Router Configuration:
- Add mode='qa_build' routing rule in router-config.yml
- Priority 8, uses local_qwen3_8b for Q&A generation
2-Stage Q&A Pipeline Tests:
- Create test_qa_pipeline.py with comprehensive tests
- Test prompt building, JSON parsing, router integration
- Mock DAGI Router responses for testing
Region Mode (Grounding OCR):
- Add region_bbox and region_page parameters to ParseRequest
- Support region mode in local_runtime with bbox in prompt
- Update endpoints to accept region parameters (x, y, width, height, page)
- Validate region parameters and filter pages for region mode
- Pass region_bbox through inference pipeline
Updates:
- Update local_runtime to support region_bbox in prompts
- Update inference.py to pass region_bbox to local_runtime
- Update endpoints.py to handle region mode parameters
Prompt Modes Integration:
- Create local_runtime.py with DOTS_PROMPT_MAP
- Map OutputMode to native dots.ocr prompt modes (prompt_layout_all_en, prompt_ocr, etc.)
- Support dict_promptmode_to_prompt from dots.ocr with fallback prompts
- Add layout_only and region modes to OutputMode enum
2-Stage Q&A Pipeline:
- Create qa_builder.py for 2-stage qa_pairs generation
- Stage 1: PARSER (dots.ocr) → raw JSON via prompt_layout_all_en
- Stage 2: LLM (DAGI Router) → Q&A pairs via mode=qa_build
- Update endpoints.py to use 2-stage pipeline for qa_pairs mode
- Add ROUTER_BASE_URL and ROUTER_TIMEOUT to config
Updates:
- Update inference.py to use local_runtime with native prompts
- Update ollama_client.py to use same prompt map
- Add PROMPT_MODES.md documentation
Model Loader:
- Update model_loader.py with complete dots.ocr loading code
- Proper device detection (CUDA/CPU/MPS) with fallback
- Memory optimization (low_cpu_mem_usage)
- Better error handling and logging
- Support for local model paths and HF Hub
Docker:
- Multi-stage Dockerfile (CPU/CUDA builds)
- docker-compose.yml for parser-service
- .dockerignore for clean builds
- Model cache volume for persistence
Configuration:
- Support DOTS_OCR_MODEL_ID and DEVICE env vars (backward compatible)
- Better defaults and environment variable handling
Deployment:
- Add DEPLOYMENT.md with detailed instructions
- Local deployment (venv)
- Docker Compose deployment
- Ollama runtime setup
- Troubleshooting guide
Integration:
- Add parser-service to main docker-compose.yml
- Configure volumes and networks
- Health checks and dependencies
Ollama Runtime:
- Add ollama_client.py for Ollama API integration
- Support for dots-ocr model via Ollama
- Add OLLAMA_BASE_URL configuration
- Update inference.py to support Ollama runtime (RUNTIME_TYPE=ollama)
- Update endpoints to handle async Ollama calls
- Alternative to local transformers model
RAG Implementation Plan:
- Create TODO-RAG.md with detailed Haystack integration plan
- Document Store setup (pgvector)
- Embedding model selection
- Ingest pipeline (PARSER → RAG)
- Query pipeline (RAG → LLM)
- Integration with DAGI Router
- Bot commands (/upload_doc, /ask_doc)
- Testing strategy
Now supports three runtime modes:
1. Local transformers (RUNTIME_TYPE=local)
2. Ollama (RUNTIME_TYPE=ollama)
3. Dummy (USE_DUMMY_PARSER=true)
G.2.5 - Tests:
- Add pytest test suite with fixtures
- test_preprocessing.py - PDF/image loading, normalization, validation
- test_postprocessing.py - chunks, QA pairs, markdown generation
- test_inference.py - dummy parser and inference functions
- test_api.py - API endpoint tests
- Add pytest.ini configuration
G.1.3 - dots.ocr Integration:
- Update model_loader.py with real model loading code
- Support for AutoModelForVision2Seq and AutoProcessor
- Device handling (CUDA/CPU/MPS) with fallback
- Error handling with dummy fallback option
- Update inference.py with real model inference
- Process images through model
- Generate and decode outputs
- Parse model output to blocks
- Add model_output_parser.py
- Parse JSON or plain text model output
