2 KiB
YAML
200 lines
6.2 KiB
YAML
services:
|
|
# ========== LLM Backends ==========
|
|
llama-swap:
|
|
image: ghcr.io/mostlygeek/llama-swap:cuda
|
|
container_name: llama-swap
|
|
ports:
|
|
- "8090:8080" # Map host port 8090 to container port 8080
|
|
volumes:
|
|
- ./models:/models # GGUF model files
|
|
- ./llama-swap-config.yaml:/app/config.yaml # llama-swap configuration
|
|
- ./llama31_notool_template.jinja:/app/llama31_notool_template.jinja # Custom chat template
|
|
runtime: nvidia
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 30s # Give more time for initial model loading
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- LOG_LEVEL=debug # Enable verbose logging for llama-swap
|
|
|
|
llama-swap-amd:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.llamaswap-rocm
|
|
container_name: llama-swap-amd
|
|
ports:
|
|
- "8091:8080" # Map host port 8091 to container port 8080
|
|
volumes:
|
|
- ./models:/models # GGUF model files
|
|
- ./llama-swap-rocm-config.yaml:/app/config.yaml # llama-swap configuration for AMD
|
|
- ./llama31_notool_template.jinja:/app/llama31_notool_template.jinja # Custom chat template
|
|
devices:
|
|
- /dev/kfd:/dev/kfd
|
|
- /dev/dri:/dev/dri
|
|
group_add:
|
|
- "985" # video group
|
|
- "989" # render group
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 30s # Give more time for initial model loading
|
|
environment:
|
|
- HSA_OVERRIDE_GFX_VERSION=10.3.0 # RX 6800 compatibility
|
|
- ROCM_PATH=/opt/rocm
|
|
- HIP_VISIBLE_DEVICES=0 # Use first AMD GPU
|
|
- GPU_DEVICE_ORDINAL=0
|
|
|
|
# ========== Cheshire Cat AI (Memory & Personality) ==========
|
|
cheshire-cat:
|
|
image: ghcr.io/cheshire-cat-ai/core:1.6.2
|
|
container_name: miku-cheshire-cat
|
|
depends_on:
|
|
cheshire-cat-vector-memory:
|
|
condition: service_started
|
|
llama-swap-amd:
|
|
condition: service_healthy
|
|
environment:
|
|
- PYTHONUNBUFFERED=1
|
|
- WATCHFILES_FORCE_POLLING=true
|
|
- CORE_HOST=localhost
|
|
- CORE_PORT=1865
|
|
- QDRANT_HOST=cheshire-cat-vector-memory
|
|
- QDRANT_PORT=6333
|
|
- CORE_USE_SECURE_PROTOCOLS=false
|
|
- API_KEY=
|
|
- LOG_LEVEL=INFO
|
|
- DEBUG=true
|
|
- SAVE_MEMORY_SNAPSHOTS=false
|
|
- OPENAI_API_BASE=http://llama-swap-amd:8080/v1
|
|
ports:
|
|
- "1865:80" # Cat admin UI on host port 1865
|
|
volumes:
|
|
- ./cheshire-cat/cat/static:/app/cat/static
|
|
- ./cat-plugins:/app/cat/plugins # Shared plugins directory
|
|
- ./cheshire-cat/cat/data:/app/cat/data # Personality data (lore, prompts)
|
|
- ./cheshire-cat/cat/log.py:/app/cat/log.py # Patched: fix loguru KeyError for third-party libs
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:80/"]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 8
|
|
start_period: 45s # Cat takes a while to load embedder + plugins
|
|
|
|
cheshire-cat-vector-memory:
|
|
image: qdrant/qdrant:v1.9.1
|
|
container_name: miku-qdrant
|
|
environment:
|
|
- LOG_LEVEL=INFO
|
|
ports:
|
|
- "6333:6333" # Qdrant REST API (for debugging)
|
|
ulimits:
|
|
nofile:
|
|
soft: 65536
|
|
hard: 65536
|
|
volumes:
|
|
- ./cheshire-cat/cat/long_term_memory/vector:/qdrant/storage
|
|
restart: unless-stopped
|
|
|
|
# ========== Discord Bot ==========
|
|
miku-bot:
|
|
build: ./bot
|
|
container_name: miku-bot
|
|
volumes:
|
|
- ./bot/memory:/app/memory
|
|
- /home/koko210Serve/ComfyUI/output:/app/ComfyUI/output:ro
|
|
- /var/run/docker.sock:/var/run/docker.sock # Allow container management
|
|
depends_on:
|
|
llama-swap:
|
|
condition: service_healthy
|
|
llama-swap-amd:
|
|
condition: service_healthy
|
|
cheshire-cat:
|
|
condition: service_healthy
|
|
environment:
|
|
- DISCORD_BOT_TOKEN=MTM0ODAyMjY0Njc3NTc0NjY1MQ.GXsxML.nNCDOplmgNxKgqdgpAomFM2PViX10GjxyuV8uw
|
|
- LLAMA_URL=http://llama-swap:8080
|
|
- LLAMA_AMD_URL=http://llama-swap-amd:8080 # Secondary AMD GPU endpoint
|
|
- TEXT_MODEL=llama3.1
|
|
- VISION_MODEL=vision
|
|
- OWNER_USER_ID=209381657369772032 # Your Discord user ID for DM analysis reports
|
|
- FACE_DETECTOR_STARTUP_TIMEOUT=60
|
|
# Cheshire Cat integration (Phase 3)
|
|
- CHESHIRE_CAT_URL=http://cheshire-cat:80
|
|
- USE_CHESHIRE_CAT=true
|
|
ports:
|
|
- "3939:3939"
|
|
networks:
|
|
- default # Stay on default for llama-swap + cheshire-cat communication
|
|
- miku-voice # Connect to voice network for RVC/TTS
|
|
restart: unless-stopped
|
|
|
|
# ========== Voice / STT ==========
|
|
miku-stt:
|
|
build:
|
|
context: ./stt-realtime
|
|
dockerfile: Dockerfile
|
|
container_name: miku-stt
|
|
runtime: nvidia
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=0 # GTX 1660
|
|
- CUDA_VISIBLE_DEVICES=0
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
- STT_HOST=0.0.0.0
|
|
- STT_PORT=8766
|
|
- STT_HTTP_PORT=8767 # HTTP health check port
|
|
volumes:
|
|
- stt-models:/root/.cache/huggingface # Persistent model storage
|
|
ports:
|
|
- "8766:8766" # WebSocket port
|
|
- "8767:8767" # HTTP health check port
|
|
networks:
|
|
- miku-voice
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids: ['0'] # GTX 1660
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
|
|
# ========== Tools (on-demand) ==========
|
|
anime-face-detector:
|
|
build: ./face-detector
|
|
container_name: anime-face-detector
|
|
runtime: nvidia
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- capabilities: [gpu]
|
|
volumes:
|
|
- ./face-detector/api:/app/api
|
|
- ./face-detector/images:/app/images
|
|
ports:
|
|
- "7860:7860" # Gradio UI
|
|
- "6078:6078" # FastAPI API
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
restart: "no" # Don't auto-restart - only run on-demand
|
|
profiles:
|
|
- tools # Don't start by default
|
|
|
|
networks:
|
|
miku-voice:
|
|
external: true
|
|
name: miku-voice-network
|
|
|
|
volumes:
|
|
stt-models:
|
|
name: miku-stt-models
|