koko210Serve
ae1e0aa144
Configuration: - .env.example, .gitignore, compose.yml (main docker compose) - docker-compose-amd.yml (ROCm), docker-compose-macos.yml - start.sh, stop.sh convenience scripts - LICENSE (Apache 2.0, from upstream Cheshire Cat) Memory management utilities: - analyze_consolidation.py, manual_consolidation.py, verify_consolidation.py - check_memories.py, extract_declarative_facts.py, store_declarative_facts.py - compare_systems.py (system comparison tool) - benchmark_cat.py, streaming_benchmark.py, streaming_benchmark_v2.py Test suite: - quick_test.py, test_setup.py, test_setup_simple.py - test_consolidation_direct.py, test_declarative_recall.py, test_recall.py - test_end_to_end.py, test_full_pipeline.py - test_phase2.py, test_phase2_comprehensive.py Documentation: - README.md, QUICK_START.txt, TEST_README.md, SETUP_COMPLETE.md - PHASE2_IMPLEMENTATION_NOTES.md, PHASE2_TEST_RESULTS.md - POST_OPTIMIZATION_ANALYSIS.md
26 lines
1.6 KiB
Plaintext
Executable File
26 lines
1.6 KiB
Plaintext
Executable File
# Decide host and port for your Cat. Default will be localhost:1865
|
|
# General settings for Cheshire Cat Core
|
|
CORE_HOST=localhost # Hostname for core service
|
|
CORE_PORT=1865 # Port for core service
|
|
LOG_LEVEL=WARNING # Default log level for all services
|
|
DEBUG=false # Enable debugging for more verbose logs
|
|
CORE_USE_SECURE_PROTOCOLS=false # Enable HTTPS/WSS for secure connections
|
|
# API_KEY=meow # Uncomment to set an API key for protected endpoints
|
|
|
|
# Settings for Qdrant vector memory service
|
|
# Uncomment and set the following if you need to specify custom settings
|
|
QDRANT_HOST=cheshire_cat_vector_memory # Hostname for the Qdrant service
|
|
QDRANT_PORT=6333 # Port for the Qdrant service
|
|
|
|
# Feature toggles
|
|
SAVE_MEMORY_SNAPSHOTS=false # Toggle for saving memory snapshots on embedder change
|
|
|
|
# Ollama-specific settings
|
|
OLLAMA_HOST=0.0.0.0 # Hostname for Ollama service
|
|
OLLAMA_PORT=11434 # Port for Ollama service
|
|
OLLAMA_FLASH_ATTENTION=false # Flash attention setting for Ollama service
|
|
OLLAMA_DEBUG=false # Debug mode for Ollama service
|
|
OLLAMA_KEEP_ALIVE="5m" # Duration models stay loaded, default 5 minutes, can be set to e.g., "24h"
|
|
OLLAMA_MAX_LOADED_MODELS=1 # Maximum number of models loaded simultaneously, default to 1
|
|
OLLAMA_NUM_PARALLEL=1 # Maximum number of allocated contexts (parallel requests). Manage resource efficiently: If OLLAMA_NUM_PARALLEL=4 and OLLAMA_MAX_LOADED_MODELS=3, the total context requirement might be up to 12 (4x3)
|