4601c6fca8
- Vision Encoder Service (OpenCLIP ViT-L/14, GPU-accelerated)
- FastAPI app with text/image embedding endpoints (768-dim)
- Docker support with NVIDIA GPU runtime
- Port 8001, health checks, model info API
- Qdrant Vector Database integration
- Port 6333/6334 (HTTP/gRPC)
- Image embeddings storage (768-dim, Cosine distance)
- Auto collection creation
- Vision RAG implementation
- VisionEncoderClient (Python client for API)
- Image Search module (text-to-image, image-to-image)
- Vision RAG routing in DAGI Router (mode: image_search)
- VisionEncoderProvider integration
- Documentation (5000+ lines)
- SYSTEM-INVENTORY.md - Complete system inventory
- VISION-ENCODER-STATUS.md - Service status
- VISION-RAG-IMPLEMENTATION.md - Implementation details
- vision_encoder_deployment_task.md - Deployment checklist
- services/vision-encoder/README.md - Deployment guide
- Updated WARP.md, INFRASTRUCTURE.md, Jupyter Notebook
- Testing
- test-vision-encoder.sh - Smoke tests (6 tests)
- Unit tests for client, image search, routing
- Services: 17 total (added Vision Encoder + Qdrant)
- AI Models: 3 (qwen3:8b, OpenCLIP ViT-L/14, BAAI/bge-m3)
- GPU Services: 2 (Vision Encoder, Ollama)
- VRAM Usage: ~10 GB (concurrent)
Status: Production Ready ✅
64 lines
2.3 KiB
Python
64 lines
2.3 KiB
Python
"""
|
|
Configuration for PARSER Service
|
|
"""
|
|
|
|
import os
|
|
from typing import Literal, Optional
|
|
from pydantic_settings import BaseSettings
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
"""Application settings"""
|
|
|
|
# Service
|
|
API_HOST: str = "0.0.0.0"
|
|
API_PORT: int = 9400
|
|
|
|
# PARSER Model
|
|
PARSER_MODEL_NAME: str = os.getenv("PARSER_MODEL_NAME", os.getenv("DOTS_OCR_MODEL_ID", "rednote-hilab/dots.ocr"))
|
|
PARSER_DEVICE: Literal["cuda", "cpu", "mps"] = os.getenv("PARSER_DEVICE", os.getenv("DEVICE", "cpu"))
|
|
PARSER_MAX_PAGES: int = int(os.getenv("PARSER_MAX_PAGES", "100"))
|
|
PARSER_MAX_RESOLUTION: str = os.getenv("PARSER_MAX_RESOLUTION", "4096x4096")
|
|
PARSER_BATCH_SIZE: int = int(os.getenv("PARSER_BATCH_SIZE", "1"))
|
|
|
|
# File handling
|
|
MAX_FILE_SIZE_MB: int = int(os.getenv("MAX_FILE_SIZE_MB", "50"))
|
|
TEMP_DIR: str = os.getenv("TEMP_DIR", "/tmp/parser")
|
|
|
|
# PDF processing
|
|
PDF_DPI: int = int(os.getenv("PDF_DPI", "200"))
|
|
PAGE_RANGE: Optional[str] = os.getenv("PAGE_RANGE", None) # e.g., "1-20" for pages 1-20
|
|
|
|
# Image processing
|
|
IMAGE_MAX_SIZE: int = int(os.getenv("IMAGE_MAX_SIZE", "2048")) # Max size for longest side
|
|
|
|
# Parser mode
|
|
USE_DUMMY_PARSER: bool = os.getenv("USE_DUMMY_PARSER", "false").lower() == "true"
|
|
ALLOW_DUMMY_FALLBACK: bool = os.getenv("ALLOW_DUMMY_FALLBACK", "true").lower() == "true"
|
|
|
|
# Runtime
|
|
RUNTIME_TYPE: Literal["local", "remote", "ollama"] = os.getenv("RUNTIME_TYPE", "local")
|
|
RUNTIME_URL: str = os.getenv("RUNTIME_URL", "http://parser-runtime:11435")
|
|
|
|
# Ollama configuration (if RUNTIME_TYPE=ollama)
|
|
OLLAMA_BASE_URL: str = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
|
|
|
|
# DAGI Router configuration (for qa_pairs 2-stage pipeline)
|
|
ROUTER_BASE_URL: str = os.getenv("ROUTER_BASE_URL", "http://router:9102")
|
|
ROUTER_TIMEOUT: int = int(os.getenv("ROUTER_TIMEOUT", "60"))
|
|
|
|
# RAG Service configuration (for ingest pipeline)
|
|
RAG_BASE_URL: str = os.getenv("RAG_BASE_URL", "http://rag-service:9500")
|
|
RAG_TIMEOUT: int = int(os.getenv("RAG_TIMEOUT", "120"))
|
|
|
|
# NATS JetStream configuration
|
|
NATS_URL: str = os.getenv("NATS_URL", "nats://localhost:4222")
|
|
|
|
class Config:
|
|
env_file = ".env"
|
|
case_sensitive = True
|
|
|
|
|
|
settings = Settings()
|
|
|