cheshire-cat/QUICK_START.txt

================================================================================
🐱 CHESHIRE CAT TEST ENVIRONMENT - QUICK START GUIDE
================================================================================

📍 Location: /home/koko210Serve/docker/miku-discord/cheshire-cat

🎯 Purpose: Test Cheshire Cat as memory/context system for Miku Bot

================================================================================
⚡ QUICK START (3 Commands)
================================================================================

1. Start services:
   ./start.sh

2. Configure and upload knowledge:
   python3 test_setup.py

3. Run benchmarks:
   python3 benchmark_cat.py

================================================================================
📊 WHAT TO LOOK FOR
================================================================================

✅ GOOD (Proceed with integration):
   - Mean latency < 1500ms
   - P95 latency < 2000ms
   - RAG retrieval is accurate

⚠️  BORDERLINE (Try GPU embeddings):
   - Mean latency 1500-2000ms
   - Consider hybrid approach

❌ POOR (Stick with current system):
   - Mean latency > 2000ms
   - RAG quality is poor

================================================================================
🔗 USEFUL LINKS
================================================================================

Admin Panel:    http://localhost:1865/admin
API Docs:       http://localhost:1865/docs
Qdrant:         http://localhost:6333/dashboard

================================================================================
📝 FILES CREATED
================================================================================

Configuration:
  ✓ .env                      Environment variables
  ✓ docker-compose.test.yml   Docker services

Scripts:
  ✓ start.sh                  Start services
  ✓ stop.sh                   Stop services
  ✓ test_setup.py             Configure Cat & upload knowledge
  ✓ benchmark_cat.py          Performance benchmarks
  ✓ compare_systems.py        Compare Cat vs current system

Documentation:
  ✓ SETUP_COMPLETE.md         Full setup guide
  ✓ TEST_README.md            Testing documentation
  ✓ QUICK_START.txt           This file

================================================================================
🎯 EXPECTED RESULTS (FX-6100)
================================================================================

With CPU embeddings:
  Mean: 1600-2200ms          ⚠️  Borderline for voice chat

With GPU embeddings:
  Mean: 900-1400ms           ✅ Good for voice chat

================================================================================
🛠️  TROUBLESHOOTING
================================================================================

Services won't start:
  docker logs miku_cheshire_cat_test

Can't connect to llama-swap:
  Edit test_setup.py line 10 with correct URL

Embeddings too slow:
  Try GPU acceleration (requires spare VRAM)

================================================================================
🧹 CLEANUP
================================================================================

Stop services:
  ./stop.sh

Remove all data:
  docker-compose -f docker-compose.test.yml down -v

================================================================================
📚 DETAILED DOCS
================================================================================

Full guide:     cat SETUP_COMPLETE.md
Test docs:      cat TEST_README.md
View all files: ls -lah

================================================================================
add: cheshire-cat configuration, tooling, tests, and documentation 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 2026-03-04 00:51:14 +02:00			`================================================================================`
			`🐱 CHESHIRE CAT TEST ENVIRONMENT - QUICK START GUIDE`
			`================================================================================`

			`📍 Location: /home/koko210Serve/docker/miku-discord/cheshire-cat`

			`🎯 Purpose: Test Cheshire Cat as memory/context system for Miku Bot`

			`================================================================================`
			`⚡ QUICK START (3 Commands)`
			`================================================================================`

			`1. Start services:`
			`./start.sh`

			`2. Configure and upload knowledge:`
			`python3 test_setup.py`

			`3. Run benchmarks:`
			`python3 benchmark_cat.py`

			`================================================================================`
			`📊 WHAT TO LOOK FOR`
			`================================================================================`

			`✅ GOOD (Proceed with integration):`
			`- Mean latency < 1500ms`
			`- P95 latency < 2000ms`
			`- RAG retrieval is accurate`

			`⚠️ BORDERLINE (Try GPU embeddings):`
			`- Mean latency 1500-2000ms`
			`- Consider hybrid approach`

			`❌ POOR (Stick with current system):`
			`- Mean latency > 2000ms`
			`- RAG quality is poor`

			`================================================================================`
			`🔗 USEFUL LINKS`
			`================================================================================`

			`Admin Panel: http://localhost:1865/admin`
			`API Docs: http://localhost:1865/docs`
			`Qdrant: http://localhost:6333/dashboard`

			`================================================================================`
			`📝 FILES CREATED`
			`================================================================================`

			`Configuration:`
			`✓ .env Environment variables`
			`✓ docker-compose.test.yml Docker services`

			`Scripts:`
			`✓ start.sh Start services`
			`✓ stop.sh Stop services`
			`✓ test_setup.py Configure Cat & upload knowledge`
			`✓ benchmark_cat.py Performance benchmarks`
			`✓ compare_systems.py Compare Cat vs current system`

			`Documentation:`
			`✓ SETUP_COMPLETE.md Full setup guide`
			`✓ TEST_README.md Testing documentation`
			`✓ QUICK_START.txt This file`

			`================================================================================`
			`🎯 EXPECTED RESULTS (FX-6100)`
			`================================================================================`

			`With CPU embeddings:`
			`Mean: 1600-2200ms ⚠️ Borderline for voice chat`

			`With GPU embeddings:`
			`Mean: 900-1400ms ✅ Good for voice chat`

			`================================================================================`
			`🛠️ TROUBLESHOOTING`
			`================================================================================`

			`Services won't start:`
			`docker logs miku_cheshire_cat_test`

			`Can't connect to llama-swap:`
			`Edit test_setup.py line 10 with correct URL`

			`Embeddings too slow:`
			`Try GPU acceleration (requires spare VRAM)`

			`================================================================================`
			`🧹 CLEANUP`
			`================================================================================`

			`Stop services:`
			`./stop.sh`

			`Remove all data:`
			`docker-compose -f docker-compose.test.yml down -v`

			`================================================================================`
			`📚 DETAILED DOCS`
			`================================================================================`

			`Full guide: cat SETUP_COMPLETE.md`
			`Test docs: cat TEST_README.md`
			`View all files: ls -lah`

			`================================================================================`