- Convert to structured blocks
- Layout detection support (placeholder)
Dependencies:
- Add pytest, pytest-asyncio, httpx for testing
- Mark G.2.3 (PDF/image support) as completed
- Mark G.2.4 (pre/post-processing) as completed
- Mark G.1.3 (configuration) as completed
- All preprocessing and postprocessing functions implemented
- Replace Whisper subprocess calls with direct qwen3_asr_toolkit API
- Remove subprocess dependencies, use pure Python API
- Update to use DASHSCOPE_API_KEY instead of WHISPER_MODEL
- Cleaner code without CLI calls
- Better Ukrainian language recognition quality
- Add STT service with Whisper support (faster-whisper, whisper CLI, OpenAI API)
- Update Gateway to handle Telegram voice/audio/video_note messages
- Add STT service to docker-compose.yml
- Gateway now converts voice → text → DAGI Router → text response
- Remove all FK constraints from models (users, teams, channels, agents)
- Keep fields as optional nullable String for testing DAARWIZZ
- Update SQL migration to remove all REFERENCES
- Fix metadata -> meta in migration
- Allows service to work without base tables for testing
- Remove FK constraint from UserFact.team_id (teams table may not exist)
- Update SQL migration to remove FK constraint
- team_id remains optional String field without FK
- Fix DialogSummary.metadata -> DialogSummary.meta
- Fix AgentMemoryFactsVector.metadata -> AgentMemoryFactsVector.meta
- All metadata fields now renamed to meta
- Rename metadata to meta in all models (UserFact, DialogSummary, AgentMemoryFactsVector)
- Update schemas to use meta instead of metadata
- Update SQL migration to use meta column name
- Fixes SQLAlchemy reserved name conflict
- Add memory-service as a service (not under networks:)
- Create Dockerfile for memory-service
- Configure depends_on city-db with healthcheck condition
- Set DATABASE_URL to connect to city-db
- Move models.py, schemas.py, crud.py, main.py to app/
- Update imports to use app.* prefix
- Update README with new structure
- Fix uvicorn run command for new structure
- Fixed Gateway to extract response from data.text field
- GPU working: RTX 4000 Ada, response time 7-10s (was 30-40s)
- DAARWIZZ now responds correctly with full personality
- Started Memory Service structure
- Update Wallet Service: balance checks (1 DAARION for create, 0.01 for usage)
- Update DAOFactory Service: use new balance checks
- Add DB migration: teams type field and city_links table
- Add DAARION.city seed data
- Create teams API routes with balance validation
- Add DAARION.city remote repository
- Add sync scripts and documentation
- Fixed Gateway: 'prompt' → 'message' field name
- Increased LLM provider timeout from 30s to 60s
- Added OLLAMA-OPTIMIZATION.md with performance tips
- DAARWIZZ now responds (slowly but works)
- Updated gateway-bot/daarwizz_prompt.txt with v3 system prompt
- Created docs/daarwizz/PROFILE.md with complete agent profile
- Defines DAARWIZZ as digital mayor and MoE coordinator
- Specifies communication style, roles, security policies
- Integration with full DAGI Stack (Router, DevTools, CrewAI, RBAC)
- Knowledge base references to official DAARION.city docs
DAARWIZZ - Official AI agent for DAARION.city ecosystem
Changes:
- gateway-bot/daarwizz_prompt.txt: System prompt defining DAARWIZZ personality
- gateway-bot/http_api.py: Load and inject DAARWIZZ context into Router requests
- gateway-bot/Dockerfile: Copy DAARWIZZ prompt file to container
- providers/llm_provider.py: Support context.system_prompt from Gateway
Features:
- Telegram webhook sends agent='daarwizz' to Router
- System prompt loaded from file (customizable)
- LLM receives full DAARWIZZ context + RBAC
- Discord support included
Usage:
- User messages DAARWIZZ in Telegram
- Gateway enriches with system prompt + RBAC
- Router routes to LLM with full context
- DAARWIZZ responds with DAO-aware answers
Next: Set TELEGRAM_BOT_TOKEN and test first dialog